title_s
stringlengths 2
79
| title_dl
stringlengths 0
200
| source_url
stringlengths 13
64
| authors
listlengths 0
10
| snippet_s
stringlengths 0
291
| text
stringlengths 21
100k
| date
timestamp[ns]date 1926-02-14 00:00:00
2030-07-14 00:00:00
| publish_date_dl
stringlengths 0
10
| url
stringlengths 15
590
| matches
listlengths 1
278
|
|---|---|---|---|---|---|---|---|---|---|
How AI and Workforce will Intersect: Navigating Risks and ... - Aon
|
How AI and Workforce will Intersect: Navigating Risks and Opportunities
|
https://www.aon.com
|
[
"Matt Chmel",
"Chief Broking Officer",
"Cyber Solutions",
"North America",
"Suzanne Courtney",
"Associate Partner",
"Talent Solutions",
"Europe",
"The Middle East",
"Aon S Thought Leaders"
] |
Amid rapid technology advancements, AI is reshaping the workforce and creating new roles and skill demands. Organizations must simultaneously harness AI's ...
|
AI Revolutionizes Workforce Dynamics and Skill Demands
Human resources is at the forefront of artificial intelligence (AI) utilization, pioneering advancements that blend technology with human insight. Teams are already using AI to optimize a host of processes, including the automation of tasks like interview scheduling, onboarding and addressing employee requests. HR professionals are generating tailored reward packages, updating recommendations in real-time, managing learning paths and creating interactive skill development simulations.
"AI may not replace HR professionals, but those with AI skills will have an advantage over those without,” says Ernest Paskey, head of Workforce Transformation Advisory at Aon. “The challenge for companies is acquiring these skills quickly."
To date, most organizations have concentrated their use of AI on making these incremental improvements to optimize existing processes rather than reimagining how they could operate. However, as AI capabilities advance over the next five years, these organizations will likely shift to reinventing entire workflows and job functions.1
| 2023-01-01T00:00:00 |
https://www.aon.com/en/insights/client-trends/workforce-technology?collection=c9c875df-cc88-40ca-9a86-547c82a0d6d4
|
[
{
"date": "2023/01/01",
"position": 34,
"query": "AI workforce transformation"
},
{
"date": "2023/11/01",
"position": 32,
"query": "AI workforce transformation"
},
{
"date": "2024/01/01",
"position": 99,
"query": "AI workforce transformation"
},
{
"date": "2024/09/01",
"position": 98,
"query": "AI workforce transformation"
},
{
"date": "2024/11/01",
"position": 32,
"query": "AI workforce transformation"
},
{
"date": "2024/12/01",
"position": 30,
"query": "AI workforce transformation"
},
{
"date": "2025/04/03",
"position": 53,
"query": "workplace AI adoption"
}
] |
|
AI in the workplace: Digital labor and the future of work - IBM
|
AI in the Workplace
|
https://www.ibm.com
|
[] |
AI-assisted software and apps can transform the HR process by streamlining recruitment, improving employee engagement and enhancing workforce management. This ...
|
Artificial intelligence (AI) is transforming the workplace, impacting how businesses operate and how employees do their jobs. The technology is expected to significantly impact the global economy by transforming the labor market and changing the nature of work.
Organizations use AI in the workplace by deploying a wide range of technologies, including machine learning and natural language processing, that can mimic human intelligence to solve problems, make decisions and perform tasks traditionally handled by humans. AI can analyze data, recognize patterns, learn from experience and adapt over time. It is often used to streamline operations, enhance productivity, automate repetitive tasks and support decision-making.
Generally, deploying AI in the workplace involves a wide ecosystem of technologies, the most common of which are:
Machine learning: A branch of computer science that focuses on using algorithms to allow AI to imitate the way humans learn, gradually improving its functionality over time.
Natural language processing (NLP): A form of AI that uses machine learning to understand and communicate in human language.
Generative AI: A form of AI recently popularized by ChatGPT that can create original content in response to a user’s request.
Robotic Process Automation (RPA): A process-driven intelligent automation technology often used to perform repetitive office tasks.
Using a combination of these technologies, deploying AI in the workplace might be as simple as automatically digitizing and filing employee records, or translating Spanish into English. It might be as complex as providing decision-makers with guidance on how to improve a company’s business processes enterprise-wide.
In the healthcare, insurance and banking industries, AI has become increasingly common. Examples include helping researchers identify new drug compounds and predict their effectiveness, or assisting cybersecurity professionals identify and mitigate fraud. AI is also routinely used to enhance employee and customer experiences through AI assistants, such as chatbots and AI agents.
| 2023-01-01T00:00:00 |
https://www.ibm.com/think/topics/ai-in-the-workplace
|
[
{
"date": "2023/01/01",
"position": 39,
"query": "AI workforce transformation"
},
{
"date": "2023/01/01",
"position": 45,
"query": "artificial intelligence workers"
},
{
"date": "2023/02/01",
"position": 96,
"query": "AI workforce transformation"
},
{
"date": "2023/02/01",
"position": 42,
"query": "artificial intelligence workers"
},
{
"date": "2023/03/01",
"position": 92,
"query": "AI workforce transformation"
},
{
"date": "2023/03/01",
"position": 51,
"query": "workplace AI adoption"
},
{
"date": "2023/04/01",
"position": 69,
"query": "artificial intelligence workers"
},
{
"date": "2023/04/01",
"position": 53,
"query": "workplace AI adoption"
},
{
"date": "2023/05/01",
"position": 96,
"query": "AI workforce transformation"
},
{
"date": "2023/05/01",
"position": 53,
"query": "workplace AI adoption"
},
{
"date": "2023/06/01",
"position": 53,
"query": "workplace AI adoption"
},
{
"date": "2023/07/01",
"position": 89,
"query": "AI workforce transformation"
},
{
"date": "2023/07/01",
"position": 56,
"query": "workplace AI adoption"
},
{
"date": "2023/08/01",
"position": 62,
"query": "artificial intelligence workers"
},
{
"date": "2023/09/01",
"position": 100,
"query": "AI workforce transformation"
},
{
"date": "2023/09/01",
"position": 69,
"query": "artificial intelligence workers"
},
{
"date": "2023/09/01",
"position": 57,
"query": "workplace AI adoption"
},
{
"date": "2023/11/01",
"position": 42,
"query": "AI workforce transformation"
},
{
"date": "2023/11/01",
"position": 57,
"query": "artificial intelligence workers"
},
{
"date": "2023/12/01",
"position": 100,
"query": "AI workforce transformation"
},
{
"date": "2023/12/01",
"position": 53,
"query": "workplace AI adoption"
},
{
"date": "2024/01/01",
"position": 96,
"query": "AI workforce transformation"
},
{
"date": "2024/01/01",
"position": 64,
"query": "artificial intelligence workers"
},
{
"date": "2024/01/01",
"position": 53,
"query": "workplace AI adoption"
},
{
"date": "2024/02/01",
"position": 69,
"query": "AI employment"
},
{
"date": "2024/02/01",
"position": 93,
"query": "AI workforce transformation"
},
{
"date": "2024/03/01",
"position": 96,
"query": "AI workforce transformation"
},
{
"date": "2024/03/01",
"position": 9,
"query": "artificial intelligence workers"
},
{
"date": "2024/03/01",
"position": 53,
"query": "workplace AI adoption"
},
{
"date": "2024/05/01",
"position": 53,
"query": "workplace AI adoption"
},
{
"date": "2024/06/01",
"position": 29,
"query": "AI workers"
},
{
"date": "2024/06/01",
"position": 52,
"query": "workplace AI adoption"
},
{
"date": "2024/07/01",
"position": 70,
"query": "artificial intelligence workers"
},
{
"date": "2024/07/01",
"position": 53,
"query": "workplace AI adoption"
},
{
"date": "2024/08/01",
"position": 86,
"query": "AI workforce transformation"
},
{
"date": "2024/09/01",
"position": 95,
"query": "AI workforce transformation"
},
{
"date": "2024/10/01",
"position": 96,
"query": "AI workforce transformation"
},
{
"date": "2024/10/01",
"position": 51,
"query": "workplace AI adoption"
},
{
"date": "2024/11/01",
"position": 19,
"query": "AI workforce transformation"
},
{
"date": "2024/11/01",
"position": 53,
"query": "workplace AI adoption"
},
{
"date": "2024/12/01",
"position": 16,
"query": "AI workforce transformation"
},
{
"date": "2024/12/01",
"position": 56,
"query": "workplace AI adoption"
},
{
"date": "2025/01/01",
"position": 56,
"query": "workplace AI adoption"
},
{
"date": "2025/02/01",
"position": 17,
"query": "machine learning workforce"
},
{
"date": "2025/03/01",
"position": 70,
"query": "AI workforce transformation"
},
{
"date": "2025/03/01",
"position": 15,
"query": "machine learning workforce"
},
{
"date": "2025/03/01",
"position": 59,
"query": "workplace AI adoption"
},
{
"date": "2025/04/01",
"position": 16,
"query": "machine learning workforce"
},
{
"date": "2025/05/01",
"position": 79,
"query": "AI workforce transformation"
},
{
"date": "2025/05/01",
"position": 48,
"query": "artificial intelligence workers"
},
{
"date": "2025/06/01",
"position": 86,
"query": "AI workforce transformation"
},
{
"date": "2025/06/01",
"position": 44,
"query": "artificial intelligence workers"
}
] |
|
SHRM Report Warns of Widening Skills Gap as AI Adoption ...
|
SHRM Report Warns of Widening Skills Gap as AI Adoption Reaches Nearly Half of U.S. Workforce
|
https://www.shrm.org
|
[] |
AI is transforming how work gets done, presenting organizations with unparalleled opportunities for efficiency and innovation. However, with ...
|
Alexandria, VA – Today, SHRM, the trusted authority on all things work, workers, and the workplace, released new findings on the growing role of artificial intelligence (AI) in the modern workplace. SHRM’s newest report, From Adoption to Empowerment: Shaping the AI-Driven Workforce of Tomorrow, emphasizes the critical role of human oversight, as well as underscores the importance of upskilling and reskilling employees to harness AI's full potential.
AI is transforming how work gets done, presenting organizations with unparalleled opportunities for efficiency and innovation. However, with these opportunities come new challenges, such as addressing skills gaps, ensuring ethical oversight, and aligning AI adoption with strategic priorities.
Key findings include:
AI adoption is rising, but disparities persist: While nearly 45% of U.S. workers reported using AI in their jobs, adoption rates vary significantly across generations, industries, and genders. Millennials lead usage at 56%, while only 25% of Baby Boomers reported engaging with AI tools.
Improved work outcomes: The report found 77% of workers using AI said it helped them accomplish more in less time. 73% of workers said it improved the quality of their work.
Training and upskilling are vital for success: More than half of workers (51%) identified enhanced training as the top priority for improving AI outcomes, underscoring the importance of workforce preparedness. Satisfaction with training is strongly related to successful AI adoption.
The importance of collaboration: Nearly three-quarters of workers (74%) agreed AI should be a complement to human talent, while strong majorities emphasized the need for oversight and collaboration.
“As AI continues to reshape the way work is done, it’s imperative we approach its integration thoughtfully and ethically,” said Alex Alonso, SHRM Chief Data & Analytics Officer. “HR professionals are at the forefront of this transformation, equipping workforces with the skills needed to thrive in an AI-driven environment while ensuring innovation aligns with organizational values.”
Additionally, the report found the way organizations integrate AI and human intelligence (AI+HI) into business goals plays a critical role in driving satisfaction with learning and development initiatives. Among workers who rated their organization’s AI+HI integration as excellent, 97% were satisfied with training opportunities. In contrast, only 21% of those who rated integration as fair and 18% of those who rated integration as poor were satisfied with the training available to them.
With AI steadily reshaping how we work, the task of preparing the workforce becomes both urgent and complex. Organizations must implement strategies to not only drive technological integration but also to empower employees to adapt, reskill, and thrive in AI-driven environments. SHRM is committed to equipping HR professionals and organizations with the tools and insights needed to navigate this transformation successfully.
Methodology
U.S. workers : A sample of 1,812 U.S.-based workers were surveyed on Jan. 10, 2025, using a third-party online panel. For the purposes of this study, participants were required to be employed by an organization. Those who were self-employed, retired, or an independent contractor did not qualify. Participants represent organizations across multiple types of industries, sectors, sizes, and locations. Data is unweighted.
HR professionals : A sample of 1,970 HR professionals were surveyed from Jan. 15 to Jan. 21, 2025, using the SHRM Voice of Work Research Panel. Participants represent organizations across multiple types of industries, sectors, sizes, and locations. Data is unweighted.
About SHRM
SHRM is a member-driven catalyst for creating better workplaces where people and businesses thrive together. As the trusted authority on all things work, SHRM is the foremost expert, researcher, advocate, and thought leader on issues and innovations impacting today’s evolving workplaces. With nearly 340,000 members in 180 countries, SHRM touches the lives of more than 362 million workers and their families globally. Discover more at SHRM.org.
| 2023-01-01T00:00:00 |
https://www.shrm.org/about/press-room/shrm-report-warns-of-widening-skills-gap-as-ai-adoption-reaches-
|
[
{
"date": "2023/01/01",
"position": 40,
"query": "AI workforce transformation"
},
{
"date": "2023/01/01",
"position": 60,
"query": "AI workers"
},
{
"date": "2023/02/01",
"position": 56,
"query": "AI skills gap"
},
{
"date": "2023/03/01",
"position": 58,
"query": "AI workers"
},
{
"date": "2023/05/01",
"position": 62,
"query": "AI skills gap"
},
{
"date": "2023/06/01",
"position": 61,
"query": "AI skills gap"
},
{
"date": "2023/08/01",
"position": 64,
"query": "AI skills gap"
},
{
"date": "2023/10/01",
"position": 64,
"query": "AI skills gap"
},
{
"date": "2023/11/01",
"position": 45,
"query": "AI workforce transformation"
},
{
"date": "2023/12/01",
"position": 73,
"query": "AI skills gap"
},
{
"date": "2024/02/01",
"position": 64,
"query": "AI skills gap"
},
{
"date": "2024/03/01",
"position": 73,
"query": "artificial intelligence workers"
},
{
"date": "2024/04/01",
"position": 71,
"query": "AI skills gap"
},
{
"date": "2024/07/01",
"position": 61,
"query": "AI skills gap"
},
{
"date": "2024/08/01",
"position": 63,
"query": "AI skills gap"
},
{
"date": "2024/09/01",
"position": 64,
"query": "AI skills gap"
},
{
"date": "2024/11/01",
"position": 38,
"query": "AI workforce transformation"
},
{
"date": "2024/12/01",
"position": 36,
"query": "AI workforce transformation"
},
{
"date": "2025/01/01",
"position": 71,
"query": "AI skills gap"
},
{
"date": "2025/02/01",
"position": 57,
"query": "AI skills gap"
},
{
"date": "2025/03/01",
"position": 58,
"query": "AI skills gap"
},
{
"date": "2025/05/01",
"position": 60,
"query": "AI skills gap"
}
] |
|
Generative AI for the Workforce - KPMG International
|
Generative AI for the Workforce
|
https://kpmg.com
|
[] |
Find out why businesses should not treat this transformation as merely a technology upgrade.
|
Generative AI success requires workforce remodel Download the full report
To realize the most value from generative AI, organizations need to rethink how their people work. That is because adopting it is not simply about upgrading to the latest technology–it is about using generative AI’s revolutionary capabilities across the enterprise to create more productive, efficient, and innovative workers.
With a well-constructed plan, organizations have an opportunity to define the workforce of the future and draw top talent to a best-in-class professional development environment employing leading-edge technology and work practices.
| 2023-08-30T00:00:00 |
2023/08/30
|
https://kpmg.com/us/en/articles/2023/generative-ai-human-capital.html
|
[
{
"date": "2023/01/01",
"position": 42,
"query": "AI workforce transformation"
},
{
"date": "2023/02/01",
"position": 95,
"query": "AI workforce transformation"
},
{
"date": "2023/03/01",
"position": 81,
"query": "AI workforce transformation"
},
{
"date": "2023/05/01",
"position": 88,
"query": "AI workforce transformation"
},
{
"date": "2023/07/01",
"position": 67,
"query": "AI workforce transformation"
},
{
"date": "2023/09/19",
"position": 52,
"query": "AI employment"
},
{
"date": "2023/09/01",
"position": 61,
"query": "AI workforce transformation"
},
{
"date": "2023/11/01",
"position": 36,
"query": "AI workforce transformation"
},
{
"date": "2023/12/01",
"position": 60,
"query": "AI workforce transformation"
},
{
"date": "2024/01/01",
"position": 57,
"query": "AI workforce transformation"
},
{
"date": "2024/02/01",
"position": 91,
"query": "AI workforce transformation"
},
{
"date": "2024/03/01",
"position": 95,
"query": "AI workforce transformation"
},
{
"date": "2024/08/01",
"position": 62,
"query": "AI workforce transformation"
},
{
"date": "2024/09/01",
"position": 55,
"query": "AI workforce transformation"
},
{
"date": "2024/10/01",
"position": 60,
"query": "AI workforce transformation"
},
{
"date": "2024/11/01",
"position": 36,
"query": "AI workforce transformation"
},
{
"date": "2024/12/01",
"position": 67,
"query": "AI workforce transformation"
},
{
"date": "2025/01/01",
"position": 91,
"query": "AI workforce transformation"
},
{
"date": "2025/03/01",
"position": 64,
"query": "AI workforce transformation"
},
{
"date": "2025/05/01",
"position": 98,
"query": "AI workforce transformation"
}
] |
AI Workforce Transformation | Reengineer Work - Reejig
|
AI Workforce Transformation
|
https://www.reejig.com
|
[] |
Reejig helps businesses re-engineer jobs, workflows, and processes to create a future-ready workforce, integrating AI in a way that maximizes both human and ...
|
Don't Just Take Our Word For It
Reejig is trusted by industry leaders across the globe to revolutionize workforce strategies and drive AI-powered transformation. Here’s what some of our customers have to say:
| 2023-01-01T00:00:00 |
https://www.reejig.com/platform/re-engineer-work
|
[
{
"date": "2023/01/01",
"position": 58,
"query": "AI workforce transformation"
},
{
"date": "2023/11/01",
"position": 60,
"query": "AI workforce transformation"
},
{
"date": "2024/11/01",
"position": 65,
"query": "AI workforce transformation"
},
{
"date": "2024/12/01",
"position": 57,
"query": "AI workforce transformation"
}
] |
|
Amazon's AI-Driven Workforce Transformation: A New Era ... - AInvest
|
Amazon's AI-Driven Workforce Transformation: A New Era of Corporate Efficiency
|
https://www.ainvest.com
|
[
"Harrison Brooks",
"I'M Your Ai Uk Business Scout",
"Tracking Boardroom Dramas",
"Industry Shakeups With A Dry Wit",
"Sharper Analysis."
] |
Amazon's AI-Driven Workforce Transformation: A New Era of Corporate Efficiency. Harrison BrooksMonday, Jun 30, 2025 8:26 pm ET. 38min read.
|
In the annals of corporate evolution, few shifts rival the scale of Amazon's current transformation. Over the past three years, the company has shed more than 27,000 jobs—a move that has sent shudders through the workforce—while pouring $105 billion into AI technologies like AWS, Bedrock, and Claude. The strategy, marked by a ruthless focus on efficiency, is not merely about cutting costs but redefining how work itself is done. For investors, this is a paradigm shift: Amazon's AI-driven restructuring is a bold bet on long-term value creation, one that could outpace rivals like Microsoft and NVIDIA in the AI arms race.
The Workforce Restructuring: From Layoffs to Efficiency Gains
The layoffs have been both sweeping and strategic. Amazon has targeted middle management (13% of global managers cut by early 2025), customer service, and administrative roles—positions where AI can now handle routine tasks. Warehouse operations, too, are being automated, with AI optimizing inventory placement and robotics efficiency. But this is not just about cutting heads. Amazon is reallocating resources to AI talent, aiming to increase the ratio of individual contributors to managers by 15%. Internal tools, such as coding assistants, have already saved “4,500 years of work” by automating boilerplate code.
The result? A stark financial turnaround. Operating income surged 86% to $68.6 billion in 2024, driven by margin expansion from AI efficiencies. The “cost to serve” metric—Amazon's measure of operational efficiency—is a clear priority, with AI reducing expenses in logistics and customer service.
The Strategic Play: High-Margin AI Products and Market Dominance
The real prize lies in Amazon's AI product ecosystem. AWS, already the cloud leader, is leveraging AI to offer advanced services like Bedrock, which competes with Microsoft's Azure AI and NVIDIA's HPC offerings. These tools are not just cost-cutting levers but revenue engines. For instance, AWS AI services command premium pricing, with enterprises willing to pay for scalable, reliable infrastructure.
Meanwhile, Amazon's consumer-facing AI—like Alexa+—is transforming customer engagement, reducing support costs while boosting stickiness. The goal is clear: out-innovate competitors by embedding AI into every layer of the business.
A Sector-Wide Shift: Amazon's Lead in the AI Revolution
Amazon is not alone in this transition. Microsoft and Meta have also slashed headcounts and invested heavily in AI, signaling a broader industry shift. Yet Amazon's head start in AI infrastructure (AWS) and its aggressive reallocation of capital give it an edge. Consider this: while Microsoft's stock price has risen steadily, Amazon's AI-driven margin growth could position it as the sector's most efficient operator.
Risks on the Horizon: Regulation and Talent Retention
Of course, risks loom. Regulatory scrutiny of AI's societal impact—particularly around job displacement and DEI—could slow adoption. Talent attrition is another concern: 47% of Amazon employees fear AI will replace 30% of their work within a year, raising turnover risks. Executing seamless AI integration without disrupting operations is no small feat.
Yet these challenges are manageable. Amazon's internal reskilling programs and focus on high-value roles (data science, AI management) address the talent issue, while its scale and cash reserves buffer against regulatory headwinds.
Investment Considerations: A Buy Signal for the Long Game
For investors, the near-term layoffs and workforce anxiety may seem daunting. But the data tells a compelling story: margin expansion is real, and AI-driven products are scaling. A “buy” rating is warranted here. Key catalysts include:
Sustained margin growth: Amazon's operating income trajectory (up 86% in 2024) suggests further upside. Competitive differentiation: AWS and Bedrock are not just cost savers but revenue generators. Reskilling success: If Amazon retains top talent in AI and data roles, execution risks diminish.
While regulatory or technical stumbles could stall progress, the broader trend is undeniable: AI is the new oil, and Amazon is refining it better than most.
Conclusion: The Future of Work, Powered by AI
Amazon's transformation is a masterclass in reimagining work for the AI age. Layoffs are painful, but they are a necessary step toward a leaner, smarter enterprise. The company's focus on high-margin AI products and operational efficiency positions it to dominate a market increasingly defined by automation. For investors, the pain today is a down payment on tomorrow's returns.
The message from Amazon is clear: adapt or be left behind. And for those willing to look past the layoffs, the payoff could be historic.
| 2023-01-01T00:00:00 |
https://www.ainvest.com/news/amazon-ai-driven-workforce-transformation-era-corporate-efficiency-2507/
|
[
{
"date": "2023/01/01",
"position": 61,
"query": "AI workforce transformation"
},
{
"date": "2023/11/01",
"position": 70,
"query": "AI workforce transformation"
},
{
"date": "2024/11/01",
"position": 62,
"query": "AI workforce transformation"
},
{
"date": "2024/12/01",
"position": 77,
"query": "AI workforce transformation"
}
] |
|
AI Impact on Jobs: Workforce Changes & Key Metrics
|
AI Impact on Jobs: Workforce Changes & Key Metrics
|
https://www.zinfi.com
|
[] |
AI Impact on Jobs: Metrics for Measuring Workforce Transformation. Artificial Intelligence (AI) is transforming the job market. The AI impact on jobs is evident ...
|
Artificial Intelligence (AI) is transforming the job market. The AI impact on jobs is evident as it automates tasks, enhances efficiency, and creates new roles. While AI adoption offers numerous opportunities, it also raises concerns about job displacement and evolving skill demands. To navigate these changes, organizations must measure the AI impact on jobs by tracking productivity, workforce adaptability, and skill evolution.
This article explores key metrics to assess the AI impact on jobs, providing businesses with insights to manage AI integration effectively. Companies can utilize these indicators to train employees, implement AI ethically, and stay competitive in an evolving job landscape. Understanding AI-driven workforce transformations enables organizations to anticipate challenges and equip their employees with the necessary skills for future success.
Additionally, AI is transforming industries at an accelerated rate. AI-driven automation reshapes businesses ' operations from healthcare and finance to manufacturing and retail. Companies that fail to adapt to these changes risk falling behind. Therefore, tracking AI’s workforce impact is critical for long-term success.
AI is also influencing business decision-making processes. Companies can anticipate industry trends, customer behaviors, and internal workforce needs with predictive analytics and machine learning. AI enhances current job functions and creates new opportunities for data-driven decision-making. To get the most out of AI, companies should develop simple ways to measure its effect on jobs and workforce performance.
The Need for Metrics in AI Workforce Transformation
AI is reshaping industries. AI impact on jobs differs across sectors. Metrics help organizations measure productivity, job shifts, and skill evolution.
They also track trends and guide workforce strategies. AI can replace routine jobs but also creates opportunities for new roles in technology, analytics, and customer experience.
Businesses can use metrics to manage workforce transformation and refine AI strategies effectively. They can also ensure ethical AI use, preventing unnecessary job displacement while fostering career growth. Businesses must also understand that AI integration is about replacing jobs and augmenting human intelligence and capabilities. AI helps employees become more efficient, handle complex problems, and develop innovative solutions.
Industries that effectively integrate AI will see rapid advancements in efficiency and scalability. For example, the retail sector has leveraged AI-driven automation for inventory management, customer engagement, and supply chain optimization. Similarly, AI-powered diagnostic tools help doctors provide faster and more accurate treatments in the medical field.
Furthermore, AI plays a crucial role in fields like cybersecurity, which helps detect and prevent cyber threats in real time. AI personalizes learning experiences in education, making it easier for students to grasp complex concepts. As these advancements continue, the need for precise metrics to evaluate their workforce impact grows stronger.
Tracking AI’s impact is also essential in government and policy-making. Governments need reliable data to assess how AI influences employment rates, job displacement, and economic development. Governments and businesses should collaborate to develop policies that create AI-driven jobs while reducing employment risks.
Key Areas of Focus
Organizations must measure AI’s impact in three main areas:
Workforce Productivity: AI improves efficiency and output. Employees can focus on strategic tasks instead of repetitive ones. AI-driven automation helps businesses scale operations without additional labor costs. Skill Evolution: Employees must acquire new competencies to adjust to AI-driven workplace transformations effectively. The integration of AI significantly redefines the demand for technical expertise, particularly in data analysis, machine learning, and problem-solving. Organizations must develop training programs to upskill their workforce and remain competitive in an AI-driven world. Economic Impact: AI affects labor costs, job creation, and business profitability. Companies must track whether AI implementation leads to cost savings, increased efficiency, or higher revenues. Understanding these economic trends will help businesses optimize AI adoption without negatively impacting their workforce. Job Satisfaction and Employee Retention: Organizations should assess how AI adoption influences employee morale and retention rates. Organizations that implement AI without proper workforce alignment risk losing valuable talent. Regulatory Compliance and Ethical Use: Businesses must ensure their AI systems comply with labor laws and ethical standards. AI bias and discrimination are growing concerns. Organizations must monitor AI’s hiring, pay, and job distribution fairness.
Metrics for Measuring AI Impact on Jobs
Productivity Metrics
AI makes processes faster and more accurate. Key productivity metrics include:
Output per Employee: Measures how much work employees complete in a given time. AI tools like robotic automation improve efficiency in manufacturing and customer service. Time Saved per Task: Tracks time reductions after AI adoption. Chatbots, for example, handle customer inquiries faster. AI-driven scheduling tools optimize workflow management. Error Reduction Rate: Measures how AI reduces mistakes. AI-powered diagnostic tools improve healthcare accuracy and reduce errors. In financial services, AI-driven risk assessments minimize costly human errors. Task Automation Rate: This shows the percentage of tasks AI handles without human intervention. A higher rate indicates better AI efficiency and reduced manual workload. Process Optimization Index: Evaluate how AI-driven systems improve operational workflows. Businesses that optimize AI processes often experience lower overhead costs and improved service quality. Cost Efficiency Score: Tracks operational reductions due to AI adoption, comparing pre- and post-AI implementation expenses.
Workforce Adaptability Metrics
Employees must learn new skills to work with AI. Key adaptability metrics include:
Training Completion Rates: Measure how many employees complete AI training programs. High rates show workforce readiness. AI-driven training modules improve learning experiences. Role Transition Success Rate: Tracks how well employees move into AI-assisted roles. Employees are transitioning from manual data entry to AI-powered data analysis systems. Companies should track how long transitions take and their overall success. Employee Satisfaction Scores: Measure how employees feel about AI integration. High scores indicate smooth adoption and minimal resistance. Measuring engagement levels during AI rollouts helps determine long-term acceptance. Change Management Index: Evaluates how well companies manage AI-driven changes. This metric considers employee feedback, leadership support, and adoption speed. Employee Collaboration Index: Measures the effectiveness of human-AI collaboration. Employees must learn to work alongside AI tools rather than against them. Workforce Flexibility Rate: Assesses how easily employees can adapt to AI-driven changes and transition between roles.
Skill Demand Metrics
AI changes which skills are in demand. Businesses must track:
Emerging Skill Index: Measures demand for machine learning and data analytics skills. Python programming is in high demand due to AI-driven projects. AI literacy and ethical AI training are also becoming essential. Skill Gap Analysis: Compares current workforce skills with AI requirements. This helps businesses prioritize training programs. Recognizing skill gaps early helps prevent workforce shortages and ensures a smoother transition to AI-driven roles. Upskilling ROI: Evaluate training effectiveness. It measures productivity improvements against training costs. Companies should assess whether AI-focused training leads to career progression. AI Certification Rate: Tracks how many employees complete AI-related certification programs. Higher certification rates indicate a workforce prepared for AI-integrated environments. Innovation Readiness Score: Assesses how well employees can develop and implement AI-driven solutions within their roles. AI Adoption Knowledge Index: Measures how well employees understand AI-related tasks and processes.
Conclusion
Measuring the AI impact on jobs helps businesses understand how AI is changing the workforce. Tracking productivity, skills, and economic implications allows companies to implement AI responsibly. Organizations that embrace AI while ensuring workforce adaptability will thrive in the evolving job market.
Using data-driven AI strategies ensures innovation, ethical practices, and long-term workforce success. As AI changes, businesses must monitor its effect on jobs and invest in their employees to stay competitive. Companies that do not assess AI’s influence may struggle to remain competitive in a rapidly evolving market.
Integrating AI into the workforce helps improve productivity, drive innovation, and support long-term economic growth. The organizations that succeed will be those that focus on both technological advancements and workforce empowerment.
Read our article on "How to Adapt to AI Impact on Jobs."
| 2025-02-17T00:00:00 |
2025/02/17
|
https://www.zinfi.com/blog/ai-impact-on-jobs-workforce-metrics/
|
[
{
"date": "2023/01/01",
"position": 65,
"query": "AI workforce transformation"
},
{
"date": "2023/02/01",
"position": 94,
"query": "AI workforce transformation"
},
{
"date": "2023/07/01",
"position": 98,
"query": "AI workforce transformation"
},
{
"date": "2023/09/01",
"position": 89,
"query": "AI workforce transformation"
},
{
"date": "2023/11/01",
"position": 62,
"query": "AI workforce transformation"
},
{
"date": "2023/12/01",
"position": 89,
"query": "AI workforce transformation"
},
{
"date": "2024/01/01",
"position": 84,
"query": "AI workforce transformation"
},
{
"date": "2024/02/01",
"position": 92,
"query": "AI workforce transformation"
},
{
"date": "2024/03/01",
"position": 94,
"query": "AI workforce transformation"
},
{
"date": "2024/08/01",
"position": 91,
"query": "AI workforce transformation"
},
{
"date": "2024/09/01",
"position": 84,
"query": "AI workforce transformation"
},
{
"date": "2024/10/01",
"position": 87,
"query": "AI workforce transformation"
},
{
"date": "2024/11/01",
"position": 69,
"query": "AI workforce transformation"
},
{
"date": "2024/12/01",
"position": 56,
"query": "AI workforce transformation"
},
{
"date": "2025/01/01",
"position": 90,
"query": "AI workforce transformation"
},
{
"date": "2025/05/01",
"position": 99,
"query": "AI workforce transformation"
},
{
"date": "2025/06/01",
"position": 99,
"query": "AI workforce transformation"
}
] |
Workforce transformation: A skills-based, AI-driven approach
|
Workforce transformation: A skills-based, AI-driven approach
|
https://eightfold.ai
|
[] |
Workforce transformation: A skills-based, AI-driven approach. How to embrace a new talent code that enables TA and HR leaders to unlock the potential of their ...
|
What every leader needs to know about responsible AI
Responsible AI is more than a compliance checkbox. It’s a strategic imperative for building trust, driving innovation, and shaping the future of work.
Why responsible AI is your competitive advantage →
| 2023-01-01T00:00:00 |
https://eightfold.ai/learn/workforce-transformation-a-skills-based-ai-driven-approach/
|
[
{
"date": "2023/01/01",
"position": 68,
"query": "AI workforce transformation"
},
{
"date": "2023/02/01",
"position": 32,
"query": "AI workforce transformation"
},
{
"date": "2023/03/01",
"position": 34,
"query": "AI workforce transformation"
},
{
"date": "2023/05/01",
"position": 33,
"query": "AI workforce transformation"
},
{
"date": "2023/07/01",
"position": 38,
"query": "AI workforce transformation"
},
{
"date": "2023/09/01",
"position": 33,
"query": "AI workforce transformation"
},
{
"date": "2023/10/01",
"position": 35,
"query": "AI workforce transformation"
},
{
"date": "2023/11/01",
"position": 71,
"query": "AI workforce transformation"
},
{
"date": "2023/12/01",
"position": 33,
"query": "AI workforce transformation"
},
{
"date": "2024/01/01",
"position": 32,
"query": "AI workforce transformation"
},
{
"date": "2024/02/01",
"position": 33,
"query": "AI workforce transformation"
},
{
"date": "2024/03/01",
"position": 34,
"query": "AI workforce transformation"
},
{
"date": "2024/08/01",
"position": 32,
"query": "AI workforce transformation"
},
{
"date": "2024/09/01",
"position": 33,
"query": "AI workforce transformation"
},
{
"date": "2024/10/01",
"position": 33,
"query": "AI workforce transformation"
},
{
"date": "2024/11/01",
"position": 81,
"query": "AI workforce transformation"
},
{
"date": "2024/12/01",
"position": 79,
"query": "AI workforce transformation"
},
{
"date": "2025/01/01",
"position": 34,
"query": "AI workforce transformation"
},
{
"date": "2025/03/01",
"position": 36,
"query": "AI workforce transformation"
},
{
"date": "2025/05/01",
"position": 37,
"query": "AI workforce transformation"
},
{
"date": "2025/06/01",
"position": 37,
"query": "AI workforce transformation"
}
] |
|
The Transformation of the Workforce Through Artificial Intelligence
|
The Transformation of the Workforce Through Artificial Intelligence
|
https://www.allegisglobalsolutions.com
|
[] |
The Transformation of the Workforce Through Artificial Intelligence. In 1989, moviegoers across the world watched in awe as Marty McFly and Doc Brown jumped ...
|
The Transformation of the Workforce Through Artificial Intelligence
In 1989, moviegoers across the world watched in awe as Marty McFly and Doc Brown jumped aboard the DeLorean time machine and travelled to the year 2015 in Back to the Future Part II.
It’s hard to believe 26 years have passed since the film hit our screens and what once seemed a far-off future has become the here and now. At first glance, director Robert Zemeckis’ vision of 2015 - flying cars and all - might seem somewhat far-fetched. However, look a little closer and you’ll see the future encountered by Marty and Doc isn’t quite so far removed from reality.
The time travellers visited a world dominated by Artificial Intelligence (AI), where services from petrol stations to cafes were operated by technology rather than human beings. If you stop and think, you’ll realise a similar transformation is occurring in the real world.
| 2023-01-01T00:00:00 |
https://www.allegisglobalsolutions.com/en/workforce-insights/white-papers/the-transformation-of-the-workforce-through-artificial-intelligence
|
[
{
"date": "2023/01/01",
"position": 69,
"query": "AI workforce transformation"
},
{
"date": "2023/11/01",
"position": 77,
"query": "AI workforce transformation"
},
{
"date": "2024/11/01",
"position": 83,
"query": "AI workforce transformation"
}
] |
|
Workforce Transformation with AI: Why Reskilling is the ... - Ozemio
|
Beyond Automation: Why Workforce Transformation Demands a Reskilling Strategy
|
https://ozemio.com
|
[
"Rinky Kapoor"
] |
Explore how AI-driven workforce transformation is reshaping industries. Learn why a strategic reskilling approach is essential for future-ready employees ...
|
The Workforce Transformation: Why Organisations Need a Proactive Approach
Imagine looking five years into the future. How many faces from your current team will occupy the same seats? Now, consider the impact of AI, automation, and the digital wave crashing over every industry.
The face count will most likely shrink faster than you thought. Change is accelerating, and businesses that don’t adapt to workforce transformation risk falling behind.
Whether you realise it or not, you face a critical challenge as a leader: ensuring your employees remain relevant and future-proof.
The key to workforce transformation is a strategic shift focused on employee reskilling. It also involves redeploying employees into roles that align with your organisation’s changing needs, ensuring long-term resilience and growth.
When done right, workforce transformation enhances organisational agility and fosters employee engagement, innovation, and retention. Let’s explore how:
Reskilling for Strategic Redeployment
Reskilling aligns talent with evolving business needs, enabling seamless redeployment and workforce agility. It helps organisations:
Adapt to Role Evolution – Equip employees for emerging roles, reducing reliance on external hiring.
Ensure Business Continuity – Fill critical skill gaps with trained internal talent.
Optimise Costs – Minimise hiring and training expenses through internal mobility.
Drive Digital Readiness – Prepare employees for AI-driven and tech-enabled roles.
Boost Retention – Offer career growth, increasing engagement and reducing turnover.
By integrating reskilling with redeployment, organisations build a future-ready workforce capable of confidently navigating change.
How Learning & Development Drives Future Readiness with Reskilling
A strategic L&D approach ensures that reskilling efforts translate into tangible business outcomes. It’s about acquiring new skills and aligning learning with evolving business needs, ensuring employees can transition into critical roles that drive growth and innovation.
To future-ready the workforce, organisations must:
Align Skills with Business Strategy – Identify skill gaps based on industry trends and business objectives, ensuring employees are equipped for high-impact roles.
Personalise Learning Journeys – Utilise AI-driven learning platforms to tailor content to individual career paths, making skill development more effective and relevant.
Leverage Experiential Learning—Deploy hands-on training, including VR simulations and scenario-based learning, to foster practical application and confidence in new roles.
Integrate Microlearning & Gamification – Use bite-sized, engaging content to accelerate learning and improve retention, making reskilling seamless.
Ensure Continuous Upskilling – Employ ongoing learning opportunities to keep employees adaptable to emerging technologies and industry shifts.
Measure Learning Effectiveness – Implement advanced analytics to track progress, skill adoption, and business impact, ensuring that reskilling translates into measurable success.
The Pivot Point: Reshaping Your Workforce for Unpredictable Times
Organisations must take a proactive approach by embedding workforce transformation into their talent strategy. Here’s how to get started:
Assess Skill Gaps: Conduct a workforce skills analysis to identify critical reskilling and role realignment areas.
Develop a Learning Roadmap: Align training initiatives with your business objectives, ensuring your employees acquire future-ready skills.
Implement AI-Driven Learning Solutions: Utilize technology-enabled learning platforms, immersive simulations, and mobile-first tailored content to deliver impactful upskilling experiences.
Embed Learning into Workflows: Shift from one-time training to continuous learning by integrating knowledge-sharing tools, coaching, and real-time feedback mechanisms.
Foster a Culture of Continuous Learning: Encourage employees to take ownership of their development through structured learning pathways, mentorship programs, and peer-driven knowledge sharing.
Design Practical Redeployment Strategies: Enable smooth transitions by providing targeted career coaching, job rotations, and skill-matching initiatives.
Partner with Experts: Leverage external learning and development experts, consultants, and solutions providers to design and execute high-impact reskilling and redeployment programs tailored to your organisation’s needs.
The future of work is already here. Are you prepared?
Organisations can future-proof their workforce by adopting reskilling, redeployment, and L&D-driven workforce transformation, ensuring business success in an ever-evolving landscape. Let’s build a workforce that’s ready for tomorrow. Contact Ozemio today!
| 2025-03-26T00:00:00 |
2025/03/26
|
https://ozemio.com/blog/workforce-transformation-with-ai/
|
[
{
"date": "2023/01/01",
"position": 72,
"query": "AI workforce transformation"
},
{
"date": "2023/02/01",
"position": 50,
"query": "AI workforce transformation"
},
{
"date": "2023/03/01",
"position": 51,
"query": "AI workforce transformation"
},
{
"date": "2023/05/01",
"position": 58,
"query": "AI workforce transformation"
},
{
"date": "2023/07/01",
"position": 53,
"query": "AI workforce transformation"
},
{
"date": "2023/09/01",
"position": 53,
"query": "AI workforce transformation"
},
{
"date": "2023/10/01",
"position": 56,
"query": "AI workforce transformation"
},
{
"date": "2023/10/01",
"position": 19,
"query": "reskilling AI automation"
},
{
"date": "2023/11/01",
"position": 72,
"query": "AI workforce transformation"
},
{
"date": "2023/12/01",
"position": 53,
"query": "AI workforce transformation"
},
{
"date": "2024/01/01",
"position": 50,
"query": "AI workforce transformation"
},
{
"date": "2024/02/01",
"position": 51,
"query": "AI workforce transformation"
},
{
"date": "2024/03/01",
"position": 52,
"query": "AI workforce transformation"
},
{
"date": "2024/08/01",
"position": 53,
"query": "AI workforce transformation"
},
{
"date": "2024/09/01",
"position": 49,
"query": "AI workforce transformation"
},
{
"date": "2024/10/01",
"position": 51,
"query": "AI workforce transformation"
},
{
"date": "2024/11/01",
"position": 73,
"query": "AI workforce transformation"
},
{
"date": "2024/12/01",
"position": 60,
"query": "AI workforce transformation"
},
{
"date": "2025/01/01",
"position": 52,
"query": "AI workforce transformation"
},
{
"date": "2025/03/01",
"position": 49,
"query": "AI workforce transformation"
},
{
"date": "2025/05/01",
"position": 55,
"query": "AI workforce transformation"
},
{
"date": "2025/06/01",
"position": 54,
"query": "AI workforce transformation"
}
] |
AI in the workforce: bridging technology and human elements - EY
|
AI in the workforce: bridging technology and human elements
|
https://www.ey.com
|
[
"Rich Macfarlane",
"Meredith Wilmot",
"Authorsalutation",
"Authorfirstname Rich Authorlastname Macfarlane Authorjobtitle Ey Oceania Technology Consulting Partner",
"Consumer Authorurl Https",
"Www.Ey.Com En_Nz People Rich-Macfarlane",
"Authorfirstname Meredith Authorlastname Wilmot Authorjobtitle Ey Partner",
"People Consulting Authorurl Https",
"Www.Ey.Com En_Nz People Meredith-Wilmot",
"Content Dam Content-Fragments Ey-Unified-Site Ey-Com People Local En_Nz R Rich-Macfarlane"
] |
As AI matures, this will lead to further enterprise-wide transformation, driving smarter decisions, tighter data governance, streamlined ...
|
There’s no denying the transformative impact of artificial intelligence (AI) as it begins to shape our workforces, with new tools and use cases appearing daily.
However, while technology leaders have traditionally been tasked with leading the charge, this may no longer be the best strategy. People are at the heart of every business, so to successfully implement AI tools, frameworks and ways of working, we believe organisations need to recognise that People teams are uniquely positioned to share the driver’s seat.
It’s not just about the tech—it’s also about the people. While technology leaders frequently have the mandate to research, build and test AI tools, people leaders have a responsibility in driving employee engagement to achieve organisational performance. People teams have a nuanced understanding of internal culture and ways of working. They know where the friction lies, how much change the organisation can absorb, and how fast to move. Whether a business is agile, experimental and fast-paced or cautious and compliance-heavy, AI strategies must reflect that context. People teams, alongside IT, can lead this kind of cultural alignment.
Humans at the centre: Global EY research shows organisations that engage employees in problem-solving are 12 times more likely to shift transformation programmes onto a trajectory that provides significantly greater value. The People team will be integral to helping ensure the right people are involved, bringing in a diverse range of thoughts and ideas that help deliver the better value for the whole business.
EY research emphasises that successful AI integration must prioritise the human experience. By understanding employee needs, motivations, and concerns, organisations can create AI strategies that enhance rather than hinder the workforce. This human-centric approach fosters a culture of collaboration and innovation, helping ensure that technology serves to empower employees rather than replace them.
For Tech and People leaders, transparency around AI strategy is critical to earning trust and proving Return On Investment on tech investments with employees. As AI matures, this will lead to further enterprise-wide transformation, driving smarter decisions, tighter data governance, streamlined workflows, and ironclad cybersecurity.
Bridging the generational divide
A growing challenge is the AI divide between generations. According to the EY 2025 AI Sentiment Report, Baby Boomers and Gen X are more sceptical of emerging technologies, while Gen Z is eager to integrate AI into everything they do. As Gen Z climbs the ladder into more senior positions, this will create a divide.
The opportunity for People teams will be considering the roles each generation holds in the workforce and planning accordingly. There’s a job to be done in making older cohorts, who are also decision-makers, more open to change. A global EY study into generations at work suggests organisations need to rethink their structural models due to multi-generational teams. The study recommends that more experienced workers are upskilled. Additionally, it also suggests that these experienced workers should feed knowledge to younger generations to help ensure institutional knowledge is passed down. Coincidentally, AI can support these transitions, utilising experienced workers and their knowledge to create prompt libraries, AI agents and workflows for future employees to learn from and embed ways of working.
Building trust
Building trust in AI systems is also crucial. AI sentiment data shows New Zealand is behind the world on trust in AI, still seeing these technologies as a threat. People teams are well placed to support the engagement and cultural change of embedding AI into an organisation and creating an environment where people feel empowered to use AI.
They should also be able to lead out from developing trust and confidence in people learning to use and leverage AI into their day-to-day work. How you deploy an enterprise-wide gen AI platform like Co-pilot should be a partnership between the Tech team and the People team, who can embed the platform and achieve successful adoption. Leaning on the People team to drive change should be a must-do. Trust won’t come from top-down mandates. It’ll come from honest conversations, visible benefits, and a gradual, people-first approach.
| 2025-06-03T00:00:00 |
2025/06/03
|
https://www.ey.com/en_nz/insights/ai/ai-in-the-workforce-bridging-technology-and-human-elements
|
[
{
"date": "2023/01/01",
"position": 75,
"query": "AI workforce transformation"
},
{
"date": "2023/11/01",
"position": 66,
"query": "AI workforce transformation"
},
{
"date": "2024/11/01",
"position": 57,
"query": "AI workforce transformation"
},
{
"date": "2024/12/01",
"position": 63,
"query": "AI workforce transformation"
}
] |
Digital Workplace Transformation with AI & IoT - Infosys
|
Digital Workplace Transformation with AI & IoT
|
https://www.infosys.com
|
[
"Infosys Limited"
] |
Infosys enables digital workplace transformation with AI, IoT & talent upskilling, ensuring a seamless, collaborative & future-ready workspace. Learn More!
|
Digital Workplace Transformation
Infosys looks at transforming the workplace to connect, collaborate and co-create. As an end-to-end service provider, we offer consulting, collaboration services and services in the domain of modern workspaces and workplace operations. We are well equipped to digitize physical workplaces using AI and IOT by leveraging our partner ecosystem.
Our vision for the Digital Workplace is focused on enhancing the user experience and, productivity through a “Collaboration Continuum” by envisioning the different work style needs across the workforce, enabling them to collaborate effectively as a purposeful network of teams and evolving to the workplace of tomorrow using evergreen IT models.
Learning forms an integral part of this exercise as it prepares employees for any potential scenario, just in case they need it. With the help of a Digital Change Management and Talent Transformation platform, Infosys aids employees in their learning journey by creating persona-based sandboxes with the AI-based personal learning coaches to help them hone new skills.
| 2023-01-01T00:00:00 |
https://www.infosys.com/services/digital-workplace-services/offerings/digital-workplace-transformation-overview.html
|
[
{
"date": "2023/01/01",
"position": 82,
"query": "AI workforce transformation"
},
{
"date": "2023/11/01",
"position": 79,
"query": "AI workforce transformation"
},
{
"date": "2024/11/01",
"position": 67,
"query": "AI workforce transformation"
},
{
"date": "2024/12/01",
"position": 82,
"query": "AI workforce transformation"
}
] |
|
Embracing AI The Future of Work and Workforce Transformation
|
Embracing AI The Future of Work and Workforce Transformation
|
https://www.thecloudcommunity.net
|
[
"The Cloud Community",
"Wednesday",
"March",
"April",
"Monday",
"February",
"Friday",
"December"
] |
The reality of AI's role in the workplace is not one of replacement but one of augmentation and empowerment. Successfully navigating this transformation ...
|
As businesses look to implement artificial intelligence (AI) into their operations, there’s no denying the transformative potential of this technology.
However, alongside its promise of efficiency and innovation comes a significant challenge: managing the impact on the workforce.
Fears of job displacement and obsolescence often dominate discussions about AI, but these concerns are largely misplaced. The reality of AI’s role in the workplace is not one of replacement but one of augmentation and empowerment. Successfully navigating this transformation requires a shared commitment from companies and employees to embrace change, upskill, and foster a collaborative environment where technology and human ingenuity work hand in hand.
The Reality of AI: Augmenting, Not Replacing
The introduction of AI into the workforce is often seen through a lens of fear and uncertainty, particularly around the idea of job loss. However, the true potential of well-implemented AI lies in its ability to augment human capabilities, not replace them. AI tools excel at automating repetitive, time-consuming tasks—allowing employees to focus on more complex, creative, and strategic work.
This shift will not only enhance productivity but also lead to the creation of new, more valuable roles that demand human insight and innovation. World Economic Forum research suggests that AI could create 97 million new jobs this year, reflecting the broad opportunities AI presents when approached appropriately.
Rather than replacing jobs, AI will transform them. Routine tasks, such as data entry or basic analysis, will be handled by machines, freeing up workers to engage in higher-level decision-making and problem-solving. Far from displacing workers, AI offers an opportunity to elevate the workforce by shifting roles toward more strategic and meaningful contributions. It’s essential for companies to communicate this vision clearly to employees, helping them understand that AI is a tool for empowerment, not a threat to their livelihood.
The Company’s Role: Driving Change and Fostering Learning
As AI becomes a central part of business operations, the responsibility for its successful integration rests largely with the company. Managing change effectively is crucial; businesses must provide comprehensive training programs, update existing policies, and ensure that AI’s adoption is aligned with ethical standards. Clear communication from leadership is key to overcoming fears about job replacement and fostering a positive view of AI as an enabler of productivity and creativity.
Companies must also recognize that AI adoption is not a one-time event but an ongoing process. As the technology evolves, so too must the skill sets of its workforce. This means offering continuous learning opportunities, both through internal training programs and external resources. Encouraging employees to engage proactively in upskilling ensures that the workforce stays competitive and capable of leveraging AI to its fullest potential.
Moreover, businesses must establish clear policies for the ethical use of AI. AI technologies must be implemented in ways that protect privacy, ensure data security, and avoid bias. Updating company handbooks, creating AI guidelines, and providing training on ethical considerations will help ensure that AI is used responsibly and transparently.
The Employee's Role: Upskilling for the Future
For employees, the key to thriving in an AI-driven workplace lies in their ability to embrace technology and continuously upskill. AI will not replace jobs altogether but will reshape the way work is done. Employees must take responsibility for their own learning by engaging with company-provided training and seeking additional learning opportunities outside the organization.
Proactive engagement with AI tools is essential for remaining relevant in a rapidly changing landscape. Employees who focus on developing their skills in areas such as data analysis, machine learning, and AI-driven problem solving will find themselves in high demand. But beyond technical skills, critical thinking remains crucial. AI can provide recommendations, generate insights, and automate tasks, but it’s the human touch that ensures these outputs are applied strategically and ethically.
Employees should view AI as an opportunity to increase their own productivity and creativity. By integrating AI into their daily workflows, they can streamline mundane tasks, allowing more time for complex problem-solving and decision-making. As such, employees who embrace AI will not only become more valuable to their organizations but will also position themselves for greater career growth.
A Collaborative Approach: AI and Human Creativity
The most successful implementations of AI will be those where technology and human creativity collaborate seamlessly. While AI excels at automating repetitive tasks and analyzing vast amounts of data, it cannot replicate human intuition, empathy, or strategic thinking. These uniquely human qualities will continue to drive business success, with AI serving as a partner rather than a competitor.
Organizations that foster this collaborative mindset will see the greatest returns on their AI investments. Employees who use AI to enhance their creativity and problem-solving capabilities will be able to innovate in ways that were not previously possible. By embracing AI as a co-creator, businesses can unlock new avenues for growth, efficiency, and customer satisfaction.
Preparing for a Future Where AI and Humans Thrive Together
The future of work is not one where AI replaces human workers but one where AI and humans coexist and thrive together. The key to achieving this harmonious future is proactive engagement from both companies and employees. Companies must lead by example, providing the necessary tools, training, and support for successful AI adoption, while employees must embrace critical thinking and lifelong learning to fully harness AI’s potential.
User Adoption Clinic Deploying technology to improve business—whether for cost savings, resource optimisation, efficiency gains, or customer experience enhancement—is nothing new. Yet, despite the investment in enablement tools, training, and systems, the expected results don’t always materialize. A key reason? Leadership’s role in enablement is often underestimated. Book your FREE User Adoption Clinic now to help you set clear expectations, achieve cultural buy-in, and gain accountability. Book your Clinic
| 2023-01-01T00:00:00 |
https://www.thecloudcommunity.net/business-performance/business-performance/jabian/embracing-ai-the-future-of-work-and-workforce-transformation/
|
[
{
"date": "2023/01/01",
"position": 88,
"query": "AI workforce transformation"
},
{
"date": "2023/02/01",
"position": 51,
"query": "AI workforce transformation"
},
{
"date": "2023/03/01",
"position": 52,
"query": "AI workforce transformation"
},
{
"date": "2023/05/01",
"position": 57,
"query": "AI workforce transformation"
},
{
"date": "2023/07/01",
"position": 56,
"query": "AI workforce transformation"
},
{
"date": "2023/09/01",
"position": 48,
"query": "AI workforce transformation"
},
{
"date": "2023/10/01",
"position": 58,
"query": "AI workforce transformation"
},
{
"date": "2023/11/01",
"position": 87,
"query": "AI workforce transformation"
},
{
"date": "2023/12/01",
"position": 48,
"query": "AI workforce transformation"
},
{
"date": "2024/01/01",
"position": 45,
"query": "AI workforce transformation"
},
{
"date": "2024/02/01",
"position": 53,
"query": "AI workforce transformation"
},
{
"date": "2024/03/01",
"position": 54,
"query": "AI workforce transformation"
},
{
"date": "2024/08/01",
"position": 52,
"query": "AI workforce transformation"
},
{
"date": "2024/09/01",
"position": 45,
"query": "AI workforce transformation"
},
{
"date": "2024/10/01",
"position": 52,
"query": "AI workforce transformation"
},
{
"date": "2024/11/01",
"position": 86,
"query": "AI workforce transformation"
},
{
"date": "2024/12/01",
"position": 72,
"query": "AI workforce transformation"
},
{
"date": "2025/01/01",
"position": 54,
"query": "AI workforce transformation"
},
{
"date": "2025/03/01",
"position": 46,
"query": "AI workforce transformation"
},
{
"date": "2025/05/01",
"position": 50,
"query": "AI workforce transformation"
},
{
"date": "2025/06/01",
"position": 53,
"query": "AI workforce transformation"
}
] |
|
Specialization. AI in Workforce Transformation & Automation ...
|
Specialization. AI in Workforce Transformation & Automation Leadership
|
https://nblcert.org
|
[] |
Learning Path. AI in Workforce Transformation & Automation Leadership. Developed & validated by NBLC certification holders, this official prep course advances ...
|
While NBLC certifications validate your existing skills and experience, preparation is critical to passing the portfolio-based assessments.
Whether you’re looking for in-person training or on-demand courses that allow you to go at your own pace, there are plenty of options for exam preparation.
| 2023-01-01T00:00:00 |
https://nblcert.org/products/specialization-ai-in-workforce-transformation-automation-leadership
|
[
{
"date": "2023/01/01",
"position": 91,
"query": "AI workforce transformation"
},
{
"date": "2023/02/01",
"position": 61,
"query": "AI workforce transformation"
},
{
"date": "2023/03/01",
"position": 66,
"query": "AI workforce transformation"
},
{
"date": "2023/05/01",
"position": 69,
"query": "AI workforce transformation"
},
{
"date": "2023/07/01",
"position": 80,
"query": "AI workforce transformation"
},
{
"date": "2023/09/01",
"position": 39,
"query": "AI workforce transformation"
},
{
"date": "2023/10/01",
"position": 71,
"query": "AI workforce transformation"
},
{
"date": "2023/11/01",
"position": 92,
"query": "AI workforce transformation"
},
{
"date": "2023/12/01",
"position": 40,
"query": "AI workforce transformation"
},
{
"date": "2024/01/01",
"position": 35,
"query": "AI workforce transformation"
},
{
"date": "2024/02/01",
"position": 63,
"query": "AI workforce transformation"
},
{
"date": "2024/03/01",
"position": 65,
"query": "AI workforce transformation"
},
{
"date": "2024/08/01",
"position": 37,
"query": "AI workforce transformation"
},
{
"date": "2024/09/01",
"position": 36,
"query": "AI workforce transformation"
},
{
"date": "2024/10/01",
"position": 41,
"query": "AI workforce transformation"
},
{
"date": "2024/11/01",
"position": 95,
"query": "AI workforce transformation"
},
{
"date": "2024/12/01",
"position": 94,
"query": "AI workforce transformation"
},
{
"date": "2025/01/01",
"position": 72,
"query": "AI workforce transformation"
},
{
"date": "2025/05/01",
"position": 32,
"query": "AI workforce transformation"
},
{
"date": "2025/06/01",
"position": 34,
"query": "AI workforce transformation"
}
] |
|
AI-Driven Workforce Transformation: Adapting to the Future of Work
|
AI-Driven Workforce Transformation: Adapting to the Future of Work
|
https://seamflexinc.com
|
[] |
As AI continues to transform industries, it is also driving the need for workforce transformation—forcing businesses to adapt to technological advancements and ...
|
Artificial Intelligence (AI) is reshaping the global workforce, creating new opportunities, redefining roles, and necessitating a shift in how organizations approach talent management, skills development, and human resources (HR) strategies. As AI continues to transform industries, it is also driving the need for workforce transformation—forcing businesses to adapt to technological advancements and rethink how they operate. AI-driven workforce transformation isn’t just about implementing new technologies; it’s about fostering a culture of continuous learning and adaptation to prepare employees for a future defined by automation and machine intelligence.
This article explores how AI is impacting skills development, HR strategies, and creating a dynamic work environment focused on agility, learning, and growth.
| 2024-09-24T00:00:00 |
2024/09/24
|
https://seamflexinc.com/ai-driven-workforce-transformation-adapting-to-the-future-of-work/
|
[
{
"date": "2023/01/01",
"position": 95,
"query": "AI workforce transformation"
},
{
"date": "2023/02/01",
"position": 58,
"query": "AI workforce transformation"
},
{
"date": "2023/03/01",
"position": 59,
"query": "AI workforce transformation"
},
{
"date": "2023/05/01",
"position": 66,
"query": "AI workforce transformation"
},
{
"date": "2023/07/01",
"position": 65,
"query": "AI workforce transformation"
},
{
"date": "2023/09/01",
"position": 60,
"query": "AI workforce transformation"
},
{
"date": "2023/10/01",
"position": 66,
"query": "AI workforce transformation"
},
{
"date": "2023/12/01",
"position": 59,
"query": "AI workforce transformation"
},
{
"date": "2024/01/01",
"position": 56,
"query": "AI workforce transformation"
},
{
"date": "2024/02/01",
"position": 60,
"query": "AI workforce transformation"
},
{
"date": "2024/03/01",
"position": 59,
"query": "AI workforce transformation"
},
{
"date": "2024/08/01",
"position": 61,
"query": "AI workforce transformation"
},
{
"date": "2024/09/01",
"position": 54,
"query": "AI workforce transformation"
},
{
"date": "2024/10/01",
"position": 58,
"query": "AI workforce transformation"
},
{
"date": "2024/12/01",
"position": 90,
"query": "AI workforce transformation"
},
{
"date": "2025/01/01",
"position": 60,
"query": "AI workforce transformation"
},
{
"date": "2025/03/01",
"position": 58,
"query": "AI workforce transformation"
},
{
"date": "2025/05/01",
"position": 65,
"query": "AI workforce transformation"
},
{
"date": "2025/06/01",
"position": 65,
"query": "AI workforce transformation"
}
] |
Realistically. Is ML a shiftable career for mid-30s ...
|
The heart of the internet
|
https://www.reddit.com
|
[] |
Yes, it's possible. In fact, having a SWE background can help you in the long run, as data scientists usually aren't that great in writing maintainable code.
|
Just looking for a realistic answer. I'm trying to shift careers and trying to shift into something that is future proof at the very least. 15yoe developer here but never took calculus 1, I'm good at math though.
the harsher the answer, the better.
| 2023-01-01T00:00:00 |
https://www.reddit.com/r/learnmachinelearning/comments/10kb4lo/realistically_is_ml_a_shiftable_career_for_mid30s/
|
[
{
"date": "2023/01/01",
"position": 1,
"query": "machine learning job market"
}
] |
|
Cloud Computing or Artificial Intelligence — Which career is ...
|
Cloud Computing or Artificial Intelligence — Which career is better?
|
https://cloudsecurityguy.substack.com
|
[
"Taimur Ijlal"
] |
Artificial Intelligence and Cloud Computing both are booming industries which offer long term career growth and success.
|
Photo by Sigmund on Unsplash
If you are newly entering the job market in 2023, then I do not blame you for being nervous
“Tech Layoffs are happening” “Jobs are scarce” “Doom and gloom everywhere”
Same old blah blah
Let us look at the advantages you have
If you are a newcomer to the industry, then you have an enormous advantage over older and more experienced people like me in that your primary goal is to nab that all-important experience
Salary and other perks while important are all secondary
Junior-level positions are also much easier to get compared to senior-level positions that have much more competition.
A common question I get asked by newcomers is which field to choose ?
I made a video a few months back on Artificial Intelligence vs Cybersecurity and it is by far the most popular video on my Youtube channel
After that people started asking me what about Cloud Computing or Artificial Intelligence ?
Which field should you choose if you are a newcomer ?
Cloud Computing vs A.I. as a career
If you are caught between deciding which field to take then the good news is that both are amazing fields with excellent growth prospects
Believe me when I say shortage of jobs or lack of demand will not a problem if you are good in either of these fields
So which is better for you ?
That really depends on your individual skills and what topic you are passionate about but I have tried to make the decision easy for you
Below is the criteria I used:
❓ Market Demand — What are the long term / short term prospects ?
⚙️ Skills needed — What skills do you need to start this career ?
🚪 Entry Barrier — How difficult is it to get into this field
💵 Salaries — How well does this career pay ?
☁ ️Cloud computing
Cloud Computing is the future of IT .. like it or hate it .. slowly but surely most companies will move towards this model. Whether it is IaaS (Infrastructure as a Service), PaaS (Platform as a service) or SaaS (Software as a Service), this vast field can accommodate all types of skills
❓ Market Demand
Cloud Computing is a very hot field with job openings for nearly every type of skill be it DevSecOps, Cloud Architects, Cloud Security Engineers etc. With giants like AWS, Microsoft and Google all investing billions into their cloud infrastructures, there is no chance of this industry going way anytime soon. Despite cuts in tech spending, CIOs do not want the hassle of maintaining data centers and the costs that come with it
The private and public cloud market in the financial services industry is poised to grow by $90175.21 mn during 2023–2027
⚙️ Skills needed
The Cloud is a massive field and an accommodate pretty much any IT skill with roles like Cloud Developer, DevSecOps engineer, Sysops engineer, DevOps engineer, Data engineer etc. all available. However the smart move is to get hands on with one of the major platforms like AWS, Azure or Google Cloud for which there are multiple free trainings available.
I have written before on how to get hands on experience even if you do not have a job right now. It was written for cloud security but can be applied even to Cloud Computing as a whole.
🚪 Entry Barrier ( LOW )
The entry barrier for Cloud computing is quite low provided you are able to develop the core skills for a cloud provider. There are simply too many cloud jobs and not enough cloud professionals but you have to be able to show you “get” the cloud before landing that job.
If the recruiter is talking about the Shared Responsibility Model and you are sitting there with a blank face then you will have problems ! Get certified and hands on with the cloud before you start applying for those jobs.
There are numerous ways of boosting your profile and getting Cloud Experience which I written about before so do check those articles out.
💵 Salaries ( Medium to High )
Cloud Professionals can command some of the highest salaries in the IT industry right now despite the cuts in tech spending. This is even more true if you are able to validate your experience with certifications like the AWS Solutions Architect professional or the Google Cloud Professional Cloud Architect which are some of the hardest to get in the industry. Without those specialized certs, you still might be able to get a good salary and then work towards a higher pay scale once you have a few years of experience under your belt.
🧠 Artificial Intelligence?
A.I. is the science and field of making intelligent machines i.e. making machines “learn” and make decisions the way humans can. This is done via machine learning algorithms that use data to build a model on which decision to make. A.I. has pretty much become commonplace now from Alexa to Deepfakes to even our Netflix recommendations list.
❓ Market Demand
A.I. is being used in every industry right now from military, education, finance, hospitality .. you name it !
Just do a simple job search and you will see job postings for Robotics programmers, Machine Learning engineers, ML researchers, A.I. technical writers etc. .. There is no shortage with people with A.I. and Machine Learning skills
Just to put things in perspective here is an excerpt from a recent report
AI could contribute up to $15.7 trillion to the global economy in 2030, more than the current output of China and India combined
⚙️ Skills needed
While A.I. is a vast field, programming and Data Science skills are some of the essentials skills you need to have a successful career. As an AI or Machine learning engineer you will be dealing with analytical models and working with datasets so if interacting with huge amounts of data is not your cup of tea then AI is definitely not the field for you.
You will also need to be proficient in languages like R, Python , Java, Perl etc. and have a good foundational knowledge of probability and statistics.
As the industry matures, more types of job openings will come up such as A.I. security or A.I. governance but currently they are far and few between.
🚪 Entry Barrier ( MEDIUM TO HIGH)
The entry barrier for A.I. is a bit higher than Cloud Computing due to the more specialized skills required. It is not easy to break into AI if you don’t have a specific set of skills ( Taken reference ! ). If you are already have good data and programing skills then you might find it easier than most and can build up the other skills over time if AI is a career you are passionate about.
There are numerous programs available over the internet such as Google AI. I would recommend going with a proper A.I. degree program as there is a higher learning curve that cloud computing . These are built for professionals and focus on real world problems to build up your knowledge. Not going to recommend any specific one but you can easily find them.
💵 Salaries ( HIGH)
A.I. jobs are typically some of the highest paying jobs year in and year out as can be seen by pretty much any salary report. While the entry barrier is high, the pay is definitely worth it !
There is a lot of turnover within A.I. professionals as they are easily able to secure better paying jobs within their industry.
Final Takeaway
I hope this gave you a good idea of both industries and helps you decide which career path you want to take. Artificial Intelligence and Cloud Computing both are booming industries which offer long term career growth and success. Make a decision about which suits your interests and passions then invest in your long term success fully.
One last point I may mention is that you can even combine the two as most A.I. platforms are hosted on Cloud providers. AWS , Microsoft and Google all offer managed services for A.I. and Machine Learning which you can learn and get the best of both worlds !
| 2023-01-01T00:00:00 |
https://cloudsecurityguy.substack.com/p/cloud-computing-or-artificial-intelligence
|
[
{
"date": "2023/01/01",
"position": 10,
"query": "machine learning job market"
}
] |
|
The Impact of AI on the Job Market
|
The Impact of AI on the Job Market
|
https://www.linkedin.com
|
[
"Richard R Little",
"Broker",
"Realtor",
"Dre"
] |
AI has the potential to bring significant benefits to the job market, including increased efficiency, productivity, and new job opportunities.
|
Artificial intelligence (AI) has been making waves in the tech world for the past several years, and its impact on the job market is a topic of much discussion. In this article, we will explore the potential effects of AI on employment and the job market, both positive and negative.
Impact of AI on the Job Market
The impact of AI on the job market has been a subject of debate among economists and experts.
⭐ On the positive side, AI has the potential to automate many tasks, freeing up workers to focus on more complex and rewarding work. This can increase productivity, efficiency, and overall job satisfaction.
For example, AI-powered chatbots can handle customer service inquiries, allowing human representatives to focus on more complex issues.
Moreover, the adoption of AI is likely to create new job opportunities in areas such as data analysis, machine learning, and AI development. As AI becomes more integrated into businesses and industries, there will be a growing demand for professionals who are knowledgeable about AI and how to use it to solve real-world problems.
Increase productivity, efficiency, and do complete workflow in auto pilot mode.
⭐ On the negative side, the negative impact of AI on the job market cannot be ignored. As AI automates certain tasks, it may lead to job loss and unemployment for workers who are displaced.
For example, self-driving cars could lead to job loss for taxi and truck drivers, while AI-powered robots could displace factory workers.
Lead for job loss and unemployment for workers.
To mitigate the negative impact of AI on employment, it is important for governments and businesses to invest in retraining programs and support for workers who are displaced by automation. By providing workers with the skills they need to transition to new jobs, we can ensure that the benefits of AI are shared more widely and that the negative impacts are minimized.
Overall, the net effect of AI on employment is likely to be complex and varied across different industries and job categories. Some experts predict that AI will lead to significant job displacement in the short-term, but that new jobs will be created as the economy adjusts in the long-term.
Negative impact of AI on employment
In conclusion, AI has the potential to bring significant benefits to the job market, including increased efficiency, productivity, and new job opportunities. However, it is important to address the potential negative impact of AI on employment, and to support workers as they transition to new jobs in an AI-driven world.
By staying informed about the latest developments in AI and the job market, and by investing in retraining and support programs, we can ensure that AI has a positive impact on employment and the economy as a whole.
Stay tuned here for getting more knowledge in next articles. ✍️
| 2023-01-01T00:00:00 |
https://www.linkedin.com/pulse/impact-ai-job-market-pavan-g
|
[
{
"date": "2023/01/01",
"position": 14,
"query": "machine learning job market"
}
] |
|
The Role Of Technology In Shaping The Future Of Work ...
|
The Role Of Technology In Shaping The Future Of Work And Job Market Trends.
|
https://medium.com
|
[
"John U. Ordillo"
] |
The use of AI and machine learning is likely to have a significant impact on the job market, particularly in fields such as finance, healthcare, and customer ...
|
The Role Of Technology In Shaping The Future Of Work And Job Market Trends. John U. Ordillo 3 min read · Jan 20, 2023 -- Listen Share
Technology is playing an increasingly important role in shaping the future of work and job market trends. The development and adoption of new technologies, such as artificial intelligence, automation, and the Internet of Things, are transforming the way we work and the types of jobs that are in demand.
One of the key ways in which technology is shaping the future of work is through automation. Automation refers to the use of technology to perform tasks that were previously done by humans. This can include things like manufacturing, transportation, and even certain types of white-collar work, such as data entry and analysis. As automation technology advances, it is becoming increasingly capable of performing a wide range of tasks that were previously done by humans, which is leading to job displacement in certain sectors. However, it is also creating new job opportunities in fields such as data analysis, programming, and robotics.
Another important trend in the future of work is the increasing use of artificial intelligence (AI) and machine learning. AI is a branch of computer science that focuses on creating machines that can perform tasks that typically require human intelligence, such as recognizing speech, understanding natural language, and making decisions. Machine learning, a subset of AI, is a method used to teach computers to learn from data and improve their performance without explicit instructions. The use of AI and machine learning is likely to have a significant impact on the job market, particularly in fields such as finance, healthcare, and customer service. However, it is also likely to lead to job displacement in certain sectors, such as data entry, and the need for new skills and jobs in data analysis, programming and development of AI systems.
The internet of things (IoT) is also playing an increasingly important role in shaping the future of work. IoT refers to the interconnectedness of physical devices, such as smartphones, appliances, and vehicles, through the internet. This allows these devices to collect and share data, which can be used to improve efficiency, reduce costs, and create new products and services. IoT is expected to create new job opportunities in fields such as data analysis, programming, and security.
A related trend is the rise of remote work and the gig economy. The widespread use of the internet and mobile technology has made it easier for people to work from anywhere and has led to the growth of the gig economy, where people work as independent contractors or freelancers rather than as traditional employees. This trend is likely to continue in the future, as technology makes it easier for people to work remotely, and as companies look for more flexible ways of organizing their workforce.
In summary, technology is playing an increasingly important role in shaping the future of work and job market trends. Automation, AI, IoT, and the rise of remote work, and the gig economy are all having an impact on the types of jobs that are in demand, as well as the skills that are required to perform those jobs. While technology is likely to lead to job displacement in certain sectors, it is also creating new job opportunities in fields such as data analysis, programming, and security. As technology continues to evolve, it will be important for individuals, businesses, and governments to adapt to these changes and invest in the necessary skills and infrastructure to take advantage of the new opportunities that technology is creating.
By: John U. Ordillo
| 2023-12-18T00:00:00 |
2023/12/18
|
https://medium.com/@ordillo1/the-role-of-technology-in-shaping-the-future-of-work-and-job-market-trends-1ed29723164a
|
[
{
"date": "2023/01/01",
"position": 20,
"query": "machine learning job market"
}
] |
Path to Learn Machine Learning: How to become an ML ...
|
Path to Learn Machine Learning: How to become an ML master
|
https://www.linkedin.com
|
[
"Doug Rose",
"Abhinavan Sarikonda",
"Elsayed Rashed"
] |
The report also found that machine learning jobs tend to have higher salaries than other types of technology jobs. In addition to traditional job roles, there ...
|
Machine learning is a rapidly developing field with a wide range of applications, including image and speech recognition, natural language processing, and predictive analytics. As a result, machine learning professionals are in high demand across many industries, including tech, finance, healthcare, and more.
According to a report by Indeed, job searches for machine learning-related positions have been increasing over the past several years, and this trend is expected to continue. The report also found that machine learning jobs tend to have higher salaries than other types of technology jobs.
In addition to traditional job roles, there may also be opportunities for machine learning professionals to work as freelancers or consultants, providing their expertise to organizations on a project-by-project basis.
Overall, it is likely that the job market for machine learning professionals will remain strong in the coming years. So, mastering ML will be ultimately helpful for you.
Introduction to Machine Learning
Machine learning is a subset of artificial intelligence that involves training algorithms to automatically improve their performance on a given task through experience. It involves using large amounts of data and mathematical models to make predictions or decisions without explicit programming.
There are two main types of machine learning: supervised and unsupervised. In supervised learning, the algorithm is trained on a labeled dataset, where the correct output is provided for each example in the training set. The goal is for the algorithm to make predictions on new, unseen examples that are drawn from the same distribution as the training set. Examples of supervised learning tasks include image classification, spam detection, and predicting the price of a house based on its characteristics.
In unsupervised learning, the algorithm is not provided with labeled training examples. Instead, it must discover the underlying structure of the data through techniques such as clustering or dimensionality reduction. Unsupervised learning is often used to explore and understand large datasets and can be used to extract features that can be used in a supervised learning task.
Machine learning has a wide range of applications, including image and speech recognition, natural language processing, and predictive analytics. It is being used in many industries, including healthcare, finance, and e-commerce, to improve decision-making and automate processes.
Choosing the Right Programming Language for ML
Choosing the right programming language for ML is crucial step in learning ML from scratch. While python might be the obvious choice for many, here are some other languages that can be used:
R for Machine Learning
R for ML
R is a programming language and software environment that is specifically designed for statistical computing and data analysis. It is a popular choice for machine learning because it provides a wide range of statistical and graphical techniques and has a large and active community of users.
Java for Machine Learning
Java is a popular programming language that can be used for machine learning. There are several libraries and frameworks available in Java for implementing machine learning algorithms and building machine learning applications.
Some popular Java libraries for machine learning include Weka, DeepLearning4J, Java-ML.
C++ for Machine Learning
C++ is a programming language that is often used for building high-performance applications, including those that involve machine learning. There are several libraries and frameworks available in C++ for implementing machine learning algorithms and building machine learning applications.
Some popular C++ libraries for machine learning include:
dlib: a general-purpose machine learning library that provides tools for creating complex machine learning models
TensorFlow: an open-source machine learning framework that can be used with a variety of programming languages, including C++
mlpack: a fast, flexible machine learning library that provides a wide range of algorithms
Python for Machine Learning
Python for Machine Learning
Python is a popular programming language that is widely used in the field of machine learning. There are many libraries and frameworks available in Python for implementing machine learning algorithms and building machine learning applications.
Some popular Python libraries for machine learning include:
scikit-learn: a simple and efficient library for data mining and machine learning
TensorFlow: an open-source machine learning framework that can be used with a variety of programming languages, including Python
Keras: a high-level neural networks library that runs on top of TensorFlow
Hands on experience with ML
Using ML to solve real world problems is an essential part of learning machine learning. It allows you to apply the concepts and techniques you have learned to real-world problems and get a feel for what it is like to work with machine learning in practice. Here are some tips for getting hands-on experience in machine learning:
Choose a problem to solve: Start by selecting a problem that you are interested in solving. This could be something you have encountered in your work or personal life, or something you have seen in the news. Gather and prepare data: In machine learning, data is the foundation of everything you do. You will need to gather and prepare data to train and test your machine learning models. Explore and visualize the data: Use visualization techniques to get a sense of what the data looks like and understand any patterns or trends. Select and apply an algorithm: Choose an algorithm that is appropriate for the problem you are trying to solve, and apply it to the data. Evaluate the results: Use evaluation metrics to understand the performance of your model and identify areas for improvement. Iterate and improve: Use what you have learned to make changes to your model and try again. This process of iteration is an important part of the machine learning process.
By working through these steps and repeating them on different problems, you can gain valuable hands-on experience in machine learning. This will help you develop the skills and confidence you need to apply machine learning in real-world situations.
Tools for Learning Machine Learning
There are many tools available to help you learn machine learning, including:
Online courses: There are many online courses and tutorials available that cover a wide range of machine learning topics. These can be a great way to learn at your own pace and in your own time. I'd suggest Andrew Ng's course on Coursera, it explains the concepts well. Textbooks: There are many textbooks available that cover machine learning concepts in detail. These can be a good resource for building a solid foundation in the field. Kaggle: Kaggle is a platform for data science and machine learning that provides a range of resources, including datasets, kernels (pre-written code that can be used as a starting point for your own projects), and online competitions. Machine learning libraries: There are many machine learning libraries available that provide pre-built algorithms and tools for building machine learning models. These can be a great resource for getting started quickly and experimenting with different approaches. Cloud-based tools: There are many cloud-based tools that provide access to machine learning resources, including hardware, software, and data. These can be a convenient way to get started with machine learning without having to invest in your own infrastructure. For example, Google Colab.
By using a combination of these tools, you can build the skills and knowledge you need to become proficient in machine learning.
Conclusion
Machine learning is a rapidly growing field that has the potential to transform the way we live and work. It involves training algorithms to automatically improve their performance on a given task through experience, and has a wide range of applications including image and speech recognition, natural language processing, and predictive analytics.
To get started with machine learning, it is important to understand the basics, including concepts such as algorithms, data, and error evaluation. It is also important to choose a programming language and get some hands-on experience by building projects and experimenting with different algorithms.
| 2023-01-01T00:00:00 |
https://www.linkedin.com/pulse/path-learn-machine-learning-how-become-ml-master-yuvraj-singh
|
[
{
"date": "2023/01/01",
"position": 24,
"query": "machine learning job market"
}
] |
|
Changing Job Skills in a Changing World
|
Changing Job Skills in a Changing World
|
https://link.springer.com
|
[
"Napierala",
"Joanna.Napierala Cedefop.Europa.Eu",
"The European Centre For The Development Of Vocational Training",
"Cedefop",
"Kvetan",
"Vladimir.Kvetan Cedefop.Europa.Eu",
"Thessaloniki",
"Joanna Napierala",
"Vladimir Kvetan",
"Search Author On"
] |
by J Napierala · 2023 · Cited by 32 — Using machine learning to measure job skill similarities. ... Combining learning analytics with job market intelligence to support learning at the workplace.
|
The growing body of knowledge on labour market generated based on the online sources translated into the increasing interest in taking advantage of the skills intelligence for policy making. In 2014, Cedefop started building a pan-European system to collect and classify online job advertisements data. The initial phase included only five EU countries. Yet, with time the project was scaled up and extended to the whole EU, including all 27 Member States + UK and all 24 official languages of the EU (Cedefop, 2019). This positive experience led Cedefop to join efforts with Eurostat (and creation of its Web Intelligence Hub) in developing well-documented data production system that has big data element integrated into the production of official statistics (Descy et al., 2019). Yet, the retrieval of good-quality and robust information from online data sources to deliver labour market analysis in an efficient way is still a challenging task. The identified key challenges in using online job advertisements (OJAs) for skills and labour market analysis are representativeness, completeness, maturity, simplification, duplication and status of vacancies (International Labour Organization, 2020). The computational challenges with building reliable time series data based on collecting information from online data sources can be grouped into four areas related to:
Data ingestion
Deduplication
Classification of occupations and skills
Representativeness
When the focus is on the data ingestion and landscaping part, then the source stability is one of the main technical problems, which has a direct impact on the representativeness of collected information and the reliability of further analysis. Firstly, some sources of information might be blocked from data collection not allowing for extraction of information, and prior agreements with the website’s owners will be needed to access the information. Secondly, some websites may not be available during the data extraction because of technical problems. Thirdly, there is also a natural lifecycle of the online sources as some new websites may appear while existing ones can close or rebrand. It has been shown that inclusion of the website that contained a large volume of spurious and anonymous job postings could lead to the discrepancy with the official vacancy statistics (International Labour Organization, 2020). In order to ensure stability of data sources, the added value of using tools like analytic hierarchy process to help in ranking of the online sources based on various dimensions, including information coverage, update frequency, popularity and expert assessment and validation, is explored. Footnote 5
The challenges with deduplication relate to the fact that it is common that the same job advertisement appears in various sources on the Internet. This can happen either intentionally, when employer publishes OJA on more than one portal, or unintentionally due to activities of aggregators—portals that automatically crawl other websites with the view of republishing OJAs. Very often, the content of such job advertisements is almost identical differing only in a small portion of the text (e.g. date of release). There are several ways to allow for identification of near-duplicate job advertisement to avoid counting the same information multiple times, e.g. using bag of words, shingling and hashing techniques (Lecocq, 2015). In the process of deduplication, the comparison of several fields in the job advertisement (e.g. job title, name of employer, sector) is done to determine whether it is a duplicate or not. Footnote 6 Metadata derived from job portals is another way to help identifying duplicate advertisements (e.g. reference ID, page URL). In addition, machine learning algorithms could be used to remove irrelevant content, e.g. training offers.
In the next phase of the data processing, the challenges relate to the classification of occupations, and skills emerge from the fact that the information is extracted from unstructured fields of job advertisements. For example, employers might have a tendency to conceal tacitly expected requirements by explicitly mentioning only a few skills from the list of required ones in online job advertisements. Similarly, the candidates building their online career profiles may signal only selected skills they have, for example, indication of “Hadoop” and “Java” could infer workers’ expertise as well as for “MapReduce” (Muthyala et al., 2017). Sometimes the same word may have different meaning depending on the context, e.g. philosophy as the field of study or as the company philosophy, informal written guidelines on how people should perform and conduct themselves at work; Java could either come from the job advertisement searching for IT or coffee making person.
In general, two approaches are used in the information extraction from unstructured text: cluster analysis and classification (Ternikov & Aleksandrova, 2020). For example, Zhao et al. (2015) developed a system for skill entity recognition and normalization based on information from resumes, while Djumalieva and Sleeman (2018) used online job advertisements data and employed machine learning methods, such as word embeddings, network community detection algorithms and consensus clustering to build general skills taxonomy. In a similar way, Khaouja et al. (2019) created a taxonomy of soft skills applying combination of DBpedia and word embeddings and evaluated similarity of concepts with cosine distance. Moreover, a social network analysis was used to build a hierarchy of terms.
The unavailability of high-quality training datasets was believed to constrain advancements in the use of AI in extraction of information from unstructured text. Yet, it is observed that solutions based on structured and fully semantic ontological approaches or taxonomies proved to work better allowing to extract meaningful information from online data compared to applications exclusively based on machine learning approaches (International Labour Organization, 2020; Sadro & Klenk, 2021). Nevertheless, the taxonomy-based extraction processes are not free from deficiencies, as the quality of extracted information tends to be as good as the underlying taxonomies used for this purpose (Cedefop et al., 2021). Plaimauer (2018) studying matches between taxonomy terms and language used in vacancies published on Austrian labour market shows that 56% of the terms from taxonomy never appeared in job advertisements. She also observed that longer terms were identified with less frequency in the vacancies’ descriptions. Grammatical cases in some language seem challenging for natural language processing tools, which often leads to misinterpretation of recognized skills (Ketamo et al., 2019).
The mapping of the unstructured text (e.g. of job titles, skills) to existing taxonomies (e.g. ISCO—International Standard Classification of Occupations) is usually done in a few steps, and pipelines are built for separate languages (Boselli et al., 2017). First the text needs to be extracted from the body of the job adverts; this could be done by bag of word or Word2Vec approach Footnote 7 (Boselli et al., 2017). In both cases the usual steps were applied to preprocess the text. Footnote 8 The bag of word extraction leads to creation of sets of n-consecutive words (so called n-grams); usually unigrams or bigrams are analysed (ibidem). The Word2Vec extraction is based on replacement of each word in a title by a corresponding vector of n-dimensional space. This approach requires huge text corpora for producing meaningful vectors (ibidem). The corpuses with specific domain can significantly improve the quality of obtained word embeddings. In the next step of the classification pipeline, machine learning techniques (e.g. decision trees, naïve Bayes, K-nearest neighbour (k-NN), support vector machines (SVM), convolutional neural network) are applied to match with the “closest” code. The similarity is judged based on the value of one of the existing indexes of similarity (e.g. Cosine, Motyka, Ruzicka, Jaccard, Levenshtein distance, Sørensen-Dice index).
The evaluation of the quality of obtained matches (e.g. between job titles and occupation classifier) is not an easy task, although the problem related to matching itself is not a new one as previously some AI solutions were developed for coding of open answers on job titles provided by respondents in survey data (Schierholz & Schonlau, 2020).
Yet, the main difference between the information on job titles provided by individual worker and information originating from job titles mentioned in online job advertisements is that the latter includes more extraneous information (e.g. “ideal candidate”, “involve regular travel”) and tends to be more difficult to parse (Turrell et al., 2019). One way to validate that the occupation classifier is generating meaningful predictions is to check the implied occupational hierarchies (Bana et al., 2021). For example, a classifier that misclassifies a high-skilled profession with a low-skilled one would be judged as performing worse than the one that would categorize such occupation as belonging to more general category but within adequate hierarchical occupational group. Nevertheless, Malandri et al. (2021a) who applied word embeddings approach to job advertisements data identified existing mismatches in the taxonomy compared to real market examples. In particular, analysing the market of ICT occupations, they showed that although in ESCO taxonomy data engineer and a data scientist belonged to the same occupation group, these are not similar occupations in the real labour market (ibidem). The previous studies show that the level of accuracy of extracted information depends from field to field and also on the level of detail, as the accuracy rate of six-digit occupation coding was about 10 percentage points lower than when done for major groups at two-digit ISCO level (Carnevale et al., 2014). A similar trade-off between more granularity and less accuracy was observed by Turrell et al. (2019) who decided to use three-digit occupation classification. Yet, using supervised algorithms it was proven to be possible at least for English language to achieve good performances (over 80%) in classifying textual job vacancies gathered from the online advertisements with respect to the fourth-level ISCO taxonomy (Boselli et al., 2017). Nevertheless, less than 85% of titles were correctly classified in the matching exercise of job titles advertised on Dutch websites with ISCO-08 ontology (Tijdens & Kaandorp, 2019). The manual check of the unclassified terms showed that job titles in vacancies could be either more specialized compared to the terms in ontology or vice versa. However, some wrong classifications also occurred despite the high reliability score of classifications for these titles that included some similar words, e.g. campaign manager versus camping manager (ibidem). Another challenge with finding matching occupation classifier is that sometimes job advertisements can have generic, meaningless job titles or no title at all. Therefore, it is also important to design and train the classifiers that, e.g. could suggest a job title acknowledging the content of entire job description as, for example, the proposed Job-Oriented Asymmetrical Pairing System (JOAPS) by Bernard et al. (2020).
Overall, the main disadvantage of classifying unstructured information with use of taxonomies is that they are not forward-looking, and the frequency of revisions that oftentimes lean on expert panels and surveys allows updating them with the information on the emerging skills and/or occupations only with substantial delays. The AI solutions were introduced to update ESCO taxonomy with information on occupations; however the detailed information on the applied procedure was not provided in the official reports (European Commission, 2021a, b). A tool with capacity to automatically enrich the standard occupation and skills taxonomy with terms that represent new occupations was proposed by Giabelli et al. (2020b, 2021). This tool identifies the most suitable terms to be added to the taxonomy on the basis of four measures, namely, Generality, Adequacy Specificity and Comparability (GASC) (for formal definitions of these measures, see Giabelli et al. (2020a)). Very often inconsistencies in terminology used by job seekers and the jargon of employers when describing the same skills are the reasons for which the solution developers struggle when matching information from different data holders (Sadro & Klenk, 2021). One way to overcome the problem is to apply the AI and advanced linguistic understanding and build a platform which “translates” jargon of job advertisements to a simpler language for job seekers (Sadro & Klenk, 2021). The revealed comparative advantage (RCA) Footnote 9 was used as a measure of the importance of a skill for an individual job by Anna Giabelli et al. (2020a) to enrich ESCO taxonomy with real labour market-derived information about skills relevance and skills similarity. Footnote 10 Another AI-based methodology to refine taxonomy was proposed by Malandri et al. (2021b). The novelty of this approach is based on the automation of the process, which is to be carried out without involvement of experts. It is based on the implementation of domain-independent metric called hierarchical semantic similarity applied to judge the semantic similarity between new terms and taxonomic elements, which value is later used to evaluate the embeddings obtained from domain-specific corpus and, eventually, the suggestions on which new terms should be assigned to a different concept are made based on comparison of these evaluations. Chiarello et al. (2021) proposed a methodology that can be used to improve taxonomy. The innovation of this approach lays in the use of the natural language processing tools for knowledge extraction from scientific papers. The extracted terms are later linked with the existing ones allowing for identification of these which were not included in the taxonomy before.
As the final step before starting to analyse online data, it is crucial to explore its representativeness. The sources of potential bias in online job advertisements are multiple (Beręsewicz & Pater, 2021). Moreover, the population of job vacancies and its structure are practically unknown, and for non-probability samples the traditional weighting cannot be used as an adjusting method (Kureková et al., 2015b). Researchers who recognize the problem of online data representativeness very often provide results of their analysis together with information from other data sources, i.e. representative surveys and registry data [e.g. Colombo et al. (2019)]. Beresewicz et al. (2021) suggest applying a combined traditional calibration with the LASSO-assisted approach to correct representation error in the online data.
| 2023-07-14T00:00:00 |
2023/07/14
|
https://link.springer.com/chapter/10.1007/978-3-031-16624-2_13
|
[
{
"date": "2023/01/01",
"position": 75,
"query": "machine learning job market"
}
] |
Good for tech: Disability expertise and labor in China's ...
|
Good for tech: Disability expertise and labor in China's artificial intelligence sector
|
https://firstmonday.org
|
[] |
by D Wu · 2023 · Cited by 8 — Essential for machine learning systems to recognize patterns from a ... job market by structural ableism. Third, and more importantly, the workers ...
|
People with disabilities are often perceived as being “given” the opportunity to work, rather than “providing” valuable labor. Centering on disabled data workers as experts involved in the quotidian construction of artificial intelligence (AI) systems in China, this article shows that disability expertise and labor can afford a technical edge to AI systems in a certain political economy. In the case examined, the work of consistently synchronizing interpretations of the ambiguous data and elusive rules of smart home systems prefers a stable annotation workforce with coordinated cognition and trained judgment. This technical demand has come to be met by a committed team of skilled disabled workers, who are pushed out from mainstream job market by systemic ableism, and pulled in by disability-informed expertise that reconfigures space, time, and political economy to meet non-normative bodyminds. Through this exceptional case run by a disabled people led organization, I draw attention to disabled people’s under-examined role as system-builders of information technologies as opposed to users, victims, or inspirations, and highlight the transformative potential of disability expertise.
Contents
Introduction: Tech for good, or good for tech?
Objectified resource, undervalued expertise
Stability as technical edge
Escaping ableism: “I’d do anything but massage!”
Embracing disability expertise: “Ghost work” alternatives
Conclusion
Introduction: Tech for good, or good for tech?
“Microwork Helps Disabled People Fly Against the Light.”
“AI Brings New Jobs for Disabled People’s Employment.”
“Big Data Annotation Heralds New Disability Assistance Model.”
Numerous news headlines in China have proclaimed people with disabilities to be the beneficiaries of new kinds of job opportunities serving the development of artificial intelligence (AI) systems (e.g., Netease.com, 2018), such as data annotation. Essential for machine learning systems to recognize patterns from a dataset, data annotation often entails a large number of human workers to hand code, label, and sort training data. In recent years, government agencies and technology companies in China have enthusiastically set up programs aimed at recruiting and training disabled people to conduct data annotation work, often branded “tech for good.” Such jobs, they claim, empower disabled people by increasing their income, by offering ways to overcome physical barriers, and by making them “useful” to society thus fulfilling these workers’ “self-worth” (JD.com, 2018).
Scholars on technology labor have demystified such narratives. Data annotation work, often organized in the form of microwork or crowdwork, is known for exploitative labor conditions that underpay, deskill, and surveil workers, who must stay hypervigilant to compete for tasks, with little means for collective action (Irani, 2016, 2015; Ekbia and Nardi, 2017; Gray and Suri, 2019; Roberts, 2019; Altenried, 2020; Vallas and Schor, 2020). Disability studies scholars have also detailed how digital work may simultaneously empower and exploit, include and exclude, people with disabilities (Yu, et al., 2019). On the one hand, information technologies have provided affordances for people with certain disabilities to bypass discrimination (Gray and Suri, 2019), to work around physical inaccessibility (Dobransky and Hargittai, 2006), to forge communities of resistance and self-governance (Lin and Yang, 2020), and to express agency, self-identity (Goggin, et al., 2019), and a sense of contribution (Boellstorff, 2019). On the other hand, new forms of algorithmic cruelty (Irani, 2016; Gray and Suri, 2019), digital inaccessibility (Zyskowski, et al., 2015), trade-offs between flexibility and security (Qu, 2022), and exacerbated precarity (Lin, et al., 2019) abound in information technology work for people with disabilities. Some disability theorists question the capitalist imperative to be productive altogether (Mitchell and Snyder, 2010).
This paper moves beyond assessing whether tech is truly “for good.” Rather than debating how tech work may empower or exploit people with disabilities, I focus on how disabled people’s labor may in turn transform technology. I show that the labor and expertise of disabled people can in fact be “good for tech.” The disabled workers examined in this study provide highly competitive data annotation services to their big tech client, “not by playing the charity card or fighting a price war,” in their own words, but by fulfilling a key structural need of the AI system. I approach people with disabilities as not the receiving end of technological promises and perils, but as experts involved in the quotidian construction of “intelligent” systems. This is inspired by information studies’ attention to the materiality of technical configurations, as well as disability studies’ emphasis on the agency of disabled people. Taken together, the two fields shed new light on the intricate relationship between disability and information technology.
My analysis focuses on one data annotation program run by a disabled persons’ organization (DPO) that I call ENABLE. I draw upon 19 remote interviews and two field trips between early 2020 and summer 2021, as well as my own five-year professional experience of managing disability advocacy programs in China’s non-profit sector. My interlocutors are a team of workers with visual or physical impairments, hired to label Chinese natural language processing (NLP) data for smart home technologies developed by a leading Chinese tech company I call AITech. ENABLE recently outperformed many non-disabled competitors and became a major data annotation service provider for AITech. This case is rather an exception, not the norm, of data annotation programs in China. As I will elaborate, run by disabled people themselves, the examined program has distinctive approaches to data labor.
Centering on the embodied experience of disabled workers and the inner workings of sociotechnical processes, I argue that the labor and expertise of disabled workers offer the AI system a technical edge. My argument is three-fold. First, as ENABLE’s workers taught me, data annotation for smart home AI systems entails human interpretations of highly ambiguous data, to which the rules can iterate on a weekly basis. To consistently formalize tacit knowledge that improves the system’s response to user queries, a stable workforce of human annotators with coordinated cognition and trained judgment is preferred. Second, this technical demand has come to be met by a committed team of skilled disabled workers, who are pushed out from the mainstream job market by structural ableism. Third, and more importantly, the workers are pulled in by the DPO’s unorthodox configurations of workplace to meet the workers’ heterogenous bodyminds. I use anthropologist Cassandra Hartblay’s concept of “disability expertise” to unpack the disability-informed knowledge of flourishing in uninhabitable worlds (Hartblay, 2020). In addition to non-normative spatial and temporal strategies, the DPO deployed a form of disability expertise that I call “resource hacking,” optimizing precarious resources in ableist political economies for maximum disability gain, or in one interlocutor’s words, “making resources serve you even when you don’t have any.” Disabled workers offer what anthropologist Michele Friedner calls “multiple regimes of value” to techno-capitalism, not only through reinscribing stigma (Friedner, 2015b), but also the deployment of genuine expertise acquired through the lived experience of disability. Through this case, I bring to the fore the role of disabled people as system-builders of information technologies rather than users, victims, or inspirations, and highlight the transformative potential of disability expertise.
Objectified resource, undervalued expertise
Disability has routinely figured as an epistemic and material resource in the history of information technology (Wu, 2021). The sound spectrograph, a precursor to speech recognition technologies (Li and Mills, 2019), was initially proposed to improve deaf education (Mills, 2010). Early time-compression technologies were popularized by blind aural speed-readers (Sterne and Mills, 2020). At robotics and AI labs at MIT, analogies between disabled bodies and machines were a recurring tool to theorize disembodied intelligence (Richardson, 2015). Disability frequently serves as a metaphor, precursor, or advertisement for the research, production, and commercialization of technoscientific objects that are ultimately designed for non-disabled users, a pattern that historian Mara Mills (2010) calls “assistive pretext.” Disability is also constantly invoked as a “narrative prosthesis” (Mitchell and Snyder, 2001) to metaphorize arguments in cultural studies of technoscience, in over-objectified and under-constructed ways (Jain, 1999). In contemporary urban India, anthropologist Michele Friedner shows that the immobility, sociality, and affect of deaf workers added multiple forms of value to their employers, many in the information technology sector, in ways that do not always benefit deaf people (Friedner, 2015b).
While the technoscientific extraction of value from objectified disabled body-minds proceeds apace, the actual knowledge and expertise of disabled people are ironically ignored. Science and technology studies scholar Ashley Shew (2020b) laments that disabled people are too often enrolled as “marginal cases” and objects of “thought experiments” in technoscientific imaginaries, while being subject to “epistemic violence” (Ymous, et al., 2020) that denies them a role as real experts and legitimate knowers. Disability scholars Aimi Hamraie and Kelly Fritsch (2019) urge us to center disabled people as experts in technoscience, and as agents who can harness technology for political change, proclaiming what they call a “crip technoscience.” Likewise, anthropologist Cassandra Hartblay calls attention to “disability expertise,” forms of knowledge that “disabled people develop about unorthodox configurations of agency, cultural norms, and relationships between selves, bodyminds, and the designed world.” [1]
This article brings the critique of value extraction and the recognition of disabled people’s expertise into conversation. In the case examined, legitimate disability expertise — in tension and in tandem with objectified resourcing of disability premised on stigma and inequality — forms a crucial part of the value added by the disabled workers. I show that when crip technoscience and disability expertise are practiced, the value of disability need not be created entirely at the expense of disabled people, and labor relations in information technology can be otherwise.
Stability as technical edge
Data annotation for smart home AI systems is far more complicated than rote “click work.” To excel at such work takes expertise. As of 2020, ENABLE has outperformed many non-disabled competitors, becoming a major supplier of data annotation services for AITech. In my experience as a non-profit professional, most corporations’ motivation to hire disabled people was to fulfill a disability employment quota mandated by the Chinese government, because non-compliance could result in a significant financial penalty (Liao, 2021). Often, even such strong incentives could not persuade employers. Many would rather pay the fine, or rent a disability certificate as a token of compliance without giving the disabled person real work (Qu, 2020). Surprisingly, at the time of this research, AITech has not claimed any disability employment quota from the hiring of ENABLE’s disabled workers. Neither, as is often the case, are the disabled workers receiving less pay for the same work as non-disabled annotators.
To understand what makes ENABLE’s labor so competitive, we need to unpack what the job entails. Tasked with classifying user intentions, rating sound qualities, or sometimes determining the gender and age of smart device users, the annotators engage in complex decision-making processes that demand skilled listening and selective in/attention (Semel, 2022). I argue that the act of classifying human intentions and interpreting sounds amidst constant iterations of commercial AI algorithms, is intrinsically ambiguous and volatile. This technical condition makes a committed data annotation workforce with trained judgment and coordinated cognition more productive than forms of labor that are highly flexible and contingent.
Ambiguous data
Contemporary voice-based AI systems built on supervised machine learning algorithms require huge data sets of high-quality, annotated user requests (Tubaro, et al., 2020). The blind and low vision workers’ official job title is “intent annotator.” Every day, they listen and determine the intention of user queries to voice-activated smart home systems, and code them into thousands of specific “features” that trigger the correct machine response. For example, if a user query reads “turn on the AC” in Chinese, annotators will sort it into “hardware control.” It sounds straightforward. But not all queries are this clear-cut. For instance, a surprisingly large number of users engage these devices in casual conversations. In this case, annotators need to determine what emotions are conveyed, whether the user is talking with another human or interacting with the device, making a command, or simply saying nonsensical words. Sometimes, the name of a song could sound like a conversation and escape an ear unattuned to the latest trends in pop culture. Lihua, a well-educated blind annotator, often finds herself frustrated by the ambiguity of the data. She describes it as making meaning out of “a broken conversation.”
The conversation is “broken” for many reasons. In between the annotator and the user lie multiple layers of cuts and transcriptions. The user’s speech is first cut out of their social context, converted from analog audio information to digital data, then transcribed from speech to text, and segmented into short phrases for annotation. Annotators, without necessarily hearing the human voice or the full sentence of the query, now need to judge the user’s “true” intention. Here is an example given by an annotator. In Mandarin Chinese, the written form of “you say you like me huh” (ni shuo ni xi huan wo ma) can at least allow three interpretations: “Did you say that you like me?” “Say that you like me!” or “Do you think you like me?” Without knowing the intonation and punctuation from the original speech, it is difficult to judge the precise meaning or emotions.
Blind annotators use screen readers — software applications that convert text into synthetic speech — to read the textual data. Screen readers are key access tools for the blind and low vision workers. Through ENABLE’s negotiation, AITech made their annotation system screen-reader compatible, so workers can listen to the content of the data and navigate the portal aurally. One may assume that annotating with a screen reader would be a disadvantage for blind workers. But sighted annotators’ experience suggests that the confusion was less caused by sensory differences than by the data’s lack of social and linguistic context. Kai is a sighted annotator with physical impairments, who works on the same types of data as the blind annotators. To him, reading those texts with vision is just as “brain burning.”
The act of classification is intrinsically reductive (Bowker and Star, 1999). User intent classification attempts to impose an artificial social order (Suchman, 1993) onto the messy, complex inner world of human users so their needs can be made legible to the machine. Data annotators are part of the layers of mediation that render the technology and end users mutually legible and constructive to each other (Robbins, et al., 2021). Far from an impartial, objective, and rote act of simple “click work,” data annotation is a “sense-making process” (Klein, et al., 2007), in which human workers with heterogenous lived experience assign meaning to snapshots of decontextualized content with prescribed labels. To excel at such work means producing consistent interpretations for not only the ocean of “commonsensical” data, but also the “brain burning” edge cases. Consistency comes from experience and coordination.
Elusive rules
If reading minds in broken words is challenging, judging sound in isolation can be equally frustrating. Staffed by predominantly sighted wheelchair users, ENABLE’s team in western China focuses on sorting sound clips, such as identifying the “wake word” (for example, “Alexa” or “Hey Google” are wake words for their respective devices), determining the age or gender of the speaker, telling speech from non-speech, and rating the clarity of speech. These sound clips are sent to the annotators for manual identification, precisely because they were accented, unclear, or confusing. Their job is to literally separate signal, or the lack thereof, from noise.
Though meticulous rules for how to annotate exist, interpretation of the rules is arbitrary. Wenbo is a young man with a humorous and relaxed demeanor. Sitting in his wheelchair, he had a cup of green tea and a cigarette on the table while we video called. The moment I asked him about annotation standards, he suddenly got serious:
Speaking of this, let me just say — there is no standard! If a lighter costs fifty cents, it costs fifty cents. But for things like sound, everyone’s ears are different, and everyone’s accents are different. [...] If the wake word was spoken very fast, I may find it OK and clear. But if the Quality Assurance (QA) person finds it unclear, then it’s not OK.
The ambiguity of judging sound is a recurring theme among workers who sort audio data. Meihui has a college degree and uses a wheelchair. For her, the hardest part of the job is to listen “objectively” and mechanically to something “subjective” and animate. In her view, “sound is meant to be a living thing! [...] But the QA would apply dead rules to judge our work.” Multiple annotators were frustrated when they listened to the same thing as the QA person but heard differently. The QA has the power to determine the “accuracy rate” of the annotated data by spot-checking datasets. If the set has an accuracy rate lower than 98 percent, the entire set would be sent back for the annotators to rework.
The heterogeneous, situational, and immersive qualities of sound (Sterne, 2003; Helmreich, 2007; Zdenek, 2015) frequently clashed with the rigid corporate quest for a single absolute meaning of an isolated sound bite, arbitrarily ruled by ears with higher epistemic authority. To mediate such tension, the workers’ strategy is to train themselves to listen like the QA (who supposedly represents the client) irrespective of what they actually hear. As human-computer interaction scholars argue in the context of computer vision data annotation, power dynamics, and organizational hierarchy have a more profound impact on the outcome of data annotation than individual bias (Miceli, et al., 2020).
Most challengingly, the constant iterations of commercial AI algorithms demand frequent updates in the annotation rules. The annotators recall modifications in rules on a weekly basis. Each time a new specification, combination, or option becomes available, the calculation of the “correct” label is subject to change. Not only are annotators required to learn the rules promptly, but the more knowledge they have about the genealogy of the existing rules, the quicker they can preclude wrong interpretations of the new rule. In other words, annotators with stronger institutional memory can better recognize patterns in the ever-changing rules, and make more accurate predictions of interpretation.
The disabled workers’ long-term knowledge also brings direct improvements to AITech’s product. To synchronize data interpretations between the annotators, QAs, and the client, the disabled workers attend weekly meetings with the developers. In these meetings, the annotators provide direct feedback on trends, problems, and recommendations. Often, the developers end up adjusting the feature of the product based on common queries that the annotators observe. As Danni, a geeky, young blind woman, remarks, “we are the ones who understand the users most.” The close feedback loop ensures that developers know what is happening on the ground.
The disabled workers function as skilled technicians who glue together elusive tacit knowledge derived from shifting managerial and technical specifications in a fast-paced institution. In the face of endless new data and new rules, high-quality data annotation means consistently predicting the preferred interpretations by the client and QAs. The best way for the annotators to hone such skills is through long-term, close collaboration, with iterative feedback from QAs, developers, and users. ENABLE’s director Zhang Fan takes pride in the fact that their annotators “get” AITech developers better, because they have been around longer, and are more familiar with earlier versions of the annotation rules, than the non-disabled QAs who have a much higher turnover rate.
Data annotation tasks and labor forms are not homogenous. While some tasks can be satisfactorily performed by part-time, flexible crowdworkers managed by platform algorithms, or short-term annotation “factories,” other tasks may favor a full-time, trained workforce that is in close coordination with developers (Lavee, et al., 2019; Semel, 2022). Forms of labor are contingent upon the nature of the data and tasks, level of secrecy, project duration, layers of outsourcing, and localized political economy of annotation labor. In the case of AITech, to synchronize the interpretations of ambiguous data and elusive rules, a constant workforce of data annotators who have rich tacit knowledge, good institutional memory, and a strong working relationship with the developers, stands out as superior to other more flexible workers. The quality of the data is thereby closely tied to the stability of the annotation workforce. Here, stability is not achieved through platform-based labor that is always-on, spatially heterogenous, and temporally flexible (Altenried, 2020), but by capitalizing upon structural ableism and disability expertise.
Escaping ableism: “I’d do anything but massage!”
The stability of disabled workers has come to be instrumental to the quality of data annotation for AITech. As ENABLE’s workers note, it is not easy to find so many experienced annotators, and most non-disabled workers would not stay in the job as long because it is “too tedious.” However, disabled workers are not naturally stable but are rendered so. In this section, I argue that the disabled workers, pushed out of mainstream labor market and pigeonholed into a few job options by structural ableism, long for a sense of mobility that, ironically, hinges upon supplying their immobility to the AI company.
The labor regime of disability in contemporary China is strongly shaped by state biopolitics and unchecked ableism. Canji, the legal category of disability, defines disability based on biomedically measured deficits in bodies and minds (Kohrman, 2005). This medicalized ideology imposes rehabilitation as the pre-requisite for disabled people’s full participation in society, deprioritizing accessible infrastructures (Cui, et al., 2019), equal education (Hu and Lin, 2017), and competitive work opportunities. Although official data estimates that 56 percent of working-age disabled people are employed (Chinanews.com, 2019), nearly half of these jobs are categorized as agriculture and cultivation, and over another quarter are “flexible” employment (China Disabled Persons’ Federation, 2021), namely temporary or part-time jobs. Key targets of poverty alleviation campaigns, households of disabled people earned only 57.1 percent of the national average income in 2018 and the gap continues to widen (Cheng, 2021).
Since the market reforms, the state has attempted to leverage economic incentives for private employers and self-employment, in contrast to the direct state investment in welfare enterprises during the Mao era (Huang, et al., 2009). The employment quota policy is a major instrument. Instituted in the 1990s, the policy mandates public and private entities to reserve at least 1.5 percent of their workforce for people with disabilities. Failure to comply shall result in financial penalty. In practice, however, the system is poorly enforced, and has created perverse incentives (Liao, 2021), such as performing “fake employment” that rents a disabled person’s certificate without real work.
Coupled with the lack of systemic opportunities is the abundance of restrictions. For many blind and low vision workers at ENABLE, their life trajectory was prescribed early on — go to special schools, take separate exams, and, if lucky, go to a special education college to study massage and become a massage therapist. Introduced as vocational education programs for students in blind schools in the 1930s (Tie, et al., 2011), massage programs have gradually morphed into an institutionalized effort to generate scalable jobs for blind people in contemporary China (Li, et al., 2022). The protective policies had constraining consequences. Massage has since been culturally imagined as the default occupation for people with visual impairments, and blind people as incapable of other professions (Dauncey, 2020; Li, et al., 2022). As a result, while mainstream universities remain inaccessible to most blind students (Hu, 2022), in special higher education, few majors are open to blind students. Roughly 80 percent of visually impaired students in special colleges major in massage (Li and Fu, 2015), many of ENABLE’s workers included.
“Escaping from massage” becomes a key drive for ENABLE’s blind and low vision workers to explore data annotation as a new profession. Some blind annotators lamented that they would do “anything but massage.” Similarly, when asked about their interest in data annotation, sighted workers with physical impairments frequently speak about the desire to “leave home,” “go out,” and “experience life,” instead of interest in the work itself. At play is less of a “politics of destination” where immobility is experienced as displacement (Chu, 2010), but a “politics of escape” in which departure from an assigned destination is an end itself. With a few exceptions, most workers at ENABLE came from an urban, lower to middle class background. Compared to China’s predominantly rural disabled population, they had relatively more means to defy their “destiny” and endure the precarity of constant circulation between gigs, trainings, and jobs. Data annotation emerged in the array around 2016.
Paradoxically, the workers’ yearning for mobility has come to rely on marketing their “stability.” Workers often cite “stability” as their comparative advantage to their non-disabled competitors. Probed further, however, they would speak of “lack of better options,” or “taking jobs more seriously.” To them, “stability” is essentially a euphemism for social and physical immobility. As Friedner (2015a, 2015b, 2014) has argued, the stigma of disabled people’s immobility is often reinscribed as value in the name of stability in late capitalism. Despite constant motion of moving around horizontally, Chinese disabled workers feel that they barely move upward in the vertical social ladder.
By contrast, tech discourse in China often naturalizes such stability. In a commentary by a well-subscribed tech media, people with visual impairments are described as “naturally gifted” to do user intent annotation, because they are “used to listening to information” and have “very strong meaning comprehension and linear logical abilities” which makes them “understand and reconstruct meaning better than normal people.” Disability hereby is essentialized as a fixed biological reality, rather than a relational and political experience (Kafer, 2013). In addition, the article notes, “with fewer visual interferences, their attention is more focused.” Although reframing a commonly assumed deficiency as an advantage may seem uplifting, the theory is rebutted by the workers for downplaying the structural restrictions imposed upon blind people. Like the indigenous women portrayed as “natural” circuit assembly workers in 1960s United States (Nakamura, 2014), disabled women and men in contemporary China become naturalized labor for AI companies. Similar discourses can be found today in the United States, where autistic data workers are often depicted as technologically gifted for AI but denied personhood (Keyes, 2020). At ENABLE, some annotators themselves may resort to naturalizing narratives when making a case about their productivity; but almost all of them are wary of attempts to pigeon-hole them yet again. As Yang, a shy blind man remarks, “if all blind people start doing data annotation, then it is like massage all over again!”
Unfortunately, naturalizing the stability of disabled workers has material consequences. Despite their evident value and proven skills, ENABLE annotators have limited prospects for upward mobility within AITech. Chunlin is an experienced blind annotator. When we talked in 2020, she had worked for over two years as an annotator, but witnessed AITech’s non-disabled annotators being promoted in less than a year:
Chunlin: Regardless of how good you are at annotation, your opportunities are frustratingly limited.
Me: Why?
Chunlin: Many reasons. From my perspective, I can see that accessibility is an issue. Currently AITech only made the annotation portal accessible, but not the portal for arbitrators [a higher-level position than annotators].
Me: Why didn’t they modify the arbitrators’ portal?
Chunlin: My guess is that they never thought about making us arbitrators.
Indeed, if annotation is where disabled people “naturally” belong, then there is no need to plan for a path that involves them. The opposite of accessibility is therefore not inaccessibility, but restricted access (Ellcessor, 2016), preserved for people who are deemed more mobile and worthy.
Disabled data annotators at ENABLE provided a crucial human resource to enhance the quality of smart home AI data annotation. The absence of better job opportunities due to systemic ableism and the medicalization of disability in China explains what pushed many ENABLE workers out of the mainstream job market. In the next section, I unravel what pulls many workers to stay despite limited career development.
Embracing disability expertise: “Ghost work” alternatives
Limited opportunities aside, data annotation is not automatically a superior job option. Multiple ENABLE workers have previously conducted platform-based, home-bound annotation work, and suffered from the same kinds of algorithmic and human cruelty often dubbed as “ghost work” (Gray and Suri, 2019). I argue that it is the disability expertise of ENABLE and their workers that made “ghost work” more humane, pulling many workers to stay in this particular workplace. Disability expertise refers to disability-informed, non-normative knowledge of inhabiting the world. Domains of disability expertise include strategies of managing perception, claiming citizenship, and living under domination (Hartblay, 2020).
Here, I show how disability expertise unfolds in high-tech workplaces. I elaborate on three domains of expertise deployed by the disabled workers that reconfigure space, time, and political economies to serve bodyminds with disabilities. Particularly, I propose a new form of disability expertise that I call “resource hacking,” a set of pragmatic skills that disabled activists, especially in resource-poor contexts, develop through navigating different variants of ableism in government, corporations, and the society, while leveraging their fragmented resources to move the needle for disability advocacy.
Co-creation of access
ENABLE’s operational model stands out from other disability AI data annotation programs — platform-based or non-disabled people led business process outsourcing — in their deliberate efforts of community building. To this end, a shared physical space is crucial. ENABLE devoted tremendous efforts in locating, partnering, and mobilizing funding for accessible and affordable offices and living spaces in major cities. Accommodation is not an afterthought, but a precondition. ENABLE had to reject many clients to avoid compromises on accessibility. Free dormitory space in big cities and a stable salary made it possible for many workers to experience life in different cities with “financial and psychological independence,” as one worker puts it. Many of them became friends through work and organized weekend trips together. Rongfei came from a small village in central China. Growing up, she never met anybody who used a wheelchair like herself. The relentless staring at her wheelchair by people in the street used to discourage her from going out. But now traveling with a dozen wheelchair users together brings her a sense of pride. Meihui, who used to walk with crutches to appear less “crippled,” also echoed how she was liberated by, rather than “confined to,” her wheelchair, thanks to a community of wheelchair users who taught her how to roll. These physical spaces that are made accessible allow ENABLE’s workers a sense of “membership and mattering” (Lynch, 2013).
The meaning of physical space can also be symbolic. ENABLE’s Shanghai office is a typical, white-collar office with about 30 individual cubicles and computers, located in a high-tech compound. Some annotators have posted photos of their office on social media, or have invited parents to visit the office, to show that they now live “a decent life.” Many workers recognize that this does not fit the “inclusive employment” canon as promoted by the United Nations’ Convention on the Rights of Persons with Disabilities (CRPD), in that they are not working alongside non-disabled colleagues. Nevertheless, annotators feel more socially integrated by doing ordinary things like commuting, working for eight hours a day, or even squabbling with discriminatory neighbors. A few disabled women especially highlighted to me how they appreciated working “with a computer” and inhabiting an office that looks “white-collar” to their family and friends. The physical workspace and particular appearance of informatics work can be integral to workers’ job experiences and even their identities (Freeman, 2000). These embodied, physical “disability worlds” (Ginsburg and Rapp, 2013) made the work much more meaningful for the annotators than just clicking alone on a computer at home earning the same income.
Digital spaces are also made accessible, a feature essential for the blind and low vision workers to annotate texts. According to director Zhang Fan, who himself is a man with low vision and uses magnifiers and screen readers, the negotiation with the client to advocate for screen-reader compatibility is a delicate process: “If you ask for too much, the client freaks out and finds you troublesome. But if you ask for too little, then the system is not usable.” It requires constant “frictioned negotiations of access and privilege” [2]. One advocacy success, in ENABLE’s view, is that after working together and witnessing the productivity of blind people, AITech developers started proactively consulting ENABLE for accessibility advice before significant system updates.
Even if the portal is made screen-readable, effective access still requires situated knowledge of diverse epistemologies. All visually impaired people do not work alike. As education researcher Lucia Hasty points out, visual learners process information from “whole to part,” whereas non-visual learners may approach from “part to whole” (Hasty, n.d.). Each of these categories of epistemology are infinite spectrums. For example, screen readers typically read a Web page from top-to-down, left-to-right. Blind annotators find it inefficient. Jiabao is one of the programming enthusiasts in the office. In his words, “screen reader compatible systems are merely functional, but not efficient. Efficient systems should create a near-non-disabled experience.” I interpreted his words as not a desire to become normates, but the demand for considering blind people’s epistemic approach as the starting point of access, rather than rigidly translating one sensory modality into another (Lundgard, et al., 2019). This is the job of Wenyu, ENABLE’s in-house blind programmer, who develops shortcuts and add-ons so annotators can “fold” the linear reading sequence of screen readers using keyboards. Meanwhile, low vision workers like Shujun do not necessarily use screen readers. Her access needs are an appropriately sized monitor and a laptop stand that allows her to lean her face towards the screen. Because she sees shapes and colors, Shujun often jumps to where she wants to click based on her memory of the shape of the text.
Access is also profoundly relational at ENABLE. Sighted and blind workers are paired to work on the same data set, so they can compare results and ensure a higher success rate. Off work, blind workers put their hands on the shoulders of low vision workers and walk to the subway station together. While travelling, those who use crutches and those with wheelchairs assist each other in different tasks. The disabled workers are relying not on high-tech solutions, but rather on what anthropologist Arseli Dokumaci calls “microactivist affordances,” namely, everyday acts through which disabled people become affordances for one another in the absence of a readily accessible environment (Dokumaci, 2020). Tacit techniques such as left-and-right hand coordination, or monitor settings that do not hurt eyes, are circulated among workers and staff members through collective trial and error. Access at ENABLE is not a standardized checklist, but a never-ending process of “care work” (Bennett, et al., 2020) centered on the ethics of interdependence (Mingus, 2010).
Crip time at work
The second important practice that made ENABLE a productive workforce for AITech, and a relatively satisfactory workplace to the workers, is their non-normative management of time, namely, “crip time” at work. “Crip time” is a concept and practice deployed by disability activists and scholars to complicate the temporal norms set by industrial time (Hendren, 2020). As disability scholar Alison Kafer puts it, “crip time bends the clock to meet disabled bodies and minds” [3]. Crip time is often imagined as incompatible with work. Words invoked to describe the presumed lack of productivity of disabled persons, often implicate time — “inefficient,” “slow,” “late,” “chronic illness,” or “cannot handle long hours.” ENABLE’s workers recall constant struggles against these temporal stereotypes. Disability scholars and activists, meanwhile, use the notion of crip time to urge a reimagination of human worth that is not bound by economic time (Kafer, 2021).
Workers at ENABLE sought to reconcile the tension between crip time and work within the bounds of corporate production. Instead of segmenting linear, progressive schedules and maximizing unit time productivity, ENABLE created a separate timeline in parallel to, but also intercalated with, corporate time. They negotiated a contract with fixed salaries for the workers specifically to set weekly group-based performance indicators rather than indicators based on individual piecework. Unlike platform-based crowdworkers, who must remain hypervigilant to compete for tasks, the disabled annotators as a whole become a production team. Because labor time does not unfold evenly across the team, individual crip time is respected.
The customization of pace did not necessarily compromise their performance. Delivering in teams guarantees that workers meet the clients’ targets while no one must work overtime. Nevertheless, the fluidity of crip time management can run into conflict with disciplining corporate time, especially with the prevalence of corporate surveillance technologies. For instance, when some workers needed a longer bathroom break to get around in wheelchairs, the QA questioned why they were not detected as “active” in the system for over 30 minutes. Overall, however, through protecting the boundaries of collective crip time, most ENABLE workers with whom I spoke experienced their work as reasonably paced.
Crip time is often perceived as slower than industrial time. But it can also get ahead. To gain control over speed, the annotators developed unconventional listening strategies. For example, if speeded up, screen readers can afford annotators with “speeds that appeared fast to the normate, while feeling timely to disabled people” (Sterne and Mills, 2020). However, most blind annotators find high-speed reading challenging in the context of annotation, because the data itself is already ambiguous and confusing. What they do instead is to disrupt time. As Danni explains:
At first, you may listen to every line in the dropdown menu in order. Once you become familiar, you can directly cut in. You may only listen to a single word of that line and move on. [...] You can just feel that the correct label is in this line.
Rhythms of work become increasingly aligned with the skilled ear. By shortcutting time, the annotators disrupt the imaginaries of linear, progressive time that deem their ways of knowing as necessarily inefficient.
Crip time also encourages budgeting significant time buffers, planning for uncertainties, and refusing to adhere to oppressive timeframes. As Katzman, et al. [4] put it, “crip time reflects the unpredictable, at times defiant, nature of human body-minds.” Contingencies are a built-in feature of crip temporality. ENABLE’s management is aware that the next iteration of AITech’s system may demand more vision in completing certain tasks, such as reading multiple rounds of conversations or labeling underlined content. This is hardly any surprise to the disabled workers, for whom living with uncertainties and exclusion has been the norm. They are prepared for hard negotiations, and more importantly, reserving the option of refusal. Zhang Fan’s plan for when that day comes is to “first, advocate for accessibility. If that’s not possible, then we will negotiate to see if it is ok for us to slow down a little.” Switching clients will be their last resort, but they remain firmly against short-term contracts.
As the COVID-19 pandemic reshuffles scheduling, pace, and the experience of time, many disability scholars argue that we now are all living in crip time (Samuels and Freeman, 2021). Out of sheer necessity, we are finally allowed to be “asynchronous,” to take the time, and to be together in time in ways for which the disability community has long been advocating (Goggin and Ellis, 2020). ENABLE’s practice demonstrates how crip temporal strategies can work in a corporate setting, to bargain with regimes of time where simply no human is fast enough.
Resource hacking
Finally, ENABLE’s expertise of consolidating fragmented resources in ableist political economies for maximum disability gain, or what I call “resource hacking,” is what made the collaboration with AITech possible in the first place. The term is inspired by ENABLE’s director Zhang Fan, who describes their approach as “making resources serve you even when you don’t have any.” We have seen how the AI company profits from the skilled labor, the naturalized immobility, and the collective expertise of disabled workers. But these benefits were not self-evident to many corporations. Rather, it has been through ENABLE’s proactive construction of value that disabled people’s previously denied access is now credited as a “tech for good” success story.
This collaboration is afforded by ENABLE’s slow work of trust building with key allies in AITech, and savvy maneuvering of the precarious political economy of disability in China. Initially, many clients were skeptical that blind people could label texts. ENABLE started with two blind annotators testing the tasks, optimizing the workflow, and modifying accessibility. Piecing together resources from governmental and philanthropic actors, such as subsidies for office space and donations for trainings, while drawing on years of experience in running information technology work programs, ENABLE made the data annotation program viable and competitive. After a year of comparing annotators from ENABLE and other non-disabled contractors, it became clear to AITech that ENABLE workers provided higher quality services.
To ENABLE, this is a great advocacy proof for the productivity of disabled persons in China, whose citizenship is often tied to their contribution to economic production (Dauncey, 2020). The tech sector can also be mobilized as an ally to the increasingly under-resourced NGOs in China (Huang, 2022). ENABLE therefore saw the “feel-good” corporate promotions as an opportunity to leverage the charisma and resource of AI to showcase disability value. However, despite supportive internal advocates, some people in AITech were initially unconvinced of the collaboration’s promotional value. They worried that if the world knows that a bunch of disabled folks are building their systems, users will question the quality of their products. AITech’s users are China’s urban, middle-class, young professionals, who call upon smart home technologies to organize their own overworked, fast-paced lives. The presence of disabled workers, it seems, may threaten the image of the frictionless, efficient, and competent virtual service worker who always obediently stays out of sight (Atanasoski and Vora, 2015).
After years of working closely together, AITech has moved from treating ENABLE like a “small experiment” to recognizing their value across the company. At a dinner I joined, workers spoke of a recent visit to AITech campus as a milestone. The pride and joy of finally earning respect and building genuine trust with powerful corporate actors cannot be read merely cynically. AITech’s senior leadership is recommending ENABLE to more teams and even other tech companies, which, to the workers, marks an appreciation of their value, and a success of “counter-eugenics activism” (Garland-Thomson, 2012). While assisting the technology through their labor and expertise, ENABLE and many disabled workers also sought to co-opt resources for community gain through hazardous engagement with techno-capitalism in uneven power terrains.
In sum, thanks to disability expertise, annotating at ENABLE turned out to be a better option for many disabled workers than being a massage therapist, doing digital piecework at home, or being excluded by non-disabled colleagues in mainstream workplaces. ENABLE’s access work (Hickman, 2019) improved many annotators’ work experience and work performance. Being in a vocal community about disabled people’s capabilities also adds a sense of purpose to their labor. Of course, ENABLE’s workers only constitute a small elite of disabled Chinese, and the DPO had to turn down many eager job candidates and select particular kinds of workers to keep the business viable. Nevertheless, these exceptional individuals have the potential to redistribute their gained advantages and renew visions for community betterment (Mauksch, 2021). I strive here to spotlight the pragmatic efforts and creative workarounds that Chinese DPOs make to further their advocacy agenda under an increasingly hostile political environment (Huang, 2019). Prioritizing workers’ experience and enacting collective bargaining, ENABLE’s practices can also offer a model for cooperative ownership and worker-governed “platforms” that digital labor scholars are advocating for (Vallas and Schor, 2020; Posada, 2021).
Conclusion
Contrary to mainstream corporate mythologies of “tech for good,” this research finds disability “good for tech” in profound ways. In this study, disabled data annotators offer a stable and high-quality human resource to the making of smart home AI systems, so that ambiguous human intentions and unruly human speech could be rendered legible to machines in consistent ways. Disabled people’s labor is competitive in this context, not because they are “naturally” more stable than non-disabled workers, but because they are pushed out of the mainstream job market by structural ableism, and pulled into ENABLE’s data annotation workforce by its accommodating labor practices. Reconfiguring space, time, and political economy, ENABLE and the workers’ disability expertise actively transformed the conditions of “ghost work,” and made their work more valuable than other suppliers.
This exceptional case is made possible because it is led by disabled people themselves, as opposed to typical commercial or governmental programs. I highlight a kind of disability expertise that I call “resource hacking,” namely, disability-informed, pragmatic skills that optimize resources in precarious political economies for community betterment. The DPO and disabled workers strategically leveraged the charisma of AI to showcase the productivity of disabled people, a form of counter-eugenics activism (Garland-Thomson, 2012) not without risks of co-optation. In turn, the AI company benefits from the skilled labor, naturalized immobility, and collective expertise of the disabled workers.
Rather than a simple story of extractive capitalism, this article strives to illuminate the potential of disability expertise in renegotiating the terms of techno-capitalism. I draw attention to disabled people’s underexamined role as technicians in information systems, in which disability is often conceived as a problem (Shew, 2020a), a pretext (Mills, 2010), or an afterthought (Nakamura, 2019). An intervention of this article is not only to lay bare the use and abuse of disability as a resource in contemporary AI development, but also to elevate crip technoscience by teasing out the disability expertise actually entailed in the production of AI. I foreground forms of disability value-making that build on genuine expertise, and are thoughtfully constructed with an activist agenda.
As an organization with deep knowledge and lived experience of disability, ENABLE negotiates on behalf of the workers, accommodates heterogenous temporal preferences at work, and builds workspace like a community space, despite scarce resources. They show that labor relations in information technology can be otherwise. Reshaping systems to meet the human, rather than vice versa, workplace disability expertise operationalizes more equitable labor practices in AI.
About the author
Di Wu is a Ph.D. candidate in the History, Anthropology, and Science, Technology, and Society (HASTS) program at MIT. Her research and practice focus on the relationship between disability, labor, and technology in contemporary China.
E-mail: wdi [at] mit [dot] edu
Acknowledgements
I am deeply grateful to my interlocutors who generously shared their stories with me. Many drafts of this article also benefited from the significant input of Gaoshan Fu, Stefan Helmreich, Andrew Hundt, Graham M. Jones, Crystal Lee, Timothy Y. Loh, Darius Longarino, Rui Wang, Ruoqi Zhu, as well as the anonymous reviewers and the editors of this special issue of First Monday. This study is in part supported by the American Ethnological Society, University of Cambridge Mellon Sawyer Seminar on “Histories of AI: A genealogy of power,” Wenner-Gren Foundation Dissertation Fieldwork Grant (Gr. 10357), and National Science Foundation Doctoral Dissertation Research Improvement Grant (BCS-2213722).
All companies, organizations, and individuals involved in this study are given pseudonyms, and personal identities are rearranged to protect anonymity to the extent possible. Although public information exists about the program examined, and the identity of some parties may be recognizable to those familiar with the issue, I strive to minimize representation that could bring economic or political risks to my interlocutors. Sources that contain identifiable information are not cited to protect anonymity. All Chinese to English translations are mine.
Notes
1. Hartblay, 2020, p. S34.
2. Hamraie, 2017, p. xiii.
3. Kafer, 2013, p. 27.
4. Katzman, et al., 2020, p. 521.
References
Moritz Altenried, 2020. “The platform as factory: Crowdwork and the hidden labour behind artificial intelligence,” Capital & Class, volume 44, number 2, pp. 145–158.
doi: https://doi.org/10.1177/0309816819899410, accessed 12 December 2022.
Neda Atanasoski and Kalindi Vora, 2015. “Surrogate humanity: Posthuman networks and the (racialized) obsolescence of labor,” Catalyst: Feminism, Theory, Technoscience, volume 1, number 1, pp. 1–40.
doi: https://doi.org/10.28968/cftt.v1i1.28809, accessed 12 December 2022.
Cynthia L. Bennett, Daniela K. Rosner, and Alex S. Taylor, 2020. “The care work of access,” CHI ’20: Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems, pp. 1–15.
doi: https://doi.org/10.1145/3313831.3376568, accessed 12 December 2022.
Tom Boellstorff, 2019. “The opportunity to contribute: Disability and the digital entrepreneur,” Information, Communication & Society, volume 22, number 4, pp. 474–490.
doi: https://doi.org/10.1080/1369118X.2018.1472796, accessed 12 December 2022.
Geoffrey C. Bowker and Susan Leigh Star, 1999. Sorting things out: Classification and its consequences. Cambridge, Mass.: MIT Press.
doi: https://doi.org/10.7551/mitpress/6352.001.0001, accessed 12 December 2022.
Kai Cheng, 2021. “建立巩固拓展残疾人脱贫攻坚成果长效机制 [Establishing long-term mechanisms to solidify and expand the outcomes of the tough battles of poverty elimination for disabled people],” qstheory.cn, at http://www.qstheory.cn/dukan/hqwg/2021-09/28/c_1127912883.htm, accessed 25 April 2022.
China Disabled Persons’ Federation, 2021. “2020年残疾人事业发展统计公报 [2020 official statistics for the development of disabled people’s affairs],” at http://www.caoss.org.cn/sbnr.asp?id=2238, accessed 25 April 2022.
Chinanews.com, 2019. “中国残疾人就业率稳步提升 [Employment rate of Chinese disabled people is steadily increasing],” at http://www.chinanews.com.cn/sh/2019/08-02/8915152.shtml, accessed 25 April 2022.
Julie Y. Chu, 2010. Cosmologies of credit: Transnational mobility and the politics of destination in China. Durham, N.C.: Duke University Press.
doi: https://doi.org/10.1515/9780822393160, accessed 12 December 2022.
Fengming Cui, Cai Cong, Xu Qiaoxian, and Xiaoming Chang, 2019. “Equal participation of persons with disabilities in the development of disability policy on accessibility in China,” International Journal of Developmental Disabilities, volume 65, number 5, pp. 319–326.
doi: https://doi.org/10.1080/20473869.2019.1664842, accessed 12 December 2022.
Sarah Dauncey, 2020. Disability in contemporary China: Citizenship, identity and culture. Cambridge: Cambridge University Press.
doi: https://doi.org/10.1017/9781316339879, accessed 12 December 2022.
Kerry Dobransky and Eszter Hargittai, 2006. “The disability divide in Internet access and use,” Information, Communication & Society, volume 9, number 3, pp. 313–334.
doi: https://doi.org/10.1080/13691180600751298, accessed 12 December 2022.
Arseli Dokumaci, 2020. “People as affordances: Building disability worlds through care intimacy,” Current Anthropology, volume 61, number S21, pp. S97–S108.
doi: https://doi.org/10.1086/705783, accessed 12 December 2022.
Hamid R. Ekbia and Bonnie A. Nardi, 2017. Heteromation, and other stories of computing and capitalism. Cambridge, Mass.: MIT Press.
Elizabeth Ellcessor, 2016. Restricted access: Media, disability, and the politics of participation. New York: New York University Press.
doi: https://doi.org/10.18574/nyu/9781479813803.001.0001, accessed 12 December 2022.
Carla Freeman, 2000. High tech and high heels in the global economy: Women, work, and pink-collar identities in the Caribbean. Durham, N.C.: Duke University Press.
doi: https://doi.org/10.1215/9780822380290, accessed 12 December 2022.
Michele Friedner, 2015a. “Deaf bodies and corporate bodies: New regimes of value in Bangalores business process outsourcing sector,” Journal of the Royal Anthropological Institute, volume 21, number 2, pp. 313–329.
doi: https://doi.org/10.1111/1467-9655.12208, accessed 12 December 2022.
Michele Friedner, 2015b. Valuing deaf worlds in urban India New Brunswick, N.J.: Rutgers University Press.
Michele Friedner, 2014. “Deaf capital: An exploration of the relationship between stigma and value in deaf multilevel marketing participation in urban India,” Medical Anthropology Quarterly, volume 28, number 4, pp. 502–518.
doi: https://doi.org/10.1111/maq.12115, accessed 12 December 2022.
Rosemarie Garland-Thomson, 2012. “The case for conserving disability,” Journal of Bioethical Inquiry, volume 9, number 3, pp. 339–355.
doi: https://doi.org/10.1007/s11673-012-9380-0, accessed 12 December 2022.
Faye Ginsburg and Rayna Rapp, 2013. “Disability worlds,” Annual Review of Anthropology, volume 42, pp. 53–68.
doi: https://doi.org/10.1146/annurev-anthro-092412-155502, accessed 12 December 2022.
Gerard Goggin and Katie Ellis, 2020. “Disability, communication, and life itself in the COVID-19 pandemic,” Health Sociology Review, volume 29, number 2, pp. 168–176.
doi: https://doi.org/10.1080/14461242.2020.1784020, accessed 12 December 2022.
Gerard Goggin, Haiqing Yu, Karen R. Fisher, and Bingqin Li, 2019. “Disability, technology innovation and social development in China and Australia,” Journal of Asian Public Policy, volume 12, number 1, pp. 34–50.
doi: https://doi.org/10.1080/17516234.2018.1492067, accessed 12 December 2022.
Mary L. Gray and Siddharth Suri, 2019. Ghost work: how to stop Silicon Valley from building a new global underclass, Boston, Mass.: Houghton Mifflin Harcourt.
Aimi Hamraie, 2017. Building access: Universal design and the politics of disability. Minneapolis: University of Minnesota Press.
Aimi Hamraie and Kelly Fritsch, 2019. “Crip technoscience manifesto,” Catalyst: Feminism, Theory, Technoscience, volume 5, number 1, pp. 1–33.
doi: https://doi.org/10.28968/cftt.v5i1.29607, accessed 12 December 2022.
Cassandra Hartblay, 2020. “Disability expertise: Claiming disability anthropology,” Current Anthropology, volume 61, number S21, pp. S26–S36.
doi: https://doi.org/10.1086/705781, accessed 12 December 2022.
Lucia Hasty, n.d. “Teaching tactile graphics,” Perkins School for the Blind eLEARNING, at https://www.perkinselearning.org/videos/webcast/teaching-tactile-graphics, accessed 28 March 2021.
Stefan Helmreich, 2007. “An anthropologist underwater: Immersive soundscapes, submarine cyborgs, and transductive ethnography,” American Ethnologist, volume 34, number 4, pp. 621–641.
doi: https://doi.org/10.1525/ae.2007.34.4.621, accessed 12 December 2022.
Sara Hendren, 2020. What can a body do? How we meet the built world. New York: Riverhead Books.
Louise Hickman, 2019. “Transcription work and the practices of crip technoscience,” Catalyst: Feminism, Theory, Technoscience, volume 5, number 1, pp. 1–10.
doi: https://doi.org/10.28968/cftt.v5i1.32081, accessed 12 December 2022.
Luanjiao Hu, 2022. “Opportunities and challenges: An examination of educational landscape for people with visual impairment in China,” Current Issues in Comparative Education, volume 24, number 1.
doi: https://doi.org/10.52214/cice.v21i1.8844, accessed 12 December 2022.
Luanjiao Hu and Jing Lin, 2017. “Access to higher education for people with disabilities: A Chinese perspective,” In: Henry C. Alphin Jr., Roy Y. Chan, and Jennie Lavine (editors). The future of accessibility in international higher education. Hershey, Pa.: IGI Global, pp. 70–87.
doi: https://doi.org/10.4018/978-1-5225-2560-8.ch005, accessed 12 December 2022.
Jin Huang, Baorong Guo, and John C. Bricout, 2009. “From concentration to dispersion: The shift in policy approach to disability employment in China,” Journal of Disability Policy Studies, volume 20, number 1, pp. 46–54.
doi: https://doi.org/10.1177/1044207308325008, accessed 12 December 2022.
Shixin Huang, 2022. “NGO as sympathy vendor or public advocate? A case study of NGOs’ participation in Internet fundraising campaigns in China,” VOLUNTAS, volume 33, pp. 1,064–1,076.
doi: https://doi.org/10.1007/s11266-022-00463-w, accessed 18 March 2022.
Shixin Huang, 2019. “Ten years of the CRPD’s adoption in China: Challenges and opportunities,” Disability & Society, volume 34, number 6, pp. 1,004–1,009.
doi: https://doi.org/10.1080/09687599.2019.1604384, accessed 12 December 2022.
Sarah S. Jain, 1999. “The prosthetic imagination: Enabling and disabling the prosthesis trope,” Science, Technology, & Human Values, volume 24, number 1, pp. 31–54.
doi: https://doi.org/10.1177/016224399902400103, accessed 12 December 2022.
JD.com, 2018. “央视点赞！人工智能为残疾人就业带来新岗位 [Liked by CCTV! AI brings new jobs for disabled people’s employment],” at https://www.sohu.com/a/226893666_99967243, accessed 2 December 2020.
Alison Kafer, 2021. “After crip, crip afters,” South Atlantic Quarterly, volume 120, number 2, pp. 415–434.
doi: https://doi.org/10.1215/00382876-8916158, accessed 12 December 2022.
Alison Kafer, 2013. Feminist, queer, crip. Bloomington: Indiana University Press.
Erika R. Katzman, Elizabeth Anne Kinsella, and Jessica Polzer, 2020. “‘Everything is down to the minute’: Clock time, crip time and the relational work of self-managing attendant services,” Disability & Society, volume 35, number 4, pp. 517–541.
doi: https://doi.org/10.1080/09687599.2019.1649126, accessed 12 December 2022.
Os Keyes, 2020. “Automating autism: Disability, discourse, and artificial intelligence,” Journal of Sociotechnical Critique, volume 1, number 1, pp. 1–31, at https://digitalcommons.odu.edu/sociotechnicalcritique/vol1/iss1/8, accessed 3 June 2021.
Gary Klein, Jennifer K. Phillips, Erica L. Rall, and Deborah A. Peluso, 2007. “A data-frame theory of sensemaking,” In: Robert R. Hoffman (editor). Expertise out of context: Proceedings of the Sixth International Conference on Naturalistic Decision Making. Mahwah, N.J.: Lawrence Erlbaum Associates, pp. 113–155.
Matthew Kohrman, 2005. Bodies of difference: Experiences of disability and institutional advocacy in the making of modern China. Berkeley: University of California Press.
Tamar Lavee, Lili Kotlerman, Matan Orbach, Yonatan Bilu, Michal Jacovi, Ranit Aharonov, and Noam Slonim, 2019. “Crowd-sourcing annotation of complex NLU tasks: A case study of argumentative content annotation,” Proceedings of the First Workshop on Aggregating and Analysing Crowdsourced Annotations for NLP, pp. 29–38.
doi: https://doi.org/10.18653/v1/D19-5905, accessed 12 December 2022.
Xiaochang Li and Mara Mills, 2019. “Vocal features: From voice identification to speech recognition by machine,” Technology and Culture, volume 60, number S2, pp. S129–S160.
doi: https://doi.org/10.1353/tech.2019.0066, accessed 12 December 2022.
Xue Hui Li, Su Qiong Xu and Luan Jiao Hu, 2022. “Protection or restriction: An analysis of the blind massage policy for employment rights of persons with visual impairments in China,” Journal of Visual Impairment & Blindness, volume 116, number 1, pp. 85–95.
doi: https://doi.org/10.1177/0145482X211073611, accessed 12 December 2022.
Xuehui Li and Zhijun Fu, 2015. “从隔离走向融合? — 我国视力障碍者高等教育的历史特点及政策变迁 [From isolation to integration — The history, features and policy change of people with visual impairment higher education],” Journal of Social Work, number 6, pp. 35–46.
Juan Liao, 2021. “The quota system for employment of people with disabilities in China: Policy, practice, barriers, and ways forward,” Disability & Society, volume 36, number 2, pp. 326–331.
doi: https://doi.org/10.1080/09687599.2020.1833311, accessed 12 December 2022.
Zhongxuan Lin and Liu Yang, 2020. “A digital promised land? Digital landscape as a heterotopia for disabled people in China,” Information, Communication & Society, volume 23, number 8, pp. 1,220–1,234.
doi: https://doi.org/10.1080/1369118X.2020.1776366, accessed 12 December 2022.
Zhongxuan Lin, Zhi’an Zhang, and Liu Yang, 2019. “Self as enterprise: Digital disability practices of entrepreneurship and employment in the wave of ‘Internet + disability’ in China,” Information, Communication & Society, volume 22, number 4, pp. 554–569.
doi: https://doi.org/10.1080/1369118X.2018.1518470, accessed 12 December 2022.
Alan Lundgard, Crystal Lee, and Arvind Satyanarayan, 2019. “Sociotechnical considerations for accessible visualization design,” 2019 IEEE Visualization Conference (VIS), pp. 16–20.
doi: https://doi.org/10.1109/VISUAL.2019.8933762, accessed 12 December 2022.
Caitrin Lynch, 2013. “Membership and mattering: Agency and work in a New England factory,” In: Caitrin Lynch and Jason Danely (editors). Transitions and transformations: Cultural perspectives on aging and the life course. New York: Berghahn Books, pp. 188–205.
doi: https://doi.org/10.1515/9780857457790-015, accessed 12 December 2022.
Stefanie Mauksch, 2021. “Being blind, being exceptional: Work integration, social entrepreneurship and the reimagination of blind potential in Nepal,” Disability & Society (9 July).
doi: https://doi.org/10.1080/09687599.2021.1933387, accessed 12 December 2022.
Milagros Miceli, Martin Schuessler, and Tianling Yang, 2020. “Between subjectivity and imposition: Power dynamics in data annotation for computer vision,” Proceedings of the ACM on Human-Computer Interaction, volume 4, number CSCW2, article number 115, pp. 1–25.
doi: https://doi.org/10.1145/3415186, accessed 12 December 2022.
Mara Mills, 2010. “Deaf jam: From inscription to reproduction to information,” Social Text, volume 28, number 1, pp. 35–58.
doi: https://doi.org/10.1215/01642472-2009-059, accessed 12 December 2022.
Mia Mingus, 2010. “Interdependency (excerpts from several talks),” Leaving Evidence (22 January), at https://leavingevidence.wordpress.com/2010/01/22/interdependency-exerpts-from-several-talks/, accessed 28 March 2021.
David Mitchell and Sharon Snyder, 2010. “Disability as multitude: Re-working non-productive labor power,” Journal of Literary & Cultural Disability Studies, volume 4, number 2, pp. 179–194.
doi: https://doi.org/10.3828/jlcds.2010.14, accessed 12 December 2022.
David Mitchell and Sharon Snyder, 2001. Narrative prosthesis: Disability and the dependencies of discourse. Ann Arbor: University of Michigan Press.
doi: https://doi.org/10.3998/mpub.11523, accessed 12 December 2022.
Karen Nakamura, 2019. “My algorithms have determined youre not human: AI-ML, reverse Turing-tests, and the disability experience,” ASSETS ’19: Proceedings of the 21st International ACM SIGACCESS Conference on Computers and Accessibility, pp. 1–2.
doi: https://doi.org/10.1145/3308561.3353812, accessed 20 October 2021.
Lisa Nakamura, 2014. “Indigenous circuits: Navajo women and the racialization of early electronic manufacture,” American Quarterly, volume 66, number 4, pp. 919–941.
doi: https://doi.org/10.1353/aq.2014.0070, accessed 12 December 2022.
Netease.com, 2018. “人工智能与‘她’‘京东微工’助残疾人逆光飞翔 [AI and ‘her’: Jingdong Microwork helps disabled people fly against the light],” at https://art.163.com/18/0530/14/DJ2H5KV4009998F3.html, accessed 2 December 2020.
Julian Posada, 2021. “Family units: Can the families whose labor powers AI seize the means of production?” Logic, number 15 (Beacons), at https://logicmag.io/beacons/family-units/, accessed 18 March 2022.
Yuanyuan Qu, 2022. “Is the Internet the game changer? Disabled people and digital work in China,” Disability & Society, volume 37, number 5, pp. 725–745.
doi: https://doi.org/10.1080/09687599.2020.1833314, accessed 12 December 2022.
Yuanyuan Qu, 2020. “Understanding the body and disability in Chinese contexts,” Disability & Society, volume 35, number 5, pp. 738–759.
doi: https://doi.org/10.1080/09687599.2019.1649123, accessed 12 December 2022.
Kathleen Richardson, 2015. An anthropology of robots and AI: Annihilation anxiety and machines. New York: Routledge.
doi: https://doi.org/10.4324/9781315736426, accessed 12 December 2022.
Holly Robbins, Taylor Stone, John Bolte, and Jeroen van den Hoven, 2021. “Legibility as a design principle: Surfacing values in sensing technologies,” Science, Technology, & Human Values, volume 46, number 5, pp. 1,104–1,135.
doi: https://doi.org/10.1177/0162243920975488, accessed 12 December 2022.
Sarah T. Roberts, 2019. Behind the screen: Content moderation in the shadows of social media. New Haven, Conn.: Yale University Press.
Ellen Samuels and Elizabeth Freeman, 2021. “Introduction: Crip temporalities,” South Atlantic Quarterly, volume 120, number 2, pp. 245–254.
doi: https://doi.org/10.1215/00382876-8915937, accessed 12 December 2022.
Beth M. Semel, 2022. “Listening like a computer: Attentional tensions and mechanized care in psychiatric digital phenotyping,” Science, Technology, & Human Values, volume 47, number 2, pp. 266–290.
doi: https://doi.org/10.1177/01622439211026371, accessed 12 December 2022.
Ashley Shew, 2020a. “Ableism, Technoableism, and future AI,” IEEE Technology and Society Magazine, volume 39, number 1, pp. 40–85.
doi: https://doi.org/10.1109/MTS.2020.2967492, accessed 12 December 2022.
Ashley Shew, 2020b. “From a figment of your imagination: Disabled marginal cases and underthought experiments,” Human Affairs, volume 30, number 4, pp. 608–616.
doi: https://doi.org/10.1515/humaff-2020-0054, accessed 12 December 2022.
Jonathan Sterne, 2003. The audible past: Cultural origins of sound reproduction. Durham, N.C.: Duke University Press.
doi: https://doi.org/10.1215/9780822384250, accessed 12 December 2022.
Jonathan Sterne and Mara Mills, 2020. “Second rate,” Triple Canopy, at https://www.canopycanopycanopy.com/contents/second-rate, accessed 16 March 2021.
Lucy Suchman, 1993. “Do categories have politics? The language/action perspective reconsidered,” In: Giorgio Michelis, Carla Simone, and Kjeld Schmidt (editors). Proceedings of the Third European Conference on Computer-Supported Cooperative Work 13–17 September 1993, Milan, Italy ECSCW ’93. Dordrecht: Springer Netherlands, pp. 1–14.
doi: https://doi.org/10.1007/978-94-011-2094-4_1, accessed 12 December 2022.
Shan Tie, Rong Guo, and Xi Chen, 2011. “回忆与思考 — 谈中国盲人按摩的发展历程 [Reminiscence and reflection on the development of Chinese blind massage],” Disability in China, number 6, pp. 46–48.
Paola Tubaro, Antonio A Casilli, and Marion Coville, 2020. “The trainer, the verifier, the imitator: Three ways in which human platform workers support artificial intelligence,” Big Data & Society, volume 7, number 1.
doi: https://doi.org/10.1177/2053951720919776, accessed 12 December 2022.
Steven Vallas and Juliet B. Schor, 2020. “What do platforms do? Understanding the gig economy,” Annual Review of Sociology, volume 46, pp. 273–294.
doi: https://doi.org/10.1146/annurev-soc-121919-054857, accessed 12 December 2022.
Di Wu, 2021. “Cripping the history of computing,” IEEE Annals of the History of Computing, volume 43, number 3, pp. 68–72.
doi: https://doi.org/10.1109/MAHC.2021.3101061, accessed 12 December 2022.
Anon Ymous, Katta Spiel, Os Keyes, Rua M. Williams, Judith Good, Eva Hornecker, and Cynthia L. Bennett, 2020. “‘I am just terrified of my future’ — Epistemic violence in disability related technology research,” CHI EA ’20: Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems, pp. 1–16.
doi: https://doi.org/10.1145/3334480.3381828, accessed 12 December 2022.
Haiqing Yu, Gerard Goggin, Karen Fisher, and Bingqin Li, 2019. “Introduction: disability participation in the digital economy,” Information, Communication & Society, volume 22, number 4, pp. 467–473.
doi: https://doi.org/10.1080/1369118X.2018.1550525, accessed 12 December 2022.
Sean Zdenek, 2015. Reading sounds: Closed-captioned media and popular culture. Chicago: University of Chicago Press.
Kathryn Zyskowski, Meredith Ringel Morris, Jeffrey P. Bigham, Mary L. Gray, and Shaun K. Kane, 2015. “Accessible crowdwork? Understanding the value in and challenge of microtask employment for people with disabilities,” CSCW ’15: Proceedings of the 18th ACM Conference on Computer Supported Cooperative Work & Social Computing, pp. 1,682–1,693.
doi: https://doi.org/10.1145/2675133.2675158, accessed 10 March 2021.
Editorial history
Received 16 November 2022; accepted 12 December 2022.
This paper is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Good for tech: Disability expertise and labor in China’s artificial intelligence sector
by Di Wu.
First Monday, Volume 28, Number 1 - 2 January 2023
https://firstmonday.org/ojs/index.php/fm/article/download/12887/10792
doi: https://dx.doi.org/10.5210/fm.v28i1.12887
| 2023-01-01T00:00:00 |
https://firstmonday.org/ojs/index.php/fm/article/download/12887/10792
|
[
{
"date": "2023/01/01",
"position": 86,
"query": "machine learning job market"
},
{
"date": "2023/01/01",
"position": 55,
"query": "AI job creation vs elimination"
}
] |
|
Are physicians and medical students ready for artificial ...
|
Are physicians and medical students ready for artificial intelligence applications in healthcare?
|
https://pmc.ncbi.nlm.nih.gov
|
[
"Adhari Alzaabi",
"Human",
"Clinical Anatomy Department",
"College Of Medicine",
"Health Science",
"Muscat",
"Sultanate Of Oman",
"Saleh Almaskari",
"Abdulrahman Aalabdulsalam",
"College Of Science"
] |
by A AlZaabi · 2023 · Cited by 66 — Instead, the majority (n=159) agreed that new positions will be created and the job market for those who embrace AI will increase. ... Machine learning is thought ...
|
Abstract Background Artificial intelligence (AI) Healthcare applications are listed in the national visions of some Gulf Cooperation Council countries. A successful use of AI depends on the attitude and perception of medical experts of its applications. Objective To evaluate physicians and medical students’ attitude and perception on AI applications in healthcare. Method A web-based survey was disseminated by email to physicians and medical students. Results A total of 293 (82 physicians and 211 medical students) individuals have participated (response rate is 27%). Seven participants (9%) reported knowing nothing about AI, while 208 (69%) were aware that it is an emerging field and would like to learn about it. Concerns about AI impact on physicians’ employability were not prominent. Instead, the majority (n=159) agreed that new positions will be created and the job market for those who embrace AI will increase. They reported willingness to adapt AI in practice if it was incorporated in international guidelines (30.5%), published in respected scientific journals (17.1%), or included in formal training (12.2%). Almost two of the three participants agreed that dedicated courses will help them to implement AI. The most commonly reported problem of AI is its inability to provide opinions in unexpected scenarios. Half of the participants think that both the manufacturer and physicians should be legally liable for medical errors occur due to AI-based decision support tools while more than one-third (36.77%) think that physicians who make the final decision should be legally liable. Senior physicians were found to be less familiar with AI and more concerned about physicians’ legal liability in case of a medical error. Conclusion Physicians and medical students showed positive attitudes and willingness to learn about AI applications in healthcare. Introducing AI learning objectives or short courses in medical curriculum would help to equip physicians with the needed skills for AI-augmented healthcare system. Keywords: Artificial intelligence, perception, attitude, familiarity, physician, medical students
Introduction Artificial intelligence (AI) is “the ability of computer systems to perform tasks that would usually require human levels of intelligence.”1 AI applications recently witnessed substantial growth across many industries including healthcare. Machine learning is thought to transform healthcare systems profoundly in the coming years.2 A plethora applications have been developed that aim to improve different aspects of clinical work such as improving medication compliance,3 reducing waiting time at outpatient clinics,4 providing fast reporting for medical imaging,5 and other reported benefits.2 Machine learning has been reported to outperform physicians in some such as detecting breast cancer in mammogram images.6 It was implemented at higher scale during the COVID-19 pandemic to improve disease diagnosis, trace tracking, and intensive care unit admission prediction.7 Some of these AI-based algorithms have been approved by the American Food and Drug Administration for clinical use.2 Despite the rapid global progress in research and development in innovative medical AI technologies, there are several barriers that hinder its clinical use at a wider scale.8 Resistance to adopt AI among physicians has been reported frequently.9,10 On the other hand, other studies have reported an optimistic view that medical AI technologies will augment physicians’ work and allow them to direct their time toward more cognitive and higher-order skills.11 Future healthcare professionals will directly use software, applications, and machines that are AI powered. To be able to implement such applications with ease, future doctors should be equipped with the needed knowledge and basic skills to understand and deal with such machines and softwares. They should be aware of the advantages and disadvantages of AI-powered medical technologies and acquire the needed skills to work in the upcoming AI medical ecosystem.12 It is even expected that AI will be a main element in the medical curriculum in the future.13 There is no agreement on how much and where AI should be introduced in medical education. Experts agree that medical curriculum should not introduce sophisticated technical tools; instead, an understanding of the topic, its uses, applications, disadvantages, limitations, and data management are the main areas to be highlighted.14 There is a growing movement to include such topics in both undergraduate and postgraduate formal medical curricula. In Oman, the healthcare system at the primary, secondary, and tertiary levels had undergone a digital transformation a long time ago and become fully digitized by the years 2008 to 2009. Since then, all patients’ records are available online through password-encrypted hospital access. The aim was to improve clinical care delivery, and patients’ experience and enhance the care operational efficiencies. With time the amount of digital data available that needs to be studied and mined to improve care necessitates enhancing digital literacy among current and future physicians. Physicians are usually not equipped with digital skills or are even unaware of the benefits of such big data and the applicability of AI techniques in their field. There is an ongoing discussion to introduce an AI-oriented learning objective in the medical curriculum at both the undergraduate and postgraduate levels in Oman. Therefore, the objective of this study is to evaluate and analyze familiarity, attitudes, and perceptions of physicians, trainees, and medical students about medical AI applications. This is a preliminary step to evaluate the baseline knowledge and readiness before introducing AI into the medical curriculum in our institute. To the best of our knowledge, this is the first study that evaluates the perceptions and attitudes of physicians, trainees, and medical students toward medical AI applications in the same setting. Previous studies have analyzed the views of either medical students or physicians in different settings.15–17
Method Study population This study was approved by the ethical committee from Sultan Qaboos University (reference no. 2078). Google Form was used to construct the questionnaire which was disseminated among physicians working at tertiary hospitals, interns, and residents from the Oman Medical Specialty Board, and medical students from the College of Medicine at Sultan Qaboos University through institutional emails. Participation was voluntary and all participants were consented and informed about the goal of the survey in the preface of the questionnaire. The IBM definition of “Artificial Intelligence in Medicine” was introduced in the preface of the survey which stated that: “Artificial intelligence (AI) in medicine is the use of machine learning models to search medical data and uncover insights to help improve health outcomes and patient experiences.” The questionnaire An anonymized survey was adapted and modified with permission from Goh and Sandars13 and Masters.12 The survey is composed of 25 closed-ended questions (Supplemental Appendix A) distributed among 5 sections as follows: demographics section (6 items), familiarity section (2 items), attitude section (14 items), expected application in medicine section (3 items), and possible risks section (1 item). Five of the questions used a 5-point ordinal Likert scale (1=strongly disagree to 5=strongly agree). The remaining 20 questions were constructed as multiple-choice questions. The survey was piloted and the reliability scores of the different sections of the survey were computed and all the sections have been modified accordingly. The calculated Cronbach’s scores for the sections were all >0.78, which indicates good inter-item reliability. Statistical analysis Basic statistics were computed for all covariates where continuous variables are expressed as mean, standard deviation, median, minimum, and maximum values, and categorical variables as frequency (n) and percentages (%). Pearson analysis was done to evaluate the effect of different demographic factors such as age, gender, and years of experience, on the participants’ responses to different items. For all tests, the level of significance was set at a p-value of ≤ 0.05.
Results Respondent demographics The survey was disseminated to 300 physicians and trainees and 750 registered medical students. A total of 293 (82 physicians and 211 medical students) have responded to the survey with a response rate of 27% and 28%, respectively. The sociodemographic and professional characteristics of the participants are shown in Table 1. Table 1. Demographic and professional descriptions of survey participants. Participants Medical role Medical student Physician Category n (%) Category n (%) Age ≤25 years 179 (84.83) <30 years 29 (35.37) 31–50 years 43 (52.44) >25 years 32 (15.16) >50 years 10 (12.19%) Gender Male 86 (40.8) Male 30 (36.6) Female 125 (59.2) Female 52 (63.4) Years of experience Junior in preclinical 61 (28.91) <5 years 32 (39.02) Senior in preclinical 103 (48.82) 5–10 years 15 (18.29) Clinical 38 (18.01) 11–20 years 22 (26.83) Pre-intern 9 (4.26) >20 years 13 (15.86) Specialty (for physicians) Specialty n (%) Specialty n (%) Child health 15 (18.3) Anesthesia 2 (2.44) Family medicine 10 (12.2) Critical care 2 (2.44) General medicine 10 (12.2) Emergency medicine 2 (2.44) Obstetrics and gynecology 9 (10.98) Histopathology 2 (2.44) Psychiatry 7 (8.5) Neurology 2 (2.44) General surgery 4 (4.88) Physician scientist 4 (4.88) Clinical biochemistry 3 (3.66) ENT 3 (3.66) Dermatology 3 (3.66) Orthopedic surgery 3 (3.66) Ophthalmology 1 (1.22) Open in a new tab About 177 (60.4%) of the total participants were females. Almost half (57.31%) of the physicians reported 10 or fewer years of medical practice and the other half has practiced for more than 10 years. The participating students were mainly from preclinical years (77.73%). Familiarity Both physicians and medical students reported being familiar that AI as a new and emerging tool in medicine (21%, and 48%, respectively) and they would like to learn more about its applications in medicine (16% and 33%, respectively; Table 2). More than half (165, 56%) of all participants have not attended a talk or read papers that focus on using AI to make interpretations, diagnostic or prognostic within the past 1 year. Only 7 (8.5%) physicians reported reading or attending 5 or more articles/talks about AI in the last year. The remaining participants reported reading or attending less than five articles/talks. Age and year of experience of the participants were found to be statically negatively associated with familiarity with AI applications in healthcare. The older physicians with more years of experience were found to be less familiar with AI and its application in medicine (p-value <0.05; Table 3). There was no association between gender and familiarity level (p-value >0.5). Table 2. Familiarity of the participants with AI applications in healthcare. Familiarity Physician Medical students Item Question n % n % How familiar are you with AI applications in healthcare? I have never heard of AI before 7 9 0 0 I have heard of AI before but didn't realize it has applications to my specialty 15 18 7 3 I know of research applications of AI in my specialty but I don't think it will reach clinical practice 21 26 33 16 I understand that AI is a new and emerging tool in my specialty 17 21 101 48 I would like to learn more about how I can start experimenting with AI in a specialty 13 16 69 33 I have experimented with programs that use AI to carry out specific tasks in my specialty 4 5 1 0 I routinely use AI in my clinical practice to carry out specific tasks 3 4 0 0 I carry out AI research in my specialty 2 2 0 0 Approximately how many talks/papers have you attended/read that focus on using AI to make interpretations, diagnostic, or prognostic within the last year conclusions in your field? None 44 54 146 69 Less than 5 31 38 61 29 More than 5 7 9 4 2 Open in a new tab Table 3. The association of different sections with the participants’ demographics. Variable Familiarity Attitude Expected application in medicine Risk r-value p-value r-value p-value r-value p-value r-value p-value Age −0.19 0.00 0.04 0.50 0.03 0.55 −0.15 0.01 Gender 0.09 0.13 −0.07 0.27 −0.05 0.37 −0.02 0.76 Years of experience −0.19 0.00 0.05 0.38 −0.04 0.55 −0.15 0.01 Open in a new tab Analysis of the five Likert scale questions from different subscales is shown in Table 4. The most perceived concerns regarding AI application in medicine are that it “Cannot be used to provide opinions in unexpected situations” and is “Difficult to apply to controversial issues.” The most perceived advantage was the AI's ability to “Speed up the management process in health care” and “can deliver clinically relevant and high-quality data in real-time.” The majority of the participant reported being neither agree nor disagree with the questions related to the item about AI replacing medical doctors. Almost half of the participants (n=159) reported that “AI will create new positions and increase the job market for those who embrace it.” Overall, the concerns about physicians’ replacement and the impact on physicians’ employability were not prominent. Almost 35% (n=105) of participants reported that “fewer doctors will be trained in some profession” and 20% (n=60) think that “currently trained doctors in some medical profession will lose their positions.” Most of the participants neither agree nor disagree that the integration of AI in their profession will affect efficiency. More than half of the participants agree that with the appropriate training, AI could increase the efficiency of their practice. When asked about their readiness—from a training perspective—to implement AI in their work, 82% (n=249) of the participants agreed that with dedicated courses and workshops, they can start implementing AI in their practice. Table 4. Analysis of Likert scale of the survey sections. Section Item Choices Mean Strongly disagree Disagree Neither agree nor disagree Agree Strongly agree SD AI application Which problems are you concerned about, regarding the application of AI in medicine? Cannot be used to provide opinions in an unexpected situation 3.6 0 18 97 139 39 0.82 Not flexible enough to be applied to every patient 3.5 0 18 100 136 39 0.74 Difficult to apply to controversial issues 3.8 0 4 111 139 39 0.70 Does not consider the emotional wellbeing of patients 3.8 0 7 125 104 57 0.80 Developed by a specialist with little clinical experience 3.1 4 11 193 75 11 0.64 What do you think are the advantages of using AI in healthcare? AI can speed up the management process in healthcare 4.0 1 2 62 205 23 0.67 AI can help in reducing the number of medical errors 3.8 0 9 114 161 9 0.65 AI can deliver clinically relevant and high-quality data in real-time 4.0 1 2 85 184 21 0.75 AI has no space-time constraint 3.0 1 2 149 126 15 0.78 AI has no emotional exhaustion or physical limitation 3.4 3 12 126 129 23 0.62 Attitude Are you concerned that AI will eventually replace some clinical specialists? Currently trained doctors in some medical professions will lose their positions 3.0 7 42 184 60 0 0.63 Fewer doctors will be trained in some profession 3.3 7 11 170 105 0 0.72 AI will not affect the physician job market 3.2 7 36 166 77 7 0.72 AI will create new positions and increase the job market for those who embrace it 3.5 14 7 113 155 4 0.79 AI will lead to a massive increase in hired physicians 3.1 11 36 210 37 0 0.62 How do you think the integration of AI in your profession will affect your efficiency? AI will decrease the efficiency of my practice 3.0 0 50 200 36 7 0.72 AI will increase the efficiency of my practice 3.5 4 14 173 84 18 0.54 With the appropriate training, AI could increase the efficiency of my practice 3.7 4 0 111 143 36 0.56 I am unsure 2.9 11 43 172 57 11 0.59 If AI is proven to be a valuable and safe decision support tool in your field, will you feel comfortable (from a training perspective) using AI tools in your practice? I don't use computers beyond basic use 2.7 7 64 200 18 4 0.59 I lack knowledge about AI and can’t learn it right now 2.9 11 64 175 39 4 0.61 I can learn it with a dedicated course and workshop 4.0 0 0 44 210 39 0.72 Open in a new tab Attitude Overall, participants expressed a positive attitude toward AI applications in healthcare. They reported willingness to adapt AI tools in clinical practice if it was incorporated in the international guideline (30.5%), published in highly respected scientific journals (17.1%), included in formal training (12.2%) or if adopted by leaders in their filed (8.5%; Figure 1). Twenty percent of the participants reported actively seeking new technologies and 11% are ready to adapt new technologies regardless of where they are published. Figure 1. Open in a new tab Willingness to incorporate new technological advances in clinical practice among the participants. All 69 (23.55%) participants showed interest to learn more about AI if dedicated courses and training are offered. Two-third (78%) of the participants expressed their willingness to adopt an AI-based decision support tool in their practice if it could help to devote more time to other clinical, academic, and/or research activities. The vast majority of participants (55% physicians and 62.5% students) strongly believe that AI use in image analysis in radiology, pathology, and dermatology will be cost-effective. The remaining participants think it will not be cost-effective or don’t know if it will be cost-effective which could be due to a lack of understanding and knowledge about AI and its use. Nearly half of the participants reported that image-based specialties such as pathology, dermatology, and radiology will be the first to adopt AI tools followed by surgical procedures and public primary care (Figure 2). Overall, many respondents predicted the integration of AI into diagnostic workflow within the next 5 years (28%) or 10 years (31.7%). The remaining (39%) predicted that it will need more than 15 years for such implementation (Figure 3). Furthermore, participants believed that AI tools application in healthcare would improve the quality of care (51.2%), research productivity (78%), and improve teaching responsibilities (45%). Figure 2. Open in a new tab Healthcare sectors to adopt artificial intelligence at a higher scale. Figure 3. Open in a new tab Respondent perception of the period needed for artificial intelligence to be a major routine tool in medical practice. When asked about how their colleagues and patients would perceive AI tools if applied in clinical practice, most of the participants (84%) agreed that they would perceive AI tools very well if they are offered proper education and awareness. The attitude of the participants was not found to be statistically associated with age, gender, or year of experience (p-value >0.5; Table 3). Risk Among all participants, more than one-third (36.77%) think that the physicians who make the final decision should be legally liable for any medical error occurred when a physician uses an AI-based decision support tool while (6.19%) think it is the manufacturer of the AI tool who should be liable and (48.45%) believed that both the manufacturer of the AI technology and the physician are legally liable (Figure 4). Figure 4. Open in a new tab Who should be held legally liable for medical errors caused by artificial intelligence-based medical software? The majority (63.5%) of the participants reported that they will follow the physician's opinion in case of conflict between an AI tool and the treating physician’s decision, 24.2% will go by patient's choice, 6.49% will consult a colleague, and 17% will follow AI opinion. This was significantly and negatively associated with the age and year of experience of the participants (p-value <0.05; Table 4). Older age physicians and those with more years of experience reported that the physicians who took the decision are to be legally liable for any medical errors resulting from the AI-based decision support tool. On the other hand, younger physicians with fewer years of experience and medical students reported that both the manufacturer and the physician should be legally liable for such medical errors.
Discussion The current healthcare systems in the Arab countries in general and the Gulf Cooperation Council (GCC) specifically is complex due to the challenge to reach an equilibrium between the quality and cost of care, technology, and maintaining humanity.18,19 Some GCC states have AI in healthcare applications as a core objective of the country's national vision.20,21 These strategies put AI at the core of the corresponding country’s development and growth. The successful use of AI in healthcare depends on the awareness and perception of medical experts of its applications.22 To the best of our knowledge, this is one of the few studies in the GCC countries23 to evaluate the opinions and attitudes of physicians and medical students on AI medical applications. Overall, we found that both physicians and medical students across all specialties and years of experience have a positive perspective about the future use of AI in healthcare which is similar to the previously reported attitude.11,24 There is a generally low familiarity with AI, especially among older and senior physicians. However, the majority have reported eagerness to learn and apply AI tools if dedicated courses and workshops are offered and if included in international guidelines and formal training.25–27 AI replacing physicians was not a concern of physicians and medical students in Oman which is consistent with findings from other studies10,28–30 but not consistent with a recent study from Saudi Arabia.23 Some participants did report a fear that some medical professions might be largely impacted and the training in these professions will be modified to adapt to working with machines especially image-based and laboratory-based specialties. This fear was mainly reported by young physicians and medical students. According to Bodenheimer,31 only 27% of physicians’ time is spent on direct clinical face-to-face duties with their patients and about 49.2% of their time is spent on electronic hospital records and desk work. In this study, 78% of participants expressed their willingness to adopt AI tools if they can direct their time toward more focused clinical-oriented tasks. The major advantage of AI as perceived by all participants in this study is AI can speed up the process of healthcare followed by providing high-quality care in real-time and reduce medical errors which are similar to perceived advantages in earlier studies.10,11,23,25–27 On the other hand, there are major concerns reported for AI in healthcare such as its inability to provide an opinion in an unexpected situation, lack of empathy, and concerns about the feasibility of AI use in controversial issues are similar to what was reported earlier.10,24 Senior physicians reported that it is both the manufacturer and the physicians who implemented the AI decision support tool to be held legally liable for any resulting medical errors. This was explained earlier as one of the causes for physicians’ resistance to the innovative technology in healthcare32 since they evaluate such technologies by their abilities to provide secure and reliable care. Generally, it is both the physician's and patient's acceptance of the new technologies that determine the successful implementation. Reports showed that patients are more excited about innovative technologies in healthcare than physicians because it gives them greater autonomy in their healthcare plans.33 The reported resistance especially among senior physicians could be explained by the lack of awareness and competencies. In a systematic review to study the major barriers to successful digital health applications in developing countries in general and Arab countries specifically, a lack of technical competencies and knowledge among healthcare workers was reported as one of the main barriers.34 Furthermore, the professional identity of physicians was claimed to be a barrier to innovative technologies implementation in the GCC countries.35 Despite all of these reported barriers, physicians who participated in this study showed an overall willingness to learn about AI applications and are ready to implement them once introduced in clinical guidelines. Therefore, to improve knowledge and acceptance, efforts should be directed toward constructing learning sessions and a medical curriculum that exposes healthcare workers and medical students to AI and its applications to prepare future doctors to work along with AI machines and software. This was clearly stated in the 2018 American Medical Association report that proposed the use of the term “augmented intelligence” instead of AI as the physician job is far from full automation.36 AI will augment and facilitate the job of physicians where the future healthcare system will be a teamwork between physicians and machines instead of a competitive environment.37–39 This would be of great impact in places with expert shortages and high-demand institutes, especially in image-based specialties. It was very obvious during the COVID-19 pandemic, that AI has been very powerful to speed up the vaccine and drug discovery process instead of the usual laborious, costly, and time-consuming clinical trials and laboratory studies.7 It is not meant to provide a final diagnosis but is found to assist human physicians in detecting suspicious images and filtering them from normal ones. This would be very helpful to devote physicians’ time to evaluating suspicious cases deeply.
Conclusion The united triple aim of healthcare has been largely impacted by the increased incidence of different chronic and acute illnesses that needs prolonged management plans and the availability of huge medical data. Therefore, technological solutions have proven their abilities to handle such big data and offer smart and fast solutions. According to a Forbes report in 2019, AI applications in healthcare would serve the triple aim of healthcare as it will cut the cost of care, improve accessibility, and improve treatment. Physicians and medical students are showing curiosity and a positive attitude toward future applications of AI in healthcare. It is well known that healthcare providers have typical resistance to change unless the change has been tried and tested thoroughly. Therefore, there is an unmet need to include AI in healthcare training, and construct dedicated courses/workshops for physicians and medical students. There is a need as well for a regulatory and multidimensional framework that lists the detailed responsibilities of stakeholders, legislations, and logistics for future AI applications. Limitations The relatively small size of physician participants is one of the limitations of our study which impacted the possibility of detecting statistical significance between different professions. Furthermore, since the survey was disseminated online, selection bias could impact the results as physicians and students who are interested in AI are more likely to participate and provide a positive perception.
Supplemental Material sj-docx-1-dhj-10.1177_20552076231152167 - Supplemental material for Are physicians and medical students ready for artificial intelligence applications in healthcare? Supplemental material, sj-docx-1-dhj-10.1177_20552076231152167 for Are physicians and medical students ready for artificial intelligence applications in healthcare? by Adhari AlZaabi, Saleh AlMaskari and Abdulrahman AalAbdulsalam in Digital Health
Acknowledgment The authors would like to acknowledge Dr Abdullah AlMunairi and the administration of the College of Medicine and Health Science and Oman Medical Specialty Board for the logistics support and the administrative work that helped to run this project. https://www.ibm.com/topics/artificial-intelligence-medicine
Footnotes Author contributions: The study conception and design were by AALZ. All authors contributed to the manuscript write-up. The compilation of all sections and the construction of headings and figures were done by AALZ and AAA. The first draft of the manuscript was written by all authors. The manuscript was proofread by AAA and SA. All authors read and approved the final manuscript. The authors declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article. Ethical approval: The project has been approved by the Ethical committee of the College of Medicine and health sciences. Funding: The authors received no financial support for the research, authorship, and/or publication of this article. Guarantor: AA. ORCID iD: Adhari AlZaabi https://orcid.org/0000-0003-4290-1272 Supplemental material: Supplemental material for this article is available online.
| 2023-01-26T00:00:00 |
2023/01/26
|
https://pmc.ncbi.nlm.nih.gov/articles/PMC9903019/
|
[
{
"date": "2023/01/01",
"position": 90,
"query": "machine learning job market"
}
] |
The Rise of AI: A Job Creator or a Job Killer ( Part 1/3)
|
The Rise of AI: A Job Creator or a Job Killer ( Part 1/3)
|
https://chrisamansood.medium.com
|
[
"Chrisaman Sood"
] |
... machine learning, and software development. As companies and organizations ... job market. It's important to remember that AI is a tool, not a ...
|
The Rise of AI: A Job Creator or a Job Killer ( Part 1/3) Chrisaman Sood 3 min read · Feb 1, 2023 -- Listen Share
It was 1998, I participated in the Interschool debate. The topic of the debate was “ Will computers cause unemployment “. I was supposed to speak on the topic in favor of the topic, but at the last moment, I spoke against it. Not because I suddenly started believing that computers would not cause job loss, but the reason was somewhat different. A very beautiful girl from a different school spoke in favor of computers and I found the girl cute, so was just trying to impress her.
2023 — it's like Deja Vu ( without that girl though ..). Let's talk about a topic that has been on everyone’s mind lately: chat GTP and the impact of artificial intelligence (AI) on jobs or simply the future of work with AI. A lot of us are getting worried that AI will replace humans and take their jobs, .. or could it be that AI will more jobs and not just replace humans? Let's explore
Before we dive into the details, let’s talk about what AI and ML (most abused terms :)) are and how they are related like cousins but different. AI refers to the development of computer systems that can perform tasks that typically require a certain set of human intelligence, such as visual perception, speech recognition, decision-making, and language translation. These systems are powered by machine learning algorithms that enable them to learn and improve over time.
Now, back to the topic at hand — the future of work with AI. The fear of AI taking over human jobs is not new. We’ve heard this before with the advent of automation and robots in the industrial revolution or with the rise of computers. But what we saw then, and what we’ll see with AI, is that while some jobs may be replaced and will be replaced, new jobs will be created.
The future of work with AI is a positive one. AI will create jobs by increasing efficiency and productivity. By automating repetitive tasks, companies and individuals will be able to focus on more strategic and creative initiatives, leading to the creation of new roles and responsibilities. For example, as AI takes over routine data analysis, human employees will have more time to focus on higher-level decision-making and problem-solving.
AI’s role in job creation — Another way AI will create jobs is by enabling new industries and markets. As AI continues to evolve, it will open up new opportunities in areas such as healthcare, finance, and retail. These industries will require new skills and expertise, leading to the creation of new jobs.
But what about the job loss that comes with AI implementation? While it’s true that some jobs will be lost, the benefits of AI far outweigh the costs. AI will help companies become more competitive, resulting in more investment, growth, and job creation. In addition, the increased efficiency and productivity brought about by AI will lead to lower prices, making it easier for people to start their own businesses and create new jobs.
On the tech side, AI’s role in job creation would be in the fields such as data science, machine learning, and software development. As companies and organizations adopt AI, they’ll need professionals who understand how to build and maintain these systems. This will create a huge demand for human brains in these fields and this is how AI will be transforming the job market
It’s important to remember that AI is a tool, not a replacement for human workers. AI can assist and augment human workers, making their jobs easier and more efficient. But AI will never be able to fully replace human intelligence and creativity. Jobs that require human empathy, emotional intelligence, and critical thinking will always be safe from automation.
In fact, if you have seen the controversial documentary “ZEITGEIST: THE MOVIE“, its third part explains human minds are not meant to do monotonous tasks but to explore creativity, and that's what AI will help us humans do.
In the next blog, I explore in more detail which areas AI should replace humans and which areas AI can never replace humanity ..
Here is the link to the Blog Jobs where AI will replace humans
Feel free to share your thoughts.
| 2023-05-04T00:00:00 |
2023/05/04
|
https://chrisamansood.medium.com/the-rise-of-ai-a-job-creator-or-a-job-killer-f28bb1822911
|
[
{
"date": "2023/01/01",
"position": 96,
"query": "machine learning job market"
},
{
"date": "2023/01/01",
"position": 35,
"query": "future of work AI"
},
{
"date": "2023/01/01",
"position": 27,
"query": "generative AI jobs"
}
] |
Artificial Intelligence Ai will NOT Eat Your JOB - 5 Reasons ...
|
AI will NOT Eat Your JOB - 5 Reasons Why Artificial Intelligence Will Create, Not Eliminate Jobs
|
https://www.linkedin.com
|
[
"Spruce Infotech Inc.",
"Supply Chain Management Review Magazine",
"Sanjay Kumar Mba Ms Phd Pmp"
] |
While AI may automate certain tasks and make some jobs obsolete, it is also creating new job opportunities in fields such as healthcare and finance.
|
Artificial Intelligence Ai will NOT Eat Your JOB - 5 Reasons Why Artificial Intelligence Will Create, Not Eliminate Jobs
Artificial intelligence (AI) is a rapidly growing field that has the potential to revolutionize many industries. However, there is a common fear that AI will lead to job loss and unemployment. While it is true that AI can automate certain tasks and make some jobs obsolete, it is important to recognize that AI can also create new jobs and opportunities.
One example of how AI is creating new jobs is in the field of healthcare. AI is being used to analyze medical images and assist with diagnoses, freeing up doctors and radiologists to focus on more complex cases.
This not only improves the efficiency of the healthcare system, but it also creates new job opportunities for AI engineers and data scientists. Another example is in the field of finance. AI is being used to process large amounts of financial data and assist with risk management and fraud detection. This not only improves the accuracy and efficiency of financial institutions, but it also creates new job opportunities for financial analysts and data scientists.
It's also important to note that the jobs that are most likely to be affected by AI are those that involve repetitive tasks, such as data entry or customer service. However, these jobs may not be the most desirable ones, and AI automation could free up employees to pursue more fulfilling and higher-paying opportunities.
In summary we can say, while AI may automate certain tasks and make some jobs obsolete, it is also creating new job opportunities in fields such as healthcare and finance. Rather than viewing AI as a threat to employment, it is important to recognize the potential it has to improve industries and create new job opportunities.
5 Reasons Why Artificial Intelligence Will Create, Not Eliminate Jobs :
A. Increased productivity and efficiency leading to economic growth: AI can lead to increased productivity and efficiency in various industries, which can ultimately lead to economic growth and job creation.
B. Assisting with dangerous or complex tasks: AI can assist with tasks that are dangerous or too complex for humans, such as in manufacturing or construction, thereby increasing safety and enabling humans to focus on more skilled tasks.
C. Augmenting human capabilities: AI can augment human capabilities, allowing employees to make better decisions and work more effectively. This can lead to increased job satisfaction and better performance.
D. Creating new job opportunities: As AI technology advances, it will create new job opportunities in fields such as data science, machine learning, and AI engineering.
| 2023-01-01T00:00:00 |
https://www.linkedin.com/pulse/ai-eat-your-job-5-reasons-why-artificial-create-jobs-bhardwaj
|
[
{
"date": "2023/01/01",
"position": 5,
"query": "AI job creation vs elimination"
}
] |
|
The Impact of AI on the Job Market: How to Stay Relevant ...
|
The Impact of AI on the Job Market: How to Stay Relevant in the Age of Automation
|
https://www.linkedin.com
|
[
"Matt Staney",
"Danish Hameed",
"Chitiz A.",
"Adad-Nirari Khochaba",
"Lecturer",
"Business Psychologist",
"Nadereh Roshanzamir. M",
"Quality Assurance",
"Quality Control Manager Operations Administrator Marine Science Seafood"
] |
The beauty of it, however, is that eliminating inefficient processes and improving living standards creates new opportunities, which in turn create new jobs.
|
Data Entry and Data Processing Jobs: AI-powered tools and software are able to process large amounts of data at a faster rate and with a higher degree of accuracy than humans. This means that jobs that involve data entry, data processing, and data analysis may be automated in the future. Repetitive Manufacturing and Assembly Line Jobs: AI-powered robots and automation systems are already being used in manufacturing and assembly line jobs. These systems can perform repetitive tasks with a high degree of accuracy, which means that jobs that involve repetitive manual labor may be replaced by AI. Customer Service and Support Jobs: AI-powered chatbots and virtual assistants are able to handle basic customer service and support inquiries, which means that jobs that involve answering frequently asked questions or troubleshooting common issues may be automated in the future. Telemarketing and Tele Sales Jobs: AI-powered tools and software are able to make sales calls and pitch products to potential customers, which means that jobs that involve telemarketing or telesales may be automated in the future. Financial Analysis and Investment Management Jobs: AI-powered tools and software are able to analyze financial data and make predictions about the stock market, which means that jobs that involve financial analysis or investment management may be automated in the future. Legal Research and Document Review Jobs: AI-powered tools and software are able to review and analyze legal documents, which means that jobs that involve legal research or document review may be automated in the future. Transportation Jobs: AI-powered self-driving cars and trucks are being developed and tested, which means that jobs that involve driving, such as truck and taxi driving, may be automated in the future. Journalism and Content Creation Jobs: AI-powered tools and software are able to write news articles and generate content, which means that jobs that involve journalism or content creation may be automated in the future. Security and Surveillance Jobs: AI-powered tools and software are able to analyze surveillance footage and identify potential security threats, which means that jobs that involve security or surveillance may be automated in the future.
| 2023-01-01T00:00:00 |
https://www.linkedin.com/pulse/impact-ai-job-market-how-stay-relevant-age-automation-jack-jendo
|
[
{
"date": "2023/01/01",
"position": 21,
"query": "AI job creation vs elimination"
}
] |
|
A pragmatic perspective on AI transparency at workplace
|
A pragmatic perspective on AI transparency at workplace
|
https://link.springer.com
|
[
"Al-Sulaiti",
"Galsulaiti Hbku.Edu.Qa",
"Qatar Computing Research Institute",
"Hamad Bin Khalifa University",
"Doha",
"Sadeghi",
"Mohammad Amin",
"Chauhan",
"Lucas",
"Chawla"
] |
by G Al-Sulaiti · 2024 · Cited by 8 — In this study, we examine transparency in AI-augmented settings, such as in workplaces, and perform a novel analysis of the different jobs and tasks that can be ...
|
The notion of transparency is multifaceted, and its theoretical conceptualization has been expanding, especially in the last ten years. This idea has been discussed in many disciplines, including computer science, social sciences, law, public policy, and medicine [26]. In fields related to AI, machine learning, and data science, transparency has become an important issue, as AI systems are becoming more complex, and their characteristics, processes, and outcomes have become more difficult to unpack and understand [14]. Scholars refer to this as the issue of the black box, in which algorithmic models become opaque either by intention or due to the increasing complexity of the models, causing the process that occurs before an input becomes an output to be opaque and difficult to understand [7, 17, 24]. The main objective of efforts to promote transparency in the field of AI has become to resolve the issue of the black box and to enable an understanding of how and why an AI system derives a decision or an output [19]. By resolving this issue, organizations and individuals using AI systems can be held accountable for their decisions, and users affected by AI-assisted decisions can contest the outcomes created by these systems [1, 28]. In this section, we review the different meanings of transparency, articulate its benefits and limitations, and provide an overview of the notion of AI errors and their impact on transparency.
2.1 Definition of transparency
A survey of the literature indicated that ambiguity exists regarding what transparency means. It is frequently used interchangeably with other terms, such as explainability, interpretability, visibility, accessibility, and openness [18]. Moreover, scholarly works have assigned different forms and typologies to AI transparency [2]. For example, Walmsley [35] distinguished between functional and outward transparency. Functional transparency is associated with the inner elements of the AI system, and outward transparency is related to external elements that are not part of the system, such as developers and users. Similarly, Preece et al. [29] tied transparency to explainability and distinguished between the transparency-based explanation, which is concerned with understanding the inner workings of the model, and the post hoc explanation, which is concerned with explaining a machine’s decision without unpacking the model’s inner workings. Similar to the work by Preece et al. [29], Zhang et al. [39] also tied transparency to explainability and distinguished between the local explanation, which refers to the explanation of the logic behind a single outcome, and the global explanation, which refers to the explanation of how the entire algorithmic model works. Felzmann et al. [19] classified transparency as prospective and retrospective. Prospective transparency deals with unveiling information about the working of the system before the user starts interacting with it, whereas retrospective transparency refers to the ability to backtrace a machine’s decision or outcome and provide post hoc explanations of how and why a decision or an outcome was derived.
In this paper, we adopt the definition of transparency provided by the High-Level Expert Group on Artificial Intelligence (AI HLEG) and view transparency as achieving three elements: traceability, explainability, and communication [1]. Traceability refers to the enabling of the retrospective examination of a system by keeping a log of the system’s development and implementation, including information about the data and processes implemented by the system to produce an output (e.g., a decision). Explainability refers to the ability to explain the technical process and the rationale for the AI system’s output. Communication refers to the communication of information about the AI system to the user, including information about the system’s accuracy and limitations so that the user is aware of what they are interacting with [1].
To achieve transparency, system owners might disclose information about data training and analysis, release source code, and provide output explanations [5]. Scholars have argued that achieving transparency requires viewing AI systems as sociotechnical artifacts, meaning that they cannot be separated from the context in which they are developed and deployed, and they cannot be isolated from cultures, values, and norms [16]. Moreover, AI systems are governed by different stakeholders, each requiring different levels of transparency to satisfy their needs. For example, Weller [38] identified developers, users, society, experts/regulators, and deployers as distinct stakeholders with different transparency requirements. A developer might require transparency to verify whether the system is working as intended, eliminate errors, and enhance the system, while users require transparency to ensure that the outcome of the AI system is not flawed or biased and to increase trust in future outcomes [19]. Since different stakeholders have different needs, releasing the source code, for example, might meet the transparency requirements of developers but not users, as they might not understand what the code does.
2.2 The benefits and limitations of transparency
Enhancing the transparency of AI systems could lead to several benefits. The first and one of the most assumed is an increase in users’ trust [12]. Schmidt et al. [32] indicated that the general perception in the literature is that transparency increases trust in AI systems and that system owners can enhance such trust by providing users with simple and easy-to-understand explanations of the system’s output [27, 40]. In the context of AI systems, trust is more important than in other traditional engineering systems because AI systems are based on induction, meaning that they make generalizations by learning from specific instances rather than applying general concepts or laws to specific applications. The second benefit of transparency is ensuring that AI systems that directly impact people do not engage in discrimination to achieve fairness [36]. The third benefit of transparency is the enabling of accountability by reducing information asymmetry, thus allowing organizations and individuals to be held accountable for their decisions [18, 20, 28].
Despite the purported benefits of transparency, several studies have indicated that these benefits might be limited, and in some cases, transparency might have negative consequences [2, 13, 38]. De Laat [13] listed four different areas where transparency might lead to limited benefits and negative consequences. The first is the tension between transparency and privacy. Releasing datasets publicly might violate the privacy of the individuals included in the dataset. Existing research suggests that individuals can be reidentified in many publicly available anonymized datasets (see [31]). The second area is the possible manipulation of an AI system. If information about the inner workings of a system, such as a source code, is released, the system can be manipulated to either prevent it from working as intended or to produce a favorable outcome for the manipulator. For example, knowing that an autonomous vehicle will force a stop if a moving object appears less than 1.5 m from the car, a person can use this information to make an autonomous car permanently idle and prevent it from moving [16]. The third area is related to protecting the property rights of firms that own AI systems. Requiring firms to publish the source code of their AI systems might infringe upon their property rights, affect their competitive stances, and disincentivize them from innovating [12, 33]. The fourth area deals with “inherent opacity,” in which the information disclosed about an AI system might not necessarily be interpretable and understandable, thus failing to achieve the objective of transparency [13].
Ananny and Crawford [2] identified additional issues and limitations related to transparency. First, transparency can be intentionally used to mislead or conceal. Firms might purposefully disclose huge amounts of information and data when adhering to regulations, making it costly and time-consuming to understand and process these data, thus limiting the usefulness of transparency. Second, the correlation between transparency and trust has yielded mixed outcomes in different studies. For example, in their study on recommender systems in the field of cultural heritage, Cramer et al. [9] found no positive correlation between transparency and trust. In the field of public policy, De Fine Licht [11] and Grimmelikhuijsen [22] also found no strong evidence that increasing transparency increases trust. Therefore, whether users consider predictions and recommendations from machines or humans to be more trustworthy is also inconclusive. In their study, Dietvirst, Simmons, and Massey [15] found that people are averse to algorithmic predictions and recommendations and prefer recommendations from humans, even if they could observe that the algorithms outperformed humans. They also found that people lose confidence in algorithms more quickly than humans when witnessing mistakes. Contrary to these findings, Logg, Minson, and Moore [27] found that people actually appreciate predications and recommendations coming from algorithms more than from humans, even when they do not understand how the algorithms make the recommendations [35]. Given the aforementioned issues and limitations of transparency, many scholars argue that achieving full transparency is undesirable, if not impossible [12, 13, 24, 30].
In summary, there is no agreed-upon definition of transparency, as it takes on different meanings in different disciplines. The literature also indicates that transparency is beneficial, although absolute transparency could have negative consequences. Despite several attempts to formalize the concept and definition of transparency in AI, to our knowledge, no work has examined transparency from the lens of AI augmentation in the workplace.
2.3 AI errors and transparency
The nature of AI errors has implications for the type of transparency required of AI systems. Current AI algorithms, or more precisely, machine learning algorithms, are based on statistical generalization; in other words, they learn from data samples to make out-of-sample decisions. Thus, AI algorithms are inductive. This is in contrast to systems that are deductive, as they are based on applications of generalized laws. For example, the automatic take-off and landing system in aircraft is an application of physics laws that are universally true for all practical purposes.
Consider an AI system that screens resumes to shortlist candidates for a job. Suppose an HR department decides to test such a system. They prepare a job description, manually curate a list of 100 resumes, and select 10 that match the position. When the AI system is fed the job description and the 100 resumes, it returns 15 resumes as candidates for screening. What level of transparency should accompany the resume screening system? In this particular case, the HR department can calculate both the precision and recall of the system, as it has curated a ground truth set. In practice, this will not always be possible. It is important to know that most AI systems will be based on some form of scoring and that there will usually be a score threshold that a user can tune based on their needs. A high threshold usually results in high precision and low recall, and a low threshold leads to low precision and high recall. In practice, if the advertised job is for a routine, low-skilled position, then high precision is sufficient to select candidates for further evaluation. However, if the position is for a high-skilled job, then high recall is important to avoid overlooking a suitable candidate whose skill set matches the job but is not presented in a standard resume template.
Another important aspect of using AI systems is understanding the bias–variance trade-off of the underlying algorithms. For practical purposes, this is a specialized skill that somebody in the organization should possess. Linear or shallow models generally have high precision and low recall while the opposite is true for non-linear and deep models [23]. From a transparency perspective, if coarse information on the complexity of the model is provided, then this should be sufficient to appreciate the behavior of the AI system over time. With more experience, an organization may ask a vendor to customize shallow or deep models for different groups of jobs. For example, shallow models for low-skill jobs and deep models for high-skill jobs can be created, with the caveat that the vendor of the AI system had sufficient data to calibrate across the job spectrum.
| 2024-05-14T00:00:00 |
2024/05/14
|
https://link.springer.com/article/10.1007/s43681-023-00257-w
|
[
{
"date": "2023/01/01",
"position": 35,
"query": "AI job creation vs elimination"
},
{
"date": "2023/01/01",
"position": 8,
"query": "workplace AI adoption"
},
{
"date": "2023/01/01",
"position": 30,
"query": "AI labor union"
}
] |
Investigating the Influence of Artificial Intelligence on ...
|
Investigating the Influence of Artificial Intelligence on Business Value in the Digital Era of Strategy: A Literature Review
|
https://www.mdpi.com
|
[
"Perifanis",
"Kitsios",
"Nikolaos-Alexandros Perifanis",
"Fotis Kitsios"
] |
by NA Perifanis · 2023 · Cited by 413 — Future research needs were identified, and a theoretical model was created to discuss the four sources of value creation, including AI and machine learning in ...
|
The structure of the current work is as follows: The methodology used to conduct the literature review is described in Section 2 . The results that emerged through the assessment of the articles are discussed in Section 3 . The last section concludes by encouraging the scientific community to further investigate the problems and connections identified in this conceptual model by summarizing the research’s findings, stating its implications, and outlining its limitations.
This study is about the integration of AI with business and IT strategies in the context of digital transformation. The research found that organizations commonly undergo a digital transition driven by technological developments and regulatory changes and that the integration of AI capabilities with business and IT strategies is crucial for achieving improved business value outcomes and enabling digital transformation alignment. The study also highlighted the importance of a dual strategic focus on innovative and routine AI deployment, as well as the need for responsible AI governance and the use of AI to support adaptive transformation. The study’s findings contribute to our understanding of how organizations can optimize their use of AI to promote strategic flexibility and benefit realization.
According to van de Wetering et al. [ 13 ], adaptive transformation capability is defined as a firm’s ability to recognize and seize new market and technological opportunities and develop organizational capabilities concomitantly with the adoption of new strategic directions [ 3 45 ]. This acumen can also be thought of as the dynamic ability to deploy organizational resources and competencies to accomplish the intended outcome [ 46 ] and drive the organization’s future entrepreneurial activities and business value potential [ 47 ]. However, little is now known about the ambidextrous use of AI, how enterprises can utilize it habitually and creatively, how this supports dynamic capabilities, and particularly how they work together to generate value [ 48 ]. While more firms are using AI today to improve and adapt organizational operations, there is a lack of theoretically grounded or empirically validated data to help organizations with their strategic orientation [ 42 45 ]. As a result, this paper’s main goal is to draw attention to key aspects of how artificial intelligence capabilities contribute to different perspectives on the business value realized through the alignment of business and IT strategies during the digital transformation in order to address this research problem in the aforementioned connection. In total, 139 sources were examined after being analyzed through the lens of the Webster and Watson methodology [ 49 ]. Companies all around the world are struggling to incorporate AI since it is continually changing and requires particular consideration of all of its different value dimensions. It is crucial to keep track of the most recent findings on the improved business value outcomes produced by the deployment of AI in the various modes of digital transformation as AI progresses from ordinary algorithms to revolutionary super intelligence and beyond.
We are aware, thanks to the IS literature, that organizations develop distinctive, difficult-to-copy capabilities by integrating and using a variety of complementary firm-level resources [ 14 41 ]. Building on this body of research, this study views AI technology as one such resource that, while necessary for the development of an AI capability, is not sufficient in and of itself [ 14 ]. This essentially indicates that while AI approaches are readily available on the market and susceptible to replication, they are unlikely to generate significant competitive advantages on their own. Additionally, the data needed to power these methods by itself will not be enough to develop distinct AI capabilities [ 13 ]. Early reports from industry leaders in AI adoption show that organizations need a special mix of physical, human, and organizational resources to establish an AI capability that can really add value by distinguishing it from competitors [ 14 42 ]. There is little comprehensive theoretical and empirically proven knowledge regarding how to profoundly develop and use AI capabilities [ 43 44 ].
Although other scholars are also of the same mind, many organizations are still experimenting with AI (e.g., using first pilots), and only a few organizations embed AI as part of the everyday working routines across the organization [ 24 33 ]. Nevertheless, organizations have invested heavily in AI and underlying machine learning algorithms to enhance business operations and support decision-making [ 34 ]. As mentioned previously, technology such as AI not only presents new opportunities and advantages for businesses but also new difficulties [ 31 35 ]. AI solutions are being implemented and used by businesses in an effort to automate processes, boost productivity, cut costs, and gain a competitive edge over rivals [ 36 38 ]. A crucial element in accomplishing these objectives is AI governance. AI governance “may be characterized as a collection of tools, methods, and levers that influence AI development and applications,” claim Butcher and Beridze [ 39 ]. However, there is still an opportunity for research on how to implement AI governance within a company and how AI governance helps a company achieve its objectives.
AI has a growing impact on a variety of societal spheres, including marketing, healthcare, and human rights. It could be detrimental to let the creation of AI applications progress without any oversight [ 30 31 ]. As a result, it is critical to support a reliable AI that complies with legal requirements and upholds moral standards (from a technical and social perspective). Because AI should be viewed as a dynamic computational frontier, governance should therefore go beyond just the content and also encompass its analysis [ 25 ]. To address issues such as the lack of alignment between business users and analytics practitioners, governance mechanisms for analytics are also required in addition to IT and data governance [ 32 ].
Information systems (IS) and business research from academic and professional institutions indicate that artificial intelligence is gaining traction in the market [ 24 28 ]. Since the 1950s, when the idea of artificial intelligence first surfaced, research on the subject has been advancing steadily. However, over the past 10 to 15 years, there has been a significant acceleration in the development and practical use of AI due to the growing availability of huge data, improved computational processing power, and novel AI approaches, learning algorithms, and applications [ 29 ].
Senior executives view analytics and AI as crucial game changers enabling businesses to survive the present crisis, according to a recent Gartner report [ 13 ]. Despite the excitement surrounding AI’s promise, presently, there is a substantial scholarly discussion about the adoption obstacles and the skills and abilities required for useful AI results from a strategic point of view [ 14 15 ]. AI can benefit businesses significantly, but in order to implement AI and enable a high effect that does not undo all the expenditure and effort, organizations must define a compelling common vision when a substantial shift is necessary [ 16 18 ]. Additionally, businesses must use several distinctive technologies such as AI to build adaptive transformation and sense-and-respond capabilities that will spur innovation, enhance customer service and experience, and promote improved performance [ 5 23 ].
The phrase “artificial intelligence” refers to a wide range of leading-edge analytics, applications, and logic-based methods that imitate human behavior, decision-making, and processes including learning and problem-solving [ 6 7 ]. However, as part of the digital transformation, AI technologies give businesses several chances to transform their operations across numerous sectors [ 8 ]. Examples include applying AI-driven decision-making to loan, credit, or sales forecasts [ 9 10 ]. Additionally, AI can provide significant benefits by automating formerly manual procedures [ 11 ] and enabling enhanced processes where humans and AI collaborate in a positive way [ 12 ].
It has become apparent that both socio-technical and political-economic changes, along with demographic changes, have swiftly accelerated during the COVID-19 pandemic. Modern businesses have had to hone their adaptive capabilities to manage changing market dynamics and client behavior under these challenging circumstances. Rapid organization evolution is made possible by adaptive capabilities, which also act as a basis for organizational change and digital transformation [ 1 2 ], but still lack strategic guidelines in order to keep up with the exponential pace of modern technology [ 3 ]. Existing businesses use cutting-edge technologies to improve and adapt their operations. Artificial intelligence, also known as the next wave of analytics, is one of those technologies [ 4 5 ].
A classification framework was applied to the investigation of one hundred and sixty-nine articles. All of the articles were organized into two overarching concepts as follows: 1. Artificial intelligence capabilities and 2. the integration of AI and business/IT strategy for enhanced business value. By providing additional knowledge in this domain and providing a better understanding of the strategic function of AI, these notions will aid present and future academics and researchers in growing the related research body. These papers are presented in Table A1 Appendix A ).
Additionally, this research contributes to our understanding of the ways organizations must optimize their AI resources to promote strategic flexibility and benefit realization at the strategic level of the organization and contributes to the current body of knowledge on shaping and developing dynamic capabilities. Furthermore, the research suggests that by establishing digital skills that are challenging to compete with, businesses can traverse challenging and shifting business environments. Additionally, the research refutes the notion that AI is frequently monolithic and unable to adjust to changing surroundings and highlights the importance of using AI to support an adaptive transformation instead of impeding it. Finally, the research draws attention to the importance of good AI governance and its direct impact on an organization’s results.
The research was developed with a scientific focus to present a more detailed picture of how AI affects organizations and demonstrate the critical role AI capabilities play in enabling the integration of digital transformation alignment, ultimately generating a competitive advantage. The study also revealed the enablers and drivers for pursuing AI’s increased business value and emphasizes the need for organizations to have a dual strategic focus on innovative and routine AI deployment for its synergistic impact on the strategic flexibility of the organization.
The novelty of this research lies in its focus on the integration of AI with business and IT strategies as a key enabler of digital transformation alignment, which improves a variety of organizational business value outcomes. The study conducted a systematic literature review using a particular technique that has been widely utilized in the past to investigate information systems strategy and subjects related to digital transformation. This research also examined the specific difficulties, solutions, levers, and streams in the context of responsible AI governance and the use of its ambidexterity in the development of AI capabilities.
The search was finished when repeating articles for different keyword combinations were found. The necessary number of articles had been acquired to match prior studies. The major findings and contributions for each paper, along with the illustrative components, were compiled on an Excel data extraction sheet, which was then used to evaluate the final sample.
The search for the aforementioned keywords resulted in the collection of a total of 1738 articles. Following the application of language, source, and category restrictions, there were a total of 942 articles remaining. After reviewing the contents of the remaining articles, we decided not to include 547 articles because of their titles, 164 articles because of their abstracts, and 109 articles because of their actual content. After that, 6 duplicate articles were eliminated, bringing the total number of articles down to 116. In addition to these, 12 articles were added as a result of the forward search, and 11 articles were added as a result of the backward search. This resulted in 139 articles being available for examination ( Figure 1 ).
The papers were found in the Scopus, Science Direct, and Web of Science databases using a combination of the phrases Artificial Intelligence (AI), AI capability, business strategy, IT strategy, business value, and digital transformation in the title, keyword, and abstract sections of the search query. Each article was published in a journal that had undergone peer review or in conference proceedings. There were no limits with regard to the year of publishing.
To investigate the AI controversy within organizational and managerial studies, Smacchia and Za [ 55 ] undertook a computational literature survey in their work. They also identified which publications and research fields this argument has evolved in over time via impact and content analyses. Di Vaio et al. [ 56 ] explored the body of literature on the application of artificial intelligence to the development of sustainable business models, offered a quantitative overview of the body of research in the area, and discussed the connections between AI, the exponential growth of machine learning, and sustainable development. Lastly, according to Dhamija and Bag’s [ 57 ] cluster analysis results on the key topics for current and future researchers in the field of artificial intelligence, six clusters emerged: (1) Artificial intelligence and optimization, (2) engineering/research and automation, (3) operational performance and machine learning, (4) sustainable supply chains and sustainable development, (5) technology adoption and green supply chain management, and (6) internet.
According to this perspective, this article aimed to fill this gap by conducting a thorough literature review focused on the integration of AI with business strategy, combining the existing approaches with models, highlighting the anticipated advantages, difficulties, and opportunities, and launching a discussion about potential new research directions. Trunk et al. [ 7 ] conducted a literature study to examine how AI and corporate decision-making interact in dynamic situations. In order to provide a summary of the prospects of existing studies in linking AI with business decision-making in dynamic environments, the authors searched for peer-reviewed publications and performed a content analysis. Insight was provided in a theoretical framework that first outlines how humans might use AI for decision-making in dynamic situations before outlining the challenges, prerequisites, and implications that need to be taken into account. Grover and colleagues [ 53 ] investigated the viability of using AI within an organization based on six factors, including job fit, complexity, long-term effects, affect towards use, social factors, and facilitating conditions for various elements of operations management, by mining the collective knowledge of experts on Twitter and through the academic literature. A systematic review of the literature in peer-reviewed scientific journal articles was conducted by Caner and Bhatti [ 54 ] in order to present a theoretical model for examining the AI organizational strategy. They deduced that the key elements of AI in organizations are its capabilities and limitations, financial matters and AI, organizational functions and AI, workforce, industries and AI, and laws and ethics of AI in identifying AI corporate strategy.
The paper by Enholm et al. [ 51 ] offers a systematic literature review that makes an effort to clarify how organizations can use AI technologies in their operations and elucidate the value-generating mechanisms. It synthesizes the existing literature and highlights (1) the major enablers and inhibitors of AI adoption and use; (2) the typologies of AI use in the organizational setting; and (3) the first- and second-order effects of AI. The report also presents the gaps in the literature and creates a research agenda that suggests areas that should be studied in more detail in the future. The framework developed by Keding [ 27 ] illustrates the structure of the research field by grouping pertinent articles into two research scopes: Condition-oriented research, which investigates antecedents for leveraging the use of AI in strategic management, and outcome-oriented research, which examines the effects of AI in strategic management at both the individual and organizational levels. In order to create a research agenda, Zuiderwijk et al. [ 52 ] conducted a thorough evaluation of the body of literature on the implications of using AI in public governance. They classified the possible advantages of AI application in government into nine categories using their qualitative analysis: (1) Benefits for efficiency and performance, (2) benefits for risk identification and monitoring, (3) economic benefits, (4) benefits for data and information processing, (5) benefits for services, (6) benefits for society as a whole, (7) benefits for decision-making, (8) benefits for engagement and interaction, and (9) benefits for sustainability. The following eight categories were used to identify issues associated with the application of AI in government: (1) Data challenges, (2) organizational and managerial challenges, (3) skills challenges, (4) interpretation challenges, (5) ethical and legitimacy challenges, (6) political, legal, and policy challenges, (7) social and societal challenges, and (8) economic challenges. A literature review was conducted by Borges et al. [ 26 ] to examine the relationship between AI and corporate strategy.
To begin with, Kitsios and Kamariotou [ 1 ] offered a study agenda on the use of AI and ML in organizational planning and decision-making procedures. Future research needs were identified, and a theoretical model was created to discuss the four sources of value creation, including AI and machine learning in organizations; the alignment of AI tools and information technology (IT) with organizational strategy; AI, knowledge management, and the decision-making process; and AI, service innovation, and value. By completing context, journal, and concept-based analyses using preferences for the AI technique, areas of application, and sector preferences perspectives, the study of Çebeci [ 50 ] analyzed the current status and orientation of AI studies in the MIS literature and presented it in detail.
Since the number of studies on AI has been growing dramatically over the years, it is not surprising that systematic literature reviews [ 1 54 ] and bibliometric analysis [ 55 57 ] are widely used as review methods in the management sector. Remarkably, the studies cover a broad range of topics, indicating that AI, in the organizational setting, is being applied in different areas for different purposes. To the best of our knowledge, no recent literature review has specifically discussed the integration of AI capabilities with Business/IT strategies in order to promote enhanced business value outcomes. Rather, these reviews have investigated the phenomenon by investigating a wide range of factors that can affect this relationship. All of these reviews are presented below ( Table 1 ).
Our research was conducted following the guidelines of Webster and Watson’s [ 49 ] systematic literature review. This is a procedure that consists of three phases: (1) In order to identify databases and keywords, a survey of the most recent literature was conducted. (2) Following this, a thorough backward search was performed to look into citations, and a forward search was performed to look for citations of the selected publications. (3) At the conclusion of the procedure, potential study opportunities were identified, and all of the articles were categorized by concept in accordance with their individual contents.
To summarize everything said above, we offer a conceptual model that outlines all the aforementioned relationships. In Figure 5 , which was modified based on the prior portions of important literature, the streams for enhanced value outcomes in the integration of AI in business/IT strategies are graphically represented. This framework was specifically designed to help managers assess the competitive value of complex AI investments while also taking a strategic stance on the anticipated connections.
Change projects that support adaptive transformation skills rather than stifling them are more likely to yield lasting effects [ 13 ]. Unfortunately, as firms undergo transformation processes, numerous impediments become ingrained in them. Consider, for example, disgruntled workers, stubborn decision-makers, and routine processes [ 34 ]. The extended leadership team is engaged by adaptive transformation capability, which also helps reshape the organization, its management, and its resilience [ 5 86 ]. Adaptive transformation capability addresses such roadblocks to transformation and directs businesses in orchestrating balanced transformation alignment. An adaptive transformation capability, as a strategic capability, enables businesses to stabilize the transformation roadmap and acts as the pillar to achieve high performance in turbulent times [ 34 90 ]. This dynamic flexibility, which is supported by AI capabilities, enables businesses to swiftly coordinate the beginning of the subsequent development phase and carry out essential adjustments [ 21 ]. With a high level of participation, businesses make sure that long-term improvements drive competitive performance and produce ground-breaking outcomes in challenging times [ 37 159 ].
Many academics contend that strategic flexibility develops a portfolio packed to implement a variety of contingent strategies and motivates the organization’s IT and business resources to be renewed in order to achieve operational capability-level efficiencies, business/IT alignment, quality improvement, and innovativeness [ 70 178 ]. Additionally, strategic flexibility enables firms to restructure and improve operational practices and capacities and accelerate the adoption of digital technologies [ 2 ]. Moreover, strategic flexibility enables organizations to create the best possible business strategies and the skills required to implement the core strategy. Furthermore, it might improve their operational ambidexterity or a dual digitalization framework to operational capabilities, or their operational exploration and exploitation capability [ 13 179 ]. Therefore, companies need to be strategically flexible because they must reassess their current operating models and adapt as quickly as their environment, especially in the face of a pandemic such as COVID-19 [ 146 182 ]. Therefore, this study conceptualizes that the alignment of AI Capabilities and Business/IT strategy enhances several business value outcomes for organizations [ 51 109 ]. This is in line with the extant literature on the IT-business value process [ 173 ], leveraging IT ambidexterity and AI capabilities in organizations [ 13 109 ].
Additionally, AI ambidexterity simplifies the ability of enterprises to coordinate and mobilize their resources, skills, and previously unrelated capabilities [ 37 63 ]. Additionally, AI ambidexterity gives businesses the resources they need to reinvent their work processes with the help of cutting-edge intelligent technologies and algorithms [ 177 ]. Finally, by empowering decision-makers to innovate [ 8 72 ], roll out or align business alternatives all around the organization, and possibly enter new business sectors [ 5 ], the organization will be able to constructively perform the business strategy. Utilizing these ostensibly incompatible and competing AI application modes means firms are better able to detect and foresee changes, respond proactively to them, and align business and IT strategies. The accepted complementary view on the capabilities of AI goes beyond a structural and temporal focus and highlights the dynamic and interconnectedness of AI’s routine and innovative use as a key factor in what motivates organizational strategic flexibility [ 21 ]. In reality, it is entirely possible that novel applications of AI, and hence the exploration mode, come before standardized methods of using them [ 8 75 ].
Though it might not be as simple as one might imagine, obtaining economic value from AI ambidexterity may be a challenge. First, given the company’s adoption and progress of AI, routine and innovative usage of AI may vary from one organization to the next [ 89 ]. According to the literature, AI should be used as a crucial organizational resource to build the dynamic capabilities of the organization so that it can reach its full potential [ 42 175 ]. A critical dynamic capability and strategic flexibility thus evolved as a result of the simultaneous strategic emphasis on these two fundamental features of AI ambidexterity [ 139 ]. This is also consistent with the claims made by [ 72 176 ], who assert that the strategic flexibility of an organization is often significantly impacted by the application of analytics and AI in action. By anticipating key change agents and potential future business scenarios, AI ambidexterity especially enables enterprises to forecast market trends, better understand the challenging environment, and respond appropriately, giving them the very first advantage [ 37 ]. The framework for developing data- and AI-driven business plans and scenarios that encourage commitment to action is provided by the ambidexterity of AI for businesses [ 13 177 ].
So far, a variety of business value outcomes have been proven to be enhanced by the implementation of AI technologies in organizations’ schema but we are still at the very beginning of this new technological era. Despite the fact that little knowledge is, as yet, robust from both a theoretical and technical viewpoint, there are remarkable studies on AI and Business Value Streams in organizations. Prior research [ 91 173 ] examined how IT resources affected higher-level organizational capacities, but there has not been much attention paid to developing intermediate capabilities in the context of AI [ 74 174 ]. As a result, businesses should adopt an ambidextrous viewpoint while utilizing AI in practice, whereby routine and novel uses of AI simultaneously fuel the growth of the organization’s strategic flexibility.
Strategy control refers to the actions taken by strategists to make sure that the execution of strategic plans proceeds as planned and to track the achievement of strategic objectives. Despite its necessity, there has not been much research on using AI for strategy control [ 66 ]. Nevertheless, due to the ability to automatically identify appropriate performance criteria, track and assess performance against standards, and recommend paths for corrective measures based on predictive analysis, various viable areas can be found. The use of AI for project management and internal communication is particularly intriguing. AI will become an important tool for assisting strategists in assessing the implementation and performance of their strategies as more and more commercial operations are managed through increasingly interconnected digital platforms [ 90 159 ].
Through the development of conversational systems and robotic sales advisers, AI is also making progress in assisting and supplanting human activities in tasks connected to the exploitation of new business ideas [ 171 ]. It is yet unclear how valuable these solutions will end up being in the long run. Questions about the effects of organizational de-skilling and a loss of client relationships as a result of robo-advisors, as well as concerns about customer acceptability of contact with AI-based systems, will present new study opportunities in the future [ 132 ]. Important questions about how AI-based technology affects strategic entrepreneurship when it comes to expanding new businesses and controlling the risk involved in entrepreneurial activity arise from a strategy perspective.
According to Chalmers, MacKenzie, and Carter [ 171 ], there are three ways that AI might improve the information-search and idea-generating processes that form the cornerstone of discovering and seizing new business opportunities. First, the capability of deep learning algorithms to locate structures in high-dimensional data enables corporate and start-up entrepreneurs to look for and test previously unobservable prospects [ 165 ]. Second, AI can encourage the creation of new businesses by identifying and capitalizing on consumer demands [ 132 ]. Third, AI-based simulations and trials offer financiers and company executives the chance to put fresh ideas and ventures to the test. For instance, simulations employing dynamic real-world data might mimic the circumstances that new businesses might face in the future [ 165 ]. When completely developed, such tools might not only be useful for investment decisions but also for designing innovations and making decisions on crucial product characteristics such as pricing or marketing [ 20 34 ]. Entrepreneurs could thus put their ideas to the test, forecast how buyers would respond to certain product features, and make adjustments to product design and pricing using AI-based simulations and trials [ 171 ].
It is becoming clearer how opportunities and obstacles for launching new businesses and strategic entrepreneurship may arise from the adoption of AI technology by businesses. A general-purpose technology (GPT) as a new way of creating, AI, and particularly deep learning, has the potential to change the structure of the R&D process and the nature of the innovation process [ 1 170 ]. They contend that improvements in AI result in a reinforcing loop between innovation at the level of AI and its application sectors, similar to the growth of previous GPT such as the microprocessor.
Post-acquisition, by merging vast expanses of unstructured data from different enterprise systems, such as those found in customer databases and contract repositories, AI may further enhance and speed up job integration and uncover potential for cost reduction. Similar to this, AI may have uses in cooperative strategies such as partner selection and identification in strategic alliances. Indicators such as a potential partner’s company emphasis or strategic orientation, for instance, may be found by strategists using NLP on annual reports [ 169 ].
Furthermore, given the importance of speed and efficiency in decision-making regarding M&A opportunities [ 167 ] and the post-merger integration stage, AI can have a significant impact on performance by automating acquisition process steps and narrowing crucial M&A cycle activities [ 109 ]. Additionally, these tasks could be carried out more cheaply. For instance, with regard to the pre-acquisition stage, transactional law has made significant strides in recent years, allowing legal practitioners to streamline the labor-intensive M&A due-diligence process. Among the many uses for AI, automation can help target companies gather and categorize pertinent documents more effectively while ensuring they adhere to disclosure laws [ 168 ].
AI technologies are also changing how businesses identify and evaluate potential merger and acquisition prospects as well as how they handle the deal cycle and post-merger integration phase. Traditional mergers and acquisitions (M-A) are bound to monitor a limited set of potential targets because they call for a variety of resource-intensive analytical activities, due diligence, market analysis, valuation, and pricing, but AI-based analytics enables businesses to display a big pool of opportunities automatically and constantly as they present themselves [ 5 86 ]. Automatic document summarization and topic modeling are two examples of natural language processing (NLP) techniques that can be used to create a filter that will preselect appealing situations for further human consideration [ 66 ]. The advantage of artificial intelligence in these situations comes from the technology’s capacity to integrate a variety of data sources, including patent databases, organizational financial records, previous M-A deal data, and social media, for example, LinkedIn data, in order to identify rare skill sets, news media, conference call document filings, and discussion forums, and dynamically adapt screening criteria to shifting environmental conditions [ 166 ]. For instance, Refinitiv, a San Francisco-based provider of emerging financial technology solutions, uses AI techniques to create predictive quantitative models on M&A targets that assist decision-makers in more correctly estimating synergies and evaluating deal value [ 34 ].
We consider its function in the study of typical corporate-level strategy concerns pertaining to a firm’s business portfolio and decisions regarding growth and diversification to provide an example of how AI can be employed in certain areas of strategy formulation and implementation [ 165 ]. A business portfolio of enterprises can be evaluated for fit, risk, and performance using artificial intelligence, and potential synergies between them can be analyzed and suggested [ 159 ]. AI can help strategists address portfolio risks, for instance, when demand swings are highly connected throughout the portfolio or when multiple firms are subject to comparable currency risks, based on an examination of market and product data across business units. Such AI “sparring partner” activities are referred to as “cognitive insight” by Davenport [ 29 ].
On the other hand, there are several reservations regarding the limitations of AI systems in the development of strategy. For instance, researchers have made the argument that while AI performs well in stable, context-specific settings, it underperforms in settings that involve creativity, novelty, and uncertainty [ 12 164 ], and it can even increase complexity in overall organizational decision making [ 66 ]. As a result, AI is better viewed as a “helper” that improves strategists’ ability to make decisions concerning external threats and opportunities, internal strengths and weaknesses, and strategic challenges [ 60 73 ].
On the one hand, scientists appear to agree that big data and modern AI applications outperform the capabilities of earlier systems. In-depth understanding of the firm, its environment, and the risk–reward profile of strategic options is necessary for effective strategy formation [ 106 163 ]. Similarly, a strategist’s skill to efficiently monitor operations and assess the effectiveness of strategic activities is essential for successful strategy implementation [ 59 ]. Therefore, the ability of AI system applications to optimize continuous data analysis, generate new information about strategic opportunities, and recognize patterns to foresee the outcome of choices stands to improve the quality of the strategist’s decisions where they relate to formulation and implementation tasks, which require primarily knowledge assets [ 27 63 ].
The activities that make up the formulation and implementation stages of the strategy process are also changing as a result of AI. Organizations set business development and financial targets, as well as associated execution strategies, at varying levels of granularity in their pursuit of profitable growth [ 157 ]. Formulating and implementing a strategy is a protracted and complicated process involving a significant amount of varied data and draws on managerial analysis and decision making at various levels of the organization, regardless of whether such a process occurs frequently and formally or infrequently and informally [ 9 34 ]. Therefore, the cognitive constraints of strategists in processing data for the decision-making and problem-solving tasks underlying strategy formulation and implementation are extensively documented in the literature [ 66 ]. Discussions regarding the development of earlier generations of decision support systems since the 1950s are strikingly similar to those surrounding the potential of AI to improve human strategy formulation and implementation.
Many firms have made AI the focal point of their high-level strategy in light of its quick ascent to the status of general-purpose technology. In the I/0 2017 keynote, Google CEO Sundar Pichai stressed the company’s policy of putting “AI first”, emphasizing a greater outlook on ML and other AI technologies to boost organizational efficiency and enhance customer experience [ 66 ]. In the years that followed, Google and its business partners made significant investments in products that appeared to be more “intelligent,” such as Google Photos, which uses AI to identify people, places, and objects in images, RankBrain, which speeds up searches, and Google Assistant, a personal virtual assistant. All of these moves significantly raised the company’s overall valuation.
Moreover, a complementary resource that is particularly pertinent for AI-supported analysis relates to customer relationships. Customers are participating in more product- and service-related discussions, consuming digital information, and exchanging expertise on a range of social media platforms [ 161 ]. Strategists can better understand patterns and seasonality in consumer needs connected to their service and product offerings by keeping track of customer behavior through their digital footprints [ 132 ]. Such information can then be used to anticipate customer preferences, which will eventually result in an analysis important to the company’s product creation [ 162 ].
A variety of additional resources crucial to the strategy process, such as demand forecasting, production planning, resource allocation, and logistics, are increasingly being analyzed with remarkable efficiency using AI algorithms. AI can enhance production planning decisions, for instance, by automating the procedure of choosing qualified suppliers by mining data from online directories and other repositories [ 9 128 ], offering forecasts on the performance of potential suppliers [ 159 ], and even estimating valuation and evaluating online bids [ 160 ].
Furthermore, organizations have vast amounts of detailed, precise, and categorized accounting and financial data. When performing an analysis, strategists frequently use balance-sheet data, for example. AI algorithms can analyze patterns by constantly or discretely clustering collected data. By performing this, algorithms can improve the interpretation of what drives specific financial resource conditions that are pertinent to the nature and timing of the firm’s strategic commitments, such as fluctuations in liquidity and exchange rate premiums at company budgets [ 45 158 ]. AI can also be applied to financial studies that are less crucial to the formulation of strategies, such as tools for keeping track of business transactions [ 157 ]. Applications are able to quickly spot fraud by detecting transactions with unusual quantities or frequencies. With the help of these tools, AI can help manage financial risk by enhancing compliance and risk management activities with better data-driven insights, utilizing quick and automated data analysis, and reducing administrative burdens, freeing up the time of finance and accounting staff members for more inventive tasks [ 142 ].
Additionally in terms of internal analysis, AI may support the strategic analysis of organizational internal elements, such as staff, budgets, and auxiliary resources, including supply chains or customer relationships [ 132 ]. AI applications can help managers detect employee performance, anticipate career paths, and uncover patterns of compensation and inequalities, including other things, by automating pattern recognition in such data, starting with human resources [ 10 ]. Strategists can more accurately gauge the degree to which a possible strategy can be implemented by carefully evaluating abilities, knowledge, aptitude, and demographics.
All these tools also provide a more dynamic method for performing competition analysis [ 142 ]. Indeed, academics have cautioned that in order to assess the ongoing validity of an organization’s strategy, assumptions about competitors must be periodically re-examined and assessed [ 86 ]. The advantage of automated competitor analysis over conventional, manual, and discrete approaches is significant: Once connected to machines that generate market and competitor data, such as web crawlers and online sales, algorithms can carry out competitor analysis continuously and aid strategists in dynamically evaluating the viability of the organization’s current strategy.
Competitor analysis is a key area where AI is used in strategic analysis. Automated analysis can assist in grouping data, spotting trends in data, and even forecasting competitors’ strategic movements as businesses amass enormous amounts of data regarding their competitors and their industries. Strategists frequently have to identify pertinent competitors in order to move forward with strategic analysis, yet doing so continues to be one of their most difficult tasks [ 86 ]. There are new methods for spotting upcoming competitors and forecasting performance, such as studying online content to determine the “correlation” or convergence of the organization’s services and product offers. Similarly, AI algorithms can be used to identify strategic groupings made up of businesses with similar strategies and estimate the transit of businesses within and between these groups [ 66 ].
Ecological and environmental considerations are gradually becoming more important in strategic analysis due to the increased climate change awareness and the focus on corporate sustainability responsibility (CSR) [ 56 ]. Though research on the use of AI in this type of study is still in its infancy, there are encouraging instances, such as studies exploring whether hydrogen electrical vehicles might evolve into the most popular mode of consumer transportation [ 86 ]. Such applications are crucial for both commercial investors and policymakers who are choosing where and how to build transportation infrastructure. Organizations usually invest a great deal in legal advisors who frequently manually compile and assess a big body of current legislation that may change the terms of business across countries and legal regimes [ 39 ]. Applications of artificial intelligence may assist in the internal collection and processing of such legal data by businesses, potentially lowering overall legal costs. For instance, an AI algorithm that sorts through thousands of pages of legal papers can offer helpful summaries pertinent to a firm’s strategy [ 66 ]. AI is also rapidly being utilized to automate financial compliance monitoring and regulation [ 157 ].
Changing demography and societal values are only two examples of social elements that strategists frequently need to consider in their analysis. While some of these changes may be gradual (such as those in national culture), others are prone to abrupt upheavals and quick changes (for example those in fashion), which may present important possibilities or risks to the organization [ 106 ]. To “map the contours of cultural fields, classify cultural materials, and follow the evolution of culture over time,” scholars have suggested methods such as automated text analysis [ 154 ]. Additionally, new algorithms allow for the systematic measuring of culture and the modeling of its development within social groups and organizations [ 27 86 ]. Such advancements provide new possibilities for strategy research’s measurement of challenging notions such as culture. From another standpoint, whether for manufacturer or user firms, researchers frequently assign technical elements a significant part in most strategic analyses [ 66 ]. AI can help businesses keep track of technical advancements and foresee any important technological changes. For instance, by sifting through enormous volumes of patent or publication data, AI is increasingly utilized to uncover trends of technological advancement [ 155 ]. These AI applications enable businesses to create “knowledge profiles” of their market and key competitors [ 156 ].
Concerning external analysis, the strategic appraisal of political, economic, social, technological, environmental, and legal variables has been impacted by AI applications [ 3 ]. The “political environment” across regions can be inferred using a variety of AI-based text analysis technologies created by political scientists. Such systems examine several data sources, such as news organizations, parliamentary proceedings, and online political dialogue. More specifically, unstructured social media data analysis using ML algorithms has proved successful [ 53 ]. Election results, policy changes, political bias, and conflicts can all be predicted using such data, according to research such as that of Chan and Zhong [ 151 ]. With AI, political trends and events may be identified and predicted early on, giving strategists a competitive position by enabling them to better grasp how the government and government policies may affect their business. Additionally, ML can be used to quantify economic patterns precisely and consistently, such as economic growth, the beginning of economic recessions, rising poverty, and bankruptcies [ 63 66 ]. The financial services sector’s embrace of ML tools is a crucial step before strategists can use them. In order to improve their investment decisions, institutional investors, for instance, employ ML to forecast stock returns and calculate systemic financial risks [ 152 153 ].
The potential of AI to improve and change strategic analysis is a place to start when investigating the role of AI in the strategy process. Despite the fact that managers have long relied on information systems to help them gather and organize data for environmental scanning and decision-making [ 128 ], AI algorithms may have the potential to significantly increase the scale, scope, and speed of analysis of an organization’s external and internal environment. This is because AI algorithms are capable of interacting with the environment and generating data. According to previous studies [ 66 ], AI can specifically help with (a) gathering data from internal and external sources on a discrete or continuous basis, (b) analyzing and interpreting that data through pattern identification, and (c) supporting executives in making decisions through predictive analysis. As a starting point for mapping how AI may support strategic analysis, we first discuss its applications for analyzing external (i.e., macro- and micro-environmental) factors. Next, we consider AI’s role in competitor analysis, and, subsequently, in the internal analysis of human, financial, and auxiliary resources.
The third component, “assemble and develop capabilities”, involves acquiring or choosing the capabilities required to carry out the core plan. In order for businesses to be able to adjust to changing client and market demands, they must speed up the development of their adaptable capabilities [ 2 148 ]. In order to effectively develop organizational skills and support structures, processes, decision rights, performance indicators, and adaptive mechanisms, the organization must plan a relevant set of enhancement activities [ 9 147 ]. To enable a successful change endeavor, decision-makers and leaders must alter their ways of thinking and acting [ 146 ]. In the end, this will make it possible for companies to prepare for and react to quick, complicated changes in the environment [ 95 ]. Additionally, change programs that support rather than restrict the organization’s capacity for adaptation are more likely to result in long-term success [ 150 ].
The ability of the organization to assess ideal strategies in order to identify essential and potentially necessary contingent parts is the focus of the second aspect of strategic flexibility, which is the formulation and design of strategies. Consequently, when a company does so consistently, this will lead to decisions about how to produce value and build clear accountability for results [ 9 145 ]. Decision-makers can use a surgical approach to data collection and analysis based on future alternatives and scenarios, and they can then concentrate on addressing important uncertainties to support decisions and foster action commitment [ 144 149 ].
The first factor focuses on the organization’s ability to describe many potential business futures and scenarios based on drivers of change. This theoretical aspect of strategic flexibility essentially charts a path between foreknowledge (denying uncertainty) and paralysis (excess ambiguity) [ 21 148 ]. For instance, scenarios assist organizations in thinking more flexibly about the future so that we can respond more quickly to changing circumstances. By forcing organizations to think deeper into the future than they normally would and forcing decision-makers to consider new options, they also promote innovation and creativity [ 20 136 ]. Thus, the first component aids in comprehending the driving factors, interactions, and changing dynamics at play in the business environment.
This study adopts a broad and comprehensive understanding of what strategic flexibility comprises, in keeping with Raynor’s paradigm for strategic flexibility as presented in [ 138 ]. As a result, the existing literature may be used to identify four essential components of strategic flexibility that together give rise to the idea of dynamic capability [ 139 ]. These components fit with strategies for resource deployment, competitive actions, and proactive and reactive capabilities [ 37 141 ]. Strategic flexibility is a multifaceted idea as a result. These four components are (1) anticipating change drivers and future options [ 43 143 ], (2) formulating and designing strategies [ 137 145 ], and (3) assembling and developing capabilities [ 95 147 ].
The performance of an AI application should be evaluated both before and after deployment by an organization that employs responsible AI governance [ 35 ]. The ability to explain the data and AI governance aspects clearly and concisely, as well as their interactions, is also crucial [ 12 ]. For instance, it is important to record every step of the data processing process, from data collection to use [ 133 ]. Since documented processes are less likely to become obsolete, documentation also reduces reliance on a single person’s expertise. Responsible AI governance also emphasizes inclusive design and the development of human agency and autonomy. These are essential elements for improving the use of human capital inside businesses and, consequently, maximizing knowledge exchanges and relationships. Finally, appropriate AI governance mandates that a high emphasis be placed on the security and dependability of entities and systems that communicate with AI agents throughout the design, implementation, and monitoring of AI applications [ 71 134 ]. By establishing such privacy and security regulations, cross-departmental access and knowledge sharing are made easier without running the danger of sensitive information being leaked or accessed by unauthorized employees [ 135 ].
The idea of responsible AI governance has seven components. Accountability, environmental sustainability, societal well-being, transparency, equity, robustness and safety, data governance, and human-centric AI are some of these dimensions [ 112 ]. Since it takes a great deal of work to develop a responsible AI governance system, one of its main goals is to lessen the potential that a small change in the weight of the input can significantly modify the output of a machine learning model. To ensure that a company is committed to creating objective and dependable AI, continuous evaluation is required [ 119 ]. Therefore, having a maturity model or set of standards to adhere to is crucial for a business while developing and implementing an AI system. The role of knowledge in enhancing an organization’s performance is crucial, as is the organization’s capacity to successfully adapt the information for future use and respond to environmental changes [ 90 ].
Responsible artificial intelligence application development has advantages from an ethical and moral perspective as well as the potential to give organizations a medium- to long-term competitive edge [ 131 ]. For instance, a business can attract technical specialists and keep top talent by demonstrating its dedication to ethical standards, especially in times when competent developers are hard to find. According to the EIU research, unethical business practices deter potential candidates from applying and erode their confidence in the sector, which contributes to the so-called “techlash”, which is the outcome of public skepticism and hostility against major tech businesses [ 115 ]. Moreover, ethical AI policies and procedures make it possible to document how a company handles artificial intelligence-related problems [ 131 ], which aids in the identification of prospective operational problems or business opportunities [ 112 ]. Because reliability increases customer retention, expenditure, and uptake of new services, responsible AI starts to have an impact on performance [ 14 132 ]. By upholding moral and responsible standards, an expertly designed AI application can protect and grow one’s clientele [ 131 ]. Businesses will be able to retain clients and boost their credibility by creating inclusive products and services that are efficient for all customer types, assure safety, and are transparent. Customers’ trust difficulties, for instance, may be resolved with the adoption of blockchain technologies in AI services for traceability and transparency [ 132 ]. From a compliance standpoint, it is equally crucial to building responsible AI governance. Authorities have started keeping an eye on artificial intelligence applications and creating rules that incorporate standards and ethical considerations, such as auditing procedures and algorithmic effect analyses. As a result, a variety of frameworks for protecting personal information and privacy now incorporate privacy by design into their structures [ 125 ].
It is asserted that academics who studied IT governance and data governance in the literature already in existence offered frameworks or procedures for enhancing functionality or reducing hazards brought on by AI [ 119 ]. However, there is a void in the governance of AI, which directly affects AI and deals with both IT governance and data governance [ 62 130 ]. As a result, research on how to implement AI governance would be of great benefit, as would knowledge of improving organizational performance while ignoring the drawbacks of AI use [ 43 ].
Collaboration amongst stakeholders is facilitated through relational governance frameworks. They encompass (1) communication, (2) training, and (3) the coordination of decision-making [ 128 ]. A collaborative development platform should be used to facilitate communication within an interdisciplinary AI team. Technical and business knowledge are crucial AI competences, according to Mikalefand Gupta [ 14 ]. Thus, employee training is u”deniably crucial. While training is frequently associated with learning how to use AI, it can also mean preparing staff members whose duties AI may automate or augment in order to reduce unfavorable effects [ 129 ]. Using communication to convey a company’s aim to deploy AI as an augmentation tool rather than a replacement could help alleviate employees’ anxiety [ 129 ]. In comparison to data governance, ML models and AI system governance are generally poorly understood [ 117 123 ].
Contractual arrangements between involved internal departments or outside entities may concern data, models, or AI systems. Models contain information about the training data that could be taken and utilized improperly in a number of ways, such as by competitors to lower data labeling costs [ 119 ]. By precisely defining the operational parameters of AI, contracts also play a significant part in lowering the risk of liability [ 106 125 ]. In situations that are unexpected and counterintuitive to human logic, AI may malfunction. Operational concerns therefore necessitate explicit legal notices. Additionally, traditional risk management strategies for AI have been proposed [ 126 ]. Monitoring compliance ensures that organizational rules, standards, processes, and contractual commitments are carried out and enforced. The European General Data Protection Regulation (GDPR), which has an impact on data and models and provides the right to model decision explanations, is one of the most notable rules [ 9 127 ]. AI-related issues are identified, managed, and resolved as part of issue management. This covers procedures for standardizing data concerns and their resolution, designating individuals to handle issue resolution, as well as an escalation process [ 123 ].
Furthermore, more suggestions have been made using software engineering as a guide [ 3 67 ]. Some draw generalizations from a case analysis describing the application of ML to address transaction errors, whereas others rely on surveys conducted within a single organization [ 119 ]. The ideal method is still a topic of contention, though [ 67 ]. As mentioned in [ 119 ], the examination of model governance has highlighted procedures for model validation, control, and evaluation (e.g., review policies, updates, and security) [ 119 ]. Significant focus has been placed on ML assurance, that is, carrying out an ML development process that produces evidence for the model’s safety, as well as testing techniques for ML systems [ 124 ]. Overall, research on models and AI techniques is generally lacking.
In accordance with ISO Standard 9000, a process is defined as a set of interrelated or interacting activities, which turns inputs into outputs, while a procedure is defined as a predetermined technique to carry out an activity or a process [ 119 ]. We think of processes and procedures in the context of governance as standardized, recorded, and repeatable ways. AI procedures can be regarded as an essential component of the effective deployment of AI governance [ 112 ]. They are related to procedures connected to ML and AI systems and procedures for data governance [ 123 ]. The cross-industry standard process for data mining is frequently used in the building of ML models while software engineering coding standards can also act as a governance tool. A similar governance tool for AI to promote interoperability may include defining and enforcing model and system architectural principles, documentation, and coding norms with the aim of improved composability and maintainability [ 32 119 ]. The recording of each feature, along with its justification, is considered to be the best practice.
High-level standards and norms are provided by AI policies. Key objectives, accountability, roles, and duties are all communicated by organizations through AI policies. Politicians are actively debating AI policies. For instance, the European Union has presented policy options on how to promote the use of AI while minimizing hazards, and a portion of them has already been included in a proposal of the 2021 European Commission [ 115 ]. Best practices could be a source for policies at the corporate level [ 122 ]. The measurement of (public) AI policy is a hot topic that is also the subject of ongoing discussion and study. For instance, Mishra et al. [ 31 ] cover the measurements of AI’s societal and economic impact and the dangers and threats posed by AI systems. While there has been significant progress in the development of data standards, there has been less progress in the establishment of AI standards [ 119 ]. Examples include Wellbeing metrics for ethical AI (IEEE P7010), Benchmarking accuracy of Facial Recognition Systems (IEEE P7013), Fail-Safe Design for AI Systems (IEEE P7009), and Ethically Driven AI Nudging Methodologies (IEEE P7008).
Based on strategic organization goals, the strategy indicates high-level guiding of actions. The study by Keding [ 27 ] focused on where AI and strategic management interact, with a particular emphasis on two aspects: (a) Antecedents, such as data-driven workflows (data value chain and data quality), managerial willingness, and organizational determinants (AI strategy and implementation); and (b) consequences of AI in strategic management on a personal and organizational level (e.g., human–AI collaboration, AI in business models) [ 119 ]. The work focuses on using AI for business intelligence-related decision-making within an organization. A number of AI strategy-related components are currently being worked on, including guiding concepts by academics and practitioners [ 118 121 ].
The goal of procedural governance mechanisms is to guarantee that AI systems and ML models function effectively and accurately, that they will be held securely, and that their operation complies with all applicable laws, regulations, and company internal rules and policies regarding explainability, fairness, accountability, security, and safety. Ensuring data, model, and system-relevant features and is another goal of procedural methods [ 119 ]. Individually and collectively, they include (1) a strategy, (2) policies, (3) standards, (4) processes and procedures, (5) contractual agreements, (6) performance assessment, (7) compliance monitoring, and (8) issue management for data, models, and systems.
The development of AI systems involves many different disciplines [ 119 ]. In order to manage the complicated interplay between model outputs, training data, and regulatory and business needs, it may be necessary to construct an inter-disciplinary AI governance council that has been proposed for AI in healthcare [ 106 ]. Executive sponsors are also vital to the process [ 3 ]. Depending on the company’s adoption level, the executive sponsor’s level of power and decision-making over performance objectives may vary. For instance, a dedicated AI budget without any performance requirements would help adoption, at least in the early stages [ 108 ]. Investigations into more precise roles connected to model elements are still ongoing.
Reporting frameworks, governing bodies, and accountability are defined by structural governance processes [ 117 ]. They consist of the distribution of decision-making authority along with roles and duties. Although there is a wealth of work on data governance [ 32 ], there is not as much on AI governance [ 106 118 ].
Different mechanisms can be used by businesses to govern AI [ 52 ]. They include formal frameworks linking business, IT, data, model, and machine learning functions, formal procedures and processes for decision-making and monitoring, and further practices encouraging stakeholder engagement and collaboration [ 34 ]. We separate governance methods into three categories: Structural, procedural, and relational in accordance with the IT governance literature [ 115 ].
AI is influencing more and more facets of society, including marketing, healthcare, and human rights. It would not be a good idea to permit the development of unsupervised AI applications [ 39 ]. Therefore, it is crucial to advance a reliable AI that abides by the law and is moral, ensuring that ethical principles and values are upheld, and is reliable from both a social and technical perspective. Depending on the viewpoint of each person, governing AI initiatives may be regarded differently. While the European Commission (EC) and Singapore principles view AI governance from a trustworthy stance where solutions are human-centric, Microsoft researchers view AI governance from a technical perspective [ 115 ]. The seven ethical AI principles, as outlined by the European Commission, are depicted in Figure 4
There is a growing consensus on responsible AI governance, despite the lack of a precise definition [ 115 ]. It can be described as a function that details the various ethical rules that apply to AI. It may also be described as a procedure that spans all phases of AI project lifecycles by adhering to the responsible use tenets [ 35 ]. In particular, it is crucial to look at what kind of impact responsible AI governance has on businesses’ capacity to adopt changes in business products, procedures, and services and benchmark against competitive performance gains [ 44 ]. Microsoft, for instance, created explainability tools to comprehend machine learning models that support decision making [ 112 116 ]. Therefore, there is accumulating evidence to support the assertion that responsible AI governance affects internal organizational knowledge management skills [ 30 ], as well as how organizations are perceived by external entities when utilizing AI [ 35 ].
Although it is predicted that the AI-specific technology needed to support projects will evolve extremely quickly, it is equally crucial to concentrate on other organizational resources that must be fostered in addition to the technology. The development of firm-specific, difficult-to-replicate AI capabilities requires these complementing organizational resources [ 14 ]. As a result, an organization’s capacity for AI might be defined as its capacity to choose, coordinate, and utilize its AI-specific resources. The study conducted by Ransbotham et al. [ 5 ] provides an exemplative illustration of the complementing organizational resources needed to gain business value through AI investments. While Davenport and Ronanki [ 33 ] point out that managers in more than a third of the studied firms do not grasp AI technologies and how they work, the previous authors remark that one of the most significant impediments to generating value is the absence of leadership to promote AI. As mentioned before, the significance of such supplementary resources has been stressed in a number of practice-based research. For example, Fountaine et al. [ 113 ] stress the value of encouraging inter-departmental collaboration and creating cross-functional teams with a variety of viewpoints and expertise. Organizations may make sure that AI projects take into account overall organizational priorities and not just specific business concerns by bringing analytics professionals together with business and operational personnel [ 102 ]. Additionally, by doing so, the applications for artificial intelligence that are created will be more in line with operational requirements [ 114 ]. As working with AI necessitates a completely new sort of skillset for both technical and management staff, developing the unique AI talents that firms need to build is another problem mentioned in numerous research studies.
The process of deploying requires actively assisting the leverage strategy [ 110 ]. Deploying requires integrating a machine learning model into a current production system so that business decisions can be based on data, such as a resource advantage, market opportunity, or entrepreneurial strategy [ 107 111 ]. Supporting a chosen leveraging strategy involves actually using capability configurations. Choosing an AI-oriented strategy and deploying solutions in accordance with it will result in diverse outcomes depending on the environmental setting in which such capability configurations are deployed in the context of AI deployments [ 84 112 ]. Because of this, there are many different ways that AI may be used within an organization, and the AI capability that a company manages to create can be coordinated and used alongside other capabilities to pursue digital business strategy [ 59 ].
Integrating mobilized assets to produce capability configurations is the process of coordination. High-level managers are crucial because they have to coordinate the individual skills and knowledge of their teams, enabling quick, effective, and seamless integrations [ 9 86 ]. This means that in the context of AI deployments, any developed AI capabilities must be successfully coordinated and integrated with other organizational capabilities in order to implement the leveraging strategy effectively and create value [ 102 ]. For example, creating AI pipelines to make the effective processing of data and models possible requires a great deal of work. This means that in order to integrate an AI capability among others that will enable the firm to generate value, there must be open lines of communication and collaboration across various organizational units [ 14 ]. Here, managers play a crucial role because it is up to them to use their network of connections to combine various competencies into arrangements that add value.
The goal of mobilizing is to determine all the capabilities needed by a company to gain a competitive edge. When the business environment is highly unclear, this is not a simple process. Businesses interested in AI technologies should determine what internal gaps they need to address and what external opportunities they need to seize [ 74 109 ]. This means that carefully evaluating which opportunities in the surroundings they are geared towards is essential before beginning to develop AI applications. This puts pressure on top-level managers to be able to strategically anticipate advancements and gain the technical expertise to be able to conceive ways in which AI technology might be applied creatively to address urgent concerns [ 3 45 ]. However, mobilizing calls for ongoing changes to the business’s processes, which can be difficult to maintain over time.
Pioneering is the process of integrating brand-new materials that have been obtained from the market and engaging in exploratory learning. This could entail the bisociation process, which involves combining information that is dissimilar and unrelated [ 4 ]. This may imply using data sources that are vastly different from those owned or controlled by the company when it comes to AI applications, or it could entail hiring employees with distinctive and completely different skill sets [ 10 ]. Being able to offer value propositions that outperform rivals in ambiguous environments contributes to a competitive advantage. In order to create such value propositions, pioneering is an essential process.
Enriching is about spreading an existing capability. This can be achieved through expanding resources, developing new skills, or forming new partnerships with businesses that have access to the necessary resources. Companies that use AI applications need data that other businesses have access to or even people with extensive understanding of tackling AI-specific problems in order to develop their AI models [ 7 ]. Alliances can offer essential skills for attaining competitive advantage without incurring significant risks, which is advantageous for both parties [ 106 ]. However, other businesses might use the same tactics, thus the competitive advantage might only be momentary and fleeting.
Tiny enhancements to current capabilities are provided through stabilizing. However, it helps to create value by enabling the company to hold onto its competitive edge over time. In the case of AI deployment, this could entail teaching machine learning to software developers or instructing analysts on how to make use of an interactive interface with the AI [ 15 ]. However, stabilizing may not be a good option in highly unpredictable environments because drastic and urgent adjustments may be required [ 104 ].
Combining resources to produce capabilities is the process of bundling resources. The mere possession of a resource does not confer an advantage. This refers to knowing the areas of application on which AI initiatives can be focused in the context of its utilization. Three subprocesses make up the bundling process: Stabilizing, enriching, and pioneering.
Releasing firm-controlled resources is referred to as divesting. Resources are few in businesses, therefore it is critical to free them up for other work. In order to develop AI capabilities, it is crucial to divest outdated systems and infrastructure, such as code written in less-preferred machine learning languages such as Python or R or computer clusters with insufficient processing capability [ 10 ]. Additionally, keeping vast amounts of low-value data, typically data used for forecasting or constructing models, simply complicates things for technical staff and uses up storage space [ 13 76 ]. It is crucial to meticulously account for each resource that is divested though, as it can be challenging to re-purchase or accumulate those resources in highly unpredictable circumstances. This applies to personnel with specific knowledge and skills and data and technology resources.
The creation of internal resources is what accumulation is all about. When businesses lack the necessary resources and are unable to adapt to changing market conditions, accumulation becomes important [ 105 ]. If not, it will be very challenging to fill the gap in time and produce gains when new opportunities arise or the environment is uncertain, such as when high-value employees leave the company [ 102 ]. As an example, the knowledge of developing AI systems or managing AI projects should be accumulated in an adequate number of employees increasing their tacit knowledge. As a result, business expertise, development information, and general know-how that exiting personnel had are not included in the company’s tacit knowledge, which could lead to gaps in producing the knowledge required for future development [ 43 ]. Compared to acquiring them from the factor market, being able to collect all pertinent data internally should be given priority in such efforts.
Acquiring in the context of artificial intelligence might mean either employing staff with in-depth expertise in AI systems or purchasing the necessary technological infrastructure, such as clusters with extremely high computation power [ 103 ]. This activity is essential for businesses that need to continuously develop and enhance their AI skills, especially if they are unable to outsource operations. Although expensive, an acquisition decision could strain the company’s budgetary management in an environment of high uncertainty [ 104 ]. Managers must use the new resources wisely by developing a new range of responses based on market prospects [ 105 ]. For instance, investing in an expensive dataset to supplement already-existing data sources could prove to be a dangerous move because the results might not be as anticipated.
The way a company structures its resource portfolio affects the tangible and intangible resources it has, which determines the potential value it may create at any specific time. Data, technology infrastructure, and people skills and expertise, as well as other intangible resources such as a culture of learning and initiative, are examples of such resources as aforementioned [ 81 ]. This procedure is crucial because it gives businesses the resources they need to develop new capabilities. This means that, in the context of AI, the types of AI-based capabilities that a company can develop (such as developing NLP tools, intelligent assistants, and forecasting) strongly depend on the data, infrastructure, competences, and other relevant resources that are widely obtainable [ 14 ].
Resource orchestration is a comprehensive method for organizing a company’s resources, grouping the current resources to produce new capabilities, and utilizing them with the aim of enhancing both business and customer value [ 102 ]. Structuring, aggregating, and leveraging are the three primary components, and as presented previously in Figure 3 , each component includes three subprocesses. Since the environment causes uncertainty, which could lead to instability for an organization and undermine its competitive edge over competitors, it has an impact on the linkages between resources that must be addressed seriously [ 103 ].
In more detail, data, technology, and basic resources are examples of tangible resources, which are defined as those that may be traded or purchased on the open market [ 93 ]. For instance, there are various categories of tangible resources, such as financial assets and physical assets such as debt and equity. As tangible resources are largely accessible to all businesses on the market, they are unlikely to offer a distinct competitive edge. However, while tangible resources are required, they are insufficient on their own to build capacities. Regarding the second group, an organization’s human capital is frequently evaluated by evaluating the knowledge, skills, experience, leadership traits, vision, communication and collaboration skills, and problem-solving prowess of its staff. Technical and business skills have been highlighted as crucial human resource pillars in previous studies on digital capabilities [ 93 97 ]. This study argues that technical and business capabilities specific to AI are two crucial elements of a company’s human AI resources. In relation to the third category, insecure and unstable marketplaces place a greater emphasis on intangible resources since those are harder for rival companies to reproduce [ 14 ]. Intangible resources are far more elusive and challenging to locate within organizations than the other two types of resources. Nevertheless, despite being challenging to quantify, they fall under the category of resources that satisfy the RBT’s VRIN (Valuable, Rare, Imperfectly Imitable, Non-Substitutable) classification [ 99 100 ]. As a result of their extreme heterogeneity and singularity, resources cannot be compared across firms. Because they are created through a special synthesis of organizational history, people, processes, and conditions that define organizations, intangible resources are heterogeneous and non-replicable. A lengthy history of empirical IS research [ 89 ] and early publications on the factors that influence AI success [ 5 33 ] emphasize the significance of intangible resources in gaining business advantages from accepted technology. Interdepartmental cooperation, organizational change capability, and risk proclivity are some of the resources that have been identified for AI [ 14 ]. Since managers and practitioners can create specific benchmark criteria and gauge their readiness in each of the dimensions, the RBT and the identification of key resources in the building of a capability are also significant perspectives for practice [ 101 ]. They can then identify possible flaws that can be resolved with focused efforts.
The studies mentioned so far, as well as a number of other academic papers and business reports, illustrate the diversity of resources that businesses must develop in order to realize a return on their investments in AI. However, theoretically valid research on how businesses might develop AI capabilities is lacking [ 14 ]. This is a critical gap for both research and practice since it may point to the main areas that businesses should concentrate on when implementing AI projects and give them a basis for estimating the potential business value and different generation mechanisms. Building on the theoretical foundations of the RBT [ 93 94 ] and empirical work implementing the RBT in the IS domain [ 91 97 ], as well as on recent studies that highlight the challenges related to AI adoption and value generation [ 5 98 ], Figure 3 presents the classification and the key types of resources in every category.
The many sorts of resources needed for the growth of organizational capabilities that drive performance have been outlined in a number of studies [ 95 ]. One of the most popular classifications is that offered by Grant [ 14 ], who distinguishes between tangible (such as material and financial resources), human abilities (expertise and skills of employees), and intangible (knowledge and skills of customers) (e.g., synergy, coordination, and strategic orientation). The IS literature makes considerable use of this division of resources into materials, human skills, and intangible resources [ 24 96 ]. To effectively leverage their investments and produce economic value, firms must create a special set of resources, as is the case with any new technology, including AI.
As previously indicated, the study by Mikalef and Gupta [ 14 ] seeks to investigate the resources needed to develop an AI capability by drawing on the resource-based theory (RBT) of the organization. The RBT is a suitable theoretical lens for dynamic and turbulent contexts, especially where resource complementarity is encouraged, and organizations create unique competencies around their respective resources. According to Melville et al. [ 89 ], the RBT enables researchers to create empirically testable hypotheses, the evaluation of which will increase our knowledge of the importance of various IT resources and how they impact organizational performance [ 43 90 ]. The RBT, according to Wade and Hulland [ 91 ], offers a solid framework for assessing the strategic value of information system resources. The fact that the RBT is a widely recognized theory in other business disciplines, such as operations management and marketing supply chain management [ 92 94 ], among others, demonstrates the RBT’s value in describing organizational-level events. As a result, Mikalef and Gupta [ 14 ] used current studies on AI in the organizational environment and previous work on IT competence to build the idea of an AI capability.
There is a paucity of knowledge regarding how AI resources or AI capabilities enable organizational business value, despite the existing literature discussing the construct of AI capability and the correlation between AI and business value [ 70 ]. As a result, in order to clarify the role of AI resources—the combination of AI assets and AI capabilities—in the development of business value and delve deeper into the topic of AI capabilities, an exploratory research study that adopts an interpretative approach is required. Despite the large potential that AI technologies hold, Brynjolfsson et al. [ 6 ] highlight that we are dealing with a modern productivity paradox. According to the authors, one of the main reasons AI has yet to deliver expected outcomes is due to implementation and restructuring lags. Organizations, therefore, need to invest in complementary resources to be able to leverage their AI investments. Understanding what complementary resources need to be developed and implementing them is imperative in the quest of realizing performance gains from AI. In other words, it is time to examine how organizations build an AI capability.
Additionally, the idea of an AI capacity has been put forward in earlier research to broaden the perspective on AI from just focusing on technical resources to also include all relevant organizational resources that are crucial for realizing the full strategic potential of AI [ 42 50 ]. According to research on AI capabilities, businesses need to have a few key resources in order to develop a capability that would allow them to adopt AI and reap performance advantages [ 14 74 ]. Organizations can incorporate AI-specific resources, such as AI algorithms, training data, etc., thanks to AI capabilities, which enable value generation. Sjödin et al. [ 87 ] analyzed case studies to examine how manufacturing companies create AI capabilities and discovered three key sets of capabilities: The data pipeline, algorithm development, and AI democratization. Through a thorough survey study, Mikalef and Gupta [ 14 ] came to the conclusion that by nurturing AI capabilities connected to human talents, tangible resources, and intangible resources, businesses could improve organizational innovation and performance. The survey’s list of AI resources driving AI capabilities was structured to investigate any extra or other significant aspects. Through exploratory interviews with professionals from business, consulting, and academia, Weber et al. [ 88 ] identified four organizational skills for AI implementation: AI project planning, the co-development of AI systems, data management, and AI model lifecycle management.
As AI is a novel technology, a greater number of research studies are being undertaken to determine the value that AI or its capabilities can bring to businesses. The main factors that influence the adoption of machine learning and top management support are uncovered by Reis et al. in [ 85 ]. Based on the mini-case studies of service provider websites, Wamba-Taguimdje et al. [ 16 ] investigated the connection between AI resources and business value. Alsheibani et al. [ 86 ] examined the issues surrounding the production of AI economic value by thoroughly reviewing real-world AI use cases and the body of prior research. They identified six AI-related organizational obstacles, including the business case for AI, the relative advantages of AI, top management support, efficient data utilization, AI talent, and AI compatibility. For the purpose of identifying the mechanisms generating AI business value, Enholm et al. [ 51 ] summarized the existing literature and provided a narrative review. They identified a number of AI use cases, facilitators, and barriers, as well as the effects of AI, particularly on competitive performance. As shown in prior studies, the introduction of AI technologies in itself is insufficient to increase organizational performance in a constantly evolving digital society, but their complementary interaction with knowledge exchange does.
Indeed, surveys have found that the biggest obstacle to the application of AI is a lack of AI capabilities [ 6 ]. Although most academics concur that AI capabilities are relevant, the respective literature does not give a clear definition of what AI capabilities are. For instance, several capabilities that are pertinent to the goal of integrating AI into a firm are mentioned in the managerial guidelines of Brock and Von Wangenheim [ 6 ]. These academics, however, take a rather broad stance, claiming that, in addition to data science and technological talents, the integration of AI calls for strategic competences. As a result, these publications’ depth of insight is restricted, especially considering that illustrating these skills was not their only, or even primary, goal. Researchers and practitioners are still unclear about the capabilities and underlying processes that are necessary in order for businesses to be able to fully utilize AI [ 33 84 ]. Profiting from a digital capability such as artificial intelligence “is not so much a technology challenge as it is a challenge to harness knowledge to create the organizational knowing to continually optimize the value that can be derived from digital technologies” [ 59 ].
The effects of AI on managers and businesses have just recently become particularly interesting research-wise [ 66 80 ]. Some initial studies have been conducted on AI-driven business models [ 81 ], AI-related organizational decision-making [ 9 61 ], and how businesses may promote AI trust [ 82 ]. The practice-oriented management literature frequently outlines procedures and actions supervisors can take to implement AI in their organizations [ 6 42 ]. There is broad agreement that the effects of AI encompass fundamentally new modes of corporate operation and expansion in addition to incremental process improvements. However, there is a shortage of research on how AI can be used to gain new skills and switch to business models that are powered by AI [ 10 ].
It is not an easy procedure to capture the value from both opposing modes of operation, i.e., routine vs. innovative application of AI, as they require different organizational routines, capabilities, and routines. Instead, it is suggested in the literature that big data and AI should be used as crucial organizational resources to enhance organizations’ dynamic capacities and enable them to utilize their full strategic potential [ 13 76 ]. Additionally, it is important to involve stakeholders to ensure their full engagement, and all employees must be committed to the new improvement projects and the organization-wide alignment with the strategic direction [ 77 ]. In order to achieve outstanding and long-lasting economic benefits and strong adaptive capacities, organizations must align “innovation” with “routine” at the same time [ 31 78 ].
AI ambidexterity, or the simultaneous adaptation of these two AI modes, enables businesses to sense their environment by examining real-time and large volumes of data, identifying and collecting customer needs and trends, discovering patterns, and extracting valuable data for decision-making processes [ 9 73 ]. According to [ 13 ], the ambidextrous use of AI in businesses will shape the organization’s dynamic capabilities as AI is used to address business problems, find innovative solutions, contribute to the success of business operations integration, and speed up change within the business [ 23 74 ]. Additionally, ambidexterity has been conceived in terms of temporal separation, which proposes that organizations should switch between periods of time that promote routine and standardization and times that prioritize creativity and exploration [ 75 ]. Last but not least, structurally divided ambidexterity relates to a dual organizational structure with entities (together with related systems, talents, and cultures) focusing on exploration and exploitation [ 21 ].
According to the ambidexterity theory, an organization’s strategic flexibility will result from placing an equal strategic focus on routine and innovative uses of AI [ 17 67 ]. The phrase “routine usage of AI” describes how an organization uses AI on a regular basis. As a result, this is seen as an exploitation and standardization posture that aims to enhance, expand, and promote incremental innovation in AI across a range of products and services a firm provides [ 19 20 ]. The routinized use of AI often entails standardizing working practices and operations using resources already at the disposal of the business (such as AI tools, frameworks, algorithms, and approaches) [ 68 ]. On the other hand, creative, emergent, and inventive use of AI in workers’ job processes is referred to as innovative application [ 69 70 ]. This perspective on AI application therefore stresses finding novel and creative methods to integrate AI into work processes [ 69 ], by offering wholly new or significantly improved client services. Additionally, the innovative application of AI is a catalyst for investigating and identifying new fields in which AI tools, applications, and uses can be implemented in business procedures [ 71 ]. This is accomplished, for instance, by starting a number of pilot programs and cutting-edge initiatives with AI at their core, learning from the outcomes, and then pushing the boundaries of organizational transformation [ 72 ].
As a result of these advancements, management academics are becoming increasingly intrigued by AI’s potential to assist or change firms [ 62 ]. However, while the use of AI algorithms is currently the subject of extensive research in a variety of functional areas, such as human resource management, marketing, information systems, economics [ 63 ], finance, operations management, and manufacturing, much less focus has been placed on comprehending how the advent of AI alters the nature of strategizing—that is, the activities of those involved in the strategy process [ 64 66 ].
Significant scientific progress has been made in the field of AI over the past ten years, which is defined as “a system’s ability to properly interpret external data, to learn from that data and to use this knowledge learned to accomplish specific objectives and tasks through flexible adaptation” [ 58 ]. Algorithms are already becoming able to digitally perform operations that effectively and productively imitate human learning, profound judgment, and decision-making across a wide range of application domains, driven by a rise in data generation and computation power [ 9 59 ]. Examples of such business applications include product design, the gathering of limited external knowledge, talent recruitment and screening, and internal business operation optimization [ 60 61 ]. The taxonomy of artificial intelligence techniques, however, is not generally agreed upon. The majority of AI techniques are grouped under the headings Fuzzy Logic (FL), Artificial Neural Networks (ANN), Expert Systems (ES), and AI-supported Meta-heuristics (MH) approaches in Figure 2 , which also presents the different types and applications of AI [ 27 50 ].
Thinking, understanding, interpretation, learning, judging, and inference are some of the numerous skills that make up intelligence. People are able to perform tasks such as learning from experience, creating answers to various and unknowable challenges they confront, and reacting as quickly as possible to a new scenario because of their intelligence [ 50 ]. The heart of AI methodologies consists of these actions. Artificial intelligence refers to a broad range of methodologies that can generate solutions with comparable designs to solve issues and attempt to replicate the intelligence of people or other living things in the computer environment. The success of these methods in solving problems that are NP (nondeterministic polynomial)-Hard, or extremely difficult to solve with conventional methods, is their greatest advantage in business and personal life.
4. Discussion
In order to help businesses align with their digital transformation and deliver improved business value outcomes, the integration of AI with business/IT strategies was the focus of this study. Artificial intelligence research is fundamentally sparked by digital transformation, extremely difficult problems, and businesses’ need to model and comprehend human behavior. The significance of management information systems, located at the intersection of information, business, and industry, has grown even more as a result of the fourth industrial revolution, particularly now that digitalization has grown into a necessity.
We conducted a systematic literature review using a particular technique that has been widely utilized in the past to investigate information systems strategy and subjects related to digital transformation. Our research indicates that an organization commonly undergoes a digital transition as a result of environmental technological developments. It is now urgently necessary for the organization to be able to connect with its surroundings and follow new regulatory frameworks. Simultaneously, the integration of AI capabilities with business/IT strategy has been highlighted as one of the key enablers of digital transformation alignment, which improves a variety of organizational business value outcomes. Specific difficulties, solutions, levers, and streams can be found in the context of responsible AI governance and the use of its ambidexterity in the development of AI capabilities. Anyhow, to be able to provide enterprises with a significant competitive edge, applied AI capabilities in conjunction with strategic flexibility unlock new routes of value creation that must be evaluated from various complex viewpoints.
The study’s findings present a more detailed picture of how AI affects organizations. Previous research has demonstrated how the application of AI can help organizations acquire the adaptive organizational capabilities necessary to increase operational efficiency. This study, which is in line with past studies, demonstrates the critical role AI capabilities play in enabling the integration of digital transformation alignment, which ultimately generates a competitive advantage. As a result, this study reveals the enablers and drivers for pursuing AI’s increased business value. This study also demonstrates that the synergistic ambidexterity effect outweighs the sole benefit of creative and consistent AI utilization. This result demonstrates the need for organizations to have a dual strategic focus on innovative and routine AI deployment, as these two essential facets of AI ambidexterity have a synergistic impact on the strategic flexibility of the organization.
Additionally, these revelations contribute to our understanding of the ways organizations must optimize their AI resources to promote strategic flexibility and benefit realization at the strategic level of the organization and contribute to the current body of knowledge on shaping and developing dynamic capabilities. Additionally, our current research suggests that by establishing digital skills that are challenging to compete with, businesses can traverse challenging and shifting business environments. Our research thus adds to the body of knowledge already in existence and satisfies the demand for additional fundamental studies on AI’s role in strategy. By doing this, we draw attention to how AI capabilities help businesses to be more adaptable. Additionally, the results of this study refute the notion that because AI has such a long life cycle, it is frequently monolithic and unable to adjust to changing surroundings. What is crucial, however, is for businesses to use AI to support adaptive transformation as opposed to impeding it.
In addition, the policies and objectives that define and steer the company strategy should take into account whether good AI governance has a direct impact on an organization’s results. The failure to comprehend how the unintended effects of an AI system could affect a firm’s overall competitive position is crucial to the creation and adoption of responsible AI regulatory frameworks that enhance economic value. Therefore, learning about and researching the proper operation of responsible AI governance frameworks could give businesses an advantage over their competitors. Managers who want to include ethical AI issues in their work must first understand what is required to do so before taking the necessary actions to create an ethical AI system. It is a significant task to reorganize organizational structures, allow a way for responsible AI research, and then implement management reforms to put new organizational practices into place in the absence of an AI governance framework.
Understanding that operational ambidexterity is driven by strategic flexibility, which leads to the simultaneous innovation and development of operational business systems and practices using digital technology, is another significant theoretical contribution. This result builds on previous research and demonstrates the critical role AI plays in attaining these operational gains. These findings can be used as a springboard and vision for IS and management researchers who want to look into the business usefulness of AI capabilities.
Numerous practical implications of this research are also present. First, policy makers need to make a concerted effort to invest in AI and highlight the creative and rather numerous ways it is already being used. The emergence of the strate
| 2023-02-14T00:00:00 |
2023/02/14
|
https://www.mdpi.com/2078-2489/14/2/85
|
[
{
"date": "2023/01/01",
"position": 59,
"query": "AI job creation vs elimination"
},
{
"date": "2023/01/01",
"position": 27,
"query": "AI economic disruption"
},
{
"date": "2023/01/01",
"position": 55,
"query": "AI labor union"
},
{
"date": "2023/01/01",
"position": 46,
"query": "artificial intelligence business leaders"
},
{
"date": "2023/02/01",
"position": 77,
"query": "AI job losses"
},
{
"date": "2023/02/01",
"position": 40,
"query": "workplace AI adoption"
},
{
"date": "2023/02/01",
"position": 62,
"query": "AI labor union"
},
{
"date": "2023/02/01",
"position": 83,
"query": "AI journalism"
}
] |
Artificial Intelligence in Nuclear Medicine: Opportunities ...
|
Artificial Intelligence in Nuclear Medicine: Opportunities, Challenges, and Responsibilities Toward a Trustworthy Ecosystem
|
https://pmc.ncbi.nlm.nih.gov
|
[
"Babak Saboury",
"Department Of Radiology",
"Imaging Sciences",
"Clinical Center",
"National Institutes Of Health",
"Bethesda",
"Maryland",
"Tyler Bradshaw",
"University Of Wisconsin Madison",
"Madison"
] |
by B Saboury · 2023 · Cited by 49 — The necessity of dealing with maladies has motivated physicians to incorporate inventions into medical practice to decrease or eliminate patient suffering.
|
Abstract Trustworthiness is a core tenet of medicine. The patient–physician relationship is evolving from a dyad to a broader ecosystem of health care. With the emergence of artificial intelligence (AI) in medicine, the elements of trust must be revisited. We envision a road map for the establishment of trustworthy AI ecosystems in nuclear medicine. In this report, AI is contextualized in the history of technologic revolutions. Opportunities for AI applications in nuclear medicine related to diagnosis, therapy, and workflow efficiency, as well as emerging challenges and critical responsibilities, are discussed. Establishing and maintaining leadership in AI require a concerted effort to promote the rational and safe deployment of this innovative technology by engaging patients, nuclear medicine physicians, scientists, technologists, and referring providers, among other stakeholders, while protecting our patients and society. This strategic plan was prepared by the AI task force of the Society of Nuclear Medicine and Molecular Imaging. Keywords: artificial intelligence, trustworthy, nuclear medicine, ecosystem
Medicine uses science, practical wisdom, and the best available tools in the art of compassionate care. The necessity of dealing with maladies has motivated physicians to incorporate inventions into medical practice to decrease or eliminate patient suffering. During the past two centuries, along with technologic revolutions, new medical devices have become the standard of care, from the stethoscope and electrocardiogram to cross-sectional imaging (Fig. 1). The stethoscope, which arose out of the first industrial revolution, is so pervasive that it has become the symbol of health-care professionals today. Compared with other medical equipment, it has the highest positive impact on the perceived trustworthiness of the practitioner seen with it (1).
FIGURE 1. Open in a new tab New technologies in medicine have coincided with each phase of industrial revolution. First industrial revolution was mechanization, with mechanical loom invented in 1784. The stethoscope was invented by René Laennec in 1816 and improved by Arthur Leared (1851) and George Philip Cammann (1852). Second industrial revolution was driven by advent of electricity, with the commercial light bulb (patented by Thomas Edison in 1879), telegram, and modern factory production line. Electrocardiogram was invented by Augustus Waller in 1887 by projecting the heartbeat captured by Lippmann capillary electrometer onto photographic plate, allowing heartbeat to be recorded in real time. Willem Einthoven (1895) assigned letters P, Q, R, S, and T to the theoretic waveform. Third industrial revolution, known as digital revolution, brought computing technology and refined it to personal computer. In 1960s, Kuhl and Edwards developed cross-sectional CT and implemented this in the SPECT scanner, which was later applied to CT scanner by Sir Godfrey Hounsfield and Allan Cormack in 1972. Fourth industrial revolution is that of modern day, with big data, hyperconnectivity, and neural networks, resulting in ability to propel self-driving cars and development of AI in nuclear medicine. CNN = convolutional neural network; IoT = Internet of things.
Nuclear medicine has always embraced the progress of technology. With the emergence of AI, we will again be poised to experience a modern renaissance, similar to the one experienced after David Kuhl’s and Roy Edwards’ groundbreaking work in the 1960s. By applying the concepts of radon transform through newly available computing technology, they introduced volumetric cross-sectional medical imaging with SPECT, which was subsequently followed by the development of x-ray–based CT and PET (2).
The past decades have seen tremendous advances in information technology and in its integration into the practice of medicine. The application of artificial intelligence (AI) to medicine represents the actualization of a new era. Such transformative technologies can affect all facets of society, yielding advances in space exploration, defense, energy, industrial processes, and finance; and even in cartography, transportation, and food service, among others.
The addition of AI into clinical practice in nuclear medicine poses opportunities and challenges. The full benefits of this new technology will continuously evolve. It is important to recognize that the nuclear medicine community must be actively involved to ensure safe and effective implementation. Establishing and maintaining AI leadership in the realm of nuclear medicine requires a comprehensive strategy to promote the application of innovative technology while protecting our patients and society, executing our professional and ethical obligations, and promoting our values. A potential advantage of deploying AI techniques is that nuclear medicine methodologies may become more widely available, increasing the access of patients to high-quality nuclear medicine procedures.
Nuclear medicine professional societies such as the Society of Nuclear Medicine and Molecular Imaging (SNMMI) and others provide leadership to ensure that we recognize the benefits of technologic advances in a manner consistent with our core values, medical ethics, and society’s best interests. In July 2020, the SNMMI formed an AI task force by bringing together experts in nuclear medicine and AI, including physicists, computational imaging scientists, physicians, statisticians, and representatives from industry and regulatory agencies. This article serves as both a strategic plan and a summary of the deliberations of the SNMMI AI task force over the past year in conjunction with other focused topics, including best practices for development (3) and evaluation (4) (Table 1).
TABLE 1. Opportunities and Challenges Ahead for Nuclear Medicine Toward Achieving Trustworthy AI Category Domain Subdomain Opportunities Diagnostic imaging Emerging nuclear imaging approaches RPTs AI-driven theranostic drug discovery and labeling Precision dosimetry Predictive dosimetry and digital twins Clinical workflow: increasing throughput while maintaining excellence Challenges Development of AI applications/medical devices Data Optimal network architecture Measurement and communication of uncertainty Clinically impactful use cases Team science Evaluation (verification of performance) Performance profiling through task-based evaluations Guidelines for validation Multicenter clinical trial network Ethical, regulatory, and legal ambiguities Ethical aspects Regulatory and legal aspects Implementation of clinical AI solutions and postimplementation monitoring AI platform Barriers of dissemination and implementation of AI technology in medicine Postdeployment: change management and performance Trust and trustworthiness Open in a new tab
NOTEWORTHY An appropriate AI ecosystem can contribute to enhancing the trustworthiness of AI tools throughout their life cycle through close collaboration among stakeholders.
A trustworthy medical AI system depends on the trustworthiness of the AI system itself, as well as the trustworthiness of all people and processes that are part of the system’s life cycle.
By encouraging the establishment of trustworthy AI in nuclear medicine, SNMMI aims to decrease health disparity, increase health system efficiency, and contribute to the improved overall health of society using AI applications in the practice of nuclear medicine.
OPPORTUNITIES Quantitative Imaging and Process Improvement Nuclear medicine is evolving toward even better image quality and more accurate and precise quantification in the precision medicine era, most recently in the paradigm of theranostics. Diagnostic Imaging AI techniques in the patient-to-image subdomain improve acquisition, and models in the image-to-patient subdomain improve decision making for interventions on patients (Fig. 2) (3). FIGURE 2. Open in a new tab From patient to image creation and back to physician, there are opportunities for AI systems to act at nearly any step in medical imaging pipeline to improve our ability to care for patients and understand disease (3). Image generation considerations are elaborated in the supplemental section “Opportunities,” part A (supplemental materials are available at http://jnm.snmjournals.org (5–40)); however, examples include improved image reconstruction from raw data (list-mode, sinogram); data corrections including for attenuation, scatter, and motion; and postreconstruction image enhancement, among others (41–43). These enhancements could impact PET and SPECT in clinical use today. Multiple–time-point acquisitions and PET/MRI may see improved feasibility. Specific opportunities in image analysis are elaborated in the supplemental section “Opportunities,” part B. A few examples include image registration, organ and lesion segmentation, biomarker measurements and multiomics integration, and kinetic modeling (44). Opportunities for clinical use of AI in nuclear medicine practice were extensively reviewed recently, including brain imaging (45), head and neck imaging (46), lung imaging (47), cardiac imaging (48,49), vascular imaging (49,50), bone imaging (51), prostate imaging (52), and imaging of lymphoma (53). Neuroendocrine tumors, other cancers (including gastrointestinal, pancreatic, hepatobiliary, sarcoma, and hereditary), infection, and inflammation are some examples of additional areas requiring further consideration. Emerging Nuclear Imaging Approaches New developments are also emerging such as total-body PET (54), which presents unique data and computational challenges. Another potential use of AI is to separate multichannel data from single-session multiisotope dynamic PET imaging. This pragmatic advancement could be valuable to extract greater phenotyping information in the evaluation of tumor heterogeneity (55). Radiopharmaceutical Therapies (RPTs) There are several areas in which AI is expected to significantly impact RPTs. AI-Driven Theranostic Drug Discovery and Labeling The use of AI for molecular discovery has been explored to select the most promising leads to design suitable theranostics for the target in question. For example, machine learning models could be trained using parameters from past theranostic successes and failures (e.g., partition coefficient, dissociation constant, and binding potential) to establish which best predict a given outcome (e.g., specific binding, blood–brain barrier penetration, and tumor-to-muscle ratio). New AI approaches are revolutionizing our understanding of protein–ligand interactions (56). New hit molecules (e.g., from the literature or high-throughput screens) can then serve as the test set in such AI models to speed up hit-to-lead optimization. Subsequently, with lead molecules identified, AI could also predict optimal labeling precursors and synthesis routes to facilitate fast and efficient development of theranostic agents (57,58). By defining parameters from existing synthetic datasets (e.g., solvents, additives, functional groups, and nuclear magnetic resonance shifts), models can be trained to predict radiochemical yield for a given substrate using different precursors and radiosynthetic methods. Subjecting new lead candidates as test sets in the models will enable rapid identification of appropriate precursors and labeling strategies for new theranostics, minimizing resource-intensive manual synthetic development. Precision Dosimetry The field of radiopharmaceutical dosimetry is progressing rapidly. After administration of radiopharmaceuticals, dynamic and complex pharmacokinetics results in time-variable biodistribution. Interaction of ionizing particles arising from the injected agent with the target and normal tissue results in energy deposition. Quantification of this deposited energy and its biologic effect is the essence of dosimetry, with opportunities to link the deposited energy to its biologic effect on diseased and normal tissues (Fig. 3). FIGURE 3. Open in a new tab Dosimetry as major frontier supported by AI toward personalization of therapy: various contributions by AI to image acquisition, generation, and processing, followed by automated dose calculations, can enable routine deployment and clinical decision support. TIAM = Time Integrated Activity Map. In dosimetry, SPECT serves as a posttreatment quantitative measuring device. One challenge is the difficulty for patients to remain flat and motionless on the scanning table for the required time. AI-based image reconstruction or enhancement methods can reduce the required SPECT scanning time for patients while maintaining or enhancing the accuracy of quantification (59) and enable attenuation correction in SPECT (60). Multiple steps in dosimetry potentially can be enhanced by AI methods, including multimodality and multiple–time-point image registration, segmentation of organs and tumors, time–activity curve fitting, time-integrated activity estimation, conversion of time-integrated activity into absorbed dose, linking macroscale dosimetry to microscale dosimetry, and arriving at comprehensive patient dose profiling (61). Predictive Dosimetry and Digital Twins Existing models can perform dosimetry before (e.g., 131I-metaiodobenzylguanidine) or after treatment. Personalized RPTs require predictive dosimetry for optimal dose prescription in which AI can play a role. Pretherapy (static or dynamic) PET scans could model radiopharmaceutical pharmacokinetics and absorbed doses in tumors and normal organs. Furthermore, it is possible to additionally use intratherapy scans (e.g., single–time-point SPECT in the first cycle of RPTs) to better anticipate and adjust doses in subsequent cycles. Overall, a vision of the future involves accurate and rapid evaluation of different RPT approaches (e.g., varying the injected radioactivity dose and rate, site of injection, and injection interval and coupling with other therapies) using the concept of the theranostic digital twin. The theranostic digital twin can aid nuclear medicine physicians in complex decision-making processes. It enables experimentation (in the digital world) with different treatment scenarios, thus optimizing delivered therapies. The opportunities discussed in the RPT section above are further described in the supplemental section “Opportunities,” part C. Clinical Workflow: Increase Throughput While Maintaining Excellence AI may impact operations in nuclear medicine, such as patient scheduling and resource use (62), predictive maintenance of devices to minimize unexpected downtimes, monitoring of quality control measurement results to discover hidden patterns and indicate potential for improvement, and monitoring of the performance of devices in real time to capture errors and detect aberrancies (62,63). These processes will make the practice of nuclear medicine safer, more reliable, and more valuable. Triage of urgent findings and augmentation of time-consuming tasks could improve the report turnaround time for the most critical cases and increase the efficiency of nuclear medicine physicians, allowing them to more effectively care for patients. It is important to ensure that AI systems in nuclear medicine are sustainable through developing new current procedural terminology codes and assigning appropriate relative value units for the technical and professional components. It is also possible that increased efficiencies in interpretation (more cases read accurately per unit time) may allow AI to be deployed into clinical workflows in an overall cost-effective manner.
AI ECOSYSTEM Actualization of Opportunities and Contextualization of Challenges Although early nuclear medicine AI systems are already emerging, many opportunities remain in which the continuous propagation of AI technology could augment our precision patient care and practice efficiencies. The environment in which AI development, evaluation, implementation, and dissemination occurs needs a sustainable ecosystem to enable progress, while appropriately mitigating concerns of stakeholders. The total life cycle of AI systems, from concept to appropriation of training data, model development and prototyping, production testing, validation and evaluation, implementation and deployment, and postdeployment surveillance, occurs within a framework that we call the AI ecosystem (Fig. 4). An appropriate AI ecosystem can contribute to enhancing the trustworthiness of AI tools throughout their life cycle through close collaboration among stakeholders. FIGURE 4. Open in a new tab AI ecosystem is a complex environment in which AI system development occurs. The ecosystem connects stakeholders from industry to regulatory agencies, physicians, patients, health systems, and payers. Proposed SNMMI AI Center of Excellence can serve as an honest broker to empower the AI ecosystem from a neutral standpoint with focus on solutions. ACE = SNMMI AI Center of Excellence; RIS = radiology information system.
CHALLENGES FOR DEVELOPMENT, VALIDATION, DEPLOYMENT, AND IMPLEMENTATION Development of AI Applications and Medical Devices Five challenges that should be addressed include availability of curated data, optimization of network architecture, measurement and communication of uncertainty, identification of clinically impactful use cases, and improvements in team science approaches (supplemental section “Development Challenges”). Evaluation (Verification of Performance) Theories on appropriate evaluation of AI software are a broad and active area of current investigation. Establishing clear and consistent guidelines for performance profiling remains challenging. Most current verification studies evaluate AI methods on the basis of metrics that are agnostic to performance on clinical tasks (64). Although such evaluation may help demonstrate promise, there is an important need for further testing on specific clinical tasks before the algorithms can be implemented. Failure-mode profiling is among the most important challenges (supplemental section “Evaluation Challenges”). Ethical, Regulatory, and Legal Ambiguities Major ethical concerns include informed consent for data use, replication of historical bias and unfairness embedded in training data, unintended consequences of AI device agency, the inherent opaqueness of some algorithms, concerns about the impact of AI on health-care disparities, and trustworthiness (supplemental section “Ethical, Regulatory, and Legal Ambiguities”). AI in nuclear medicine has limited legal precedent (65). Implementation of Clinical AI Solutions and Postdeployment Monitoring The lack of an AI platform integrating AI applications in the nuclear medicine workflow is among the most critical challenges of implementation (66). Barriers of dissemination can be categorized at the individual level (health-care providers), at the institutional level (organization culture), and at the societal level (67). Deployment is not the end of the implementation process (supplemental section “Implementation of Clinical AI Solutions and Post-Deployment Monitoring”).
TRUST AND TRUSTWORTHINESS In medicine, trust is the essence, not a pleasance. Successful solutions to the above-mentioned challenges are necessary but not sufficient for the sustainability of AI ecosystems in medicine. Well-developed and validated AI devices with supportive regulatory context, appropriate reimbursement, and successful primary implementation may still fail if physicians, patients, and society lose trust because of lack of transparency and other critical elements of trustworthiness such as perceived inattention to health disparity or racial injustice. In a recent survey, Martinho et al. (68) found significant perceived mistrust among health-care providers with regard to AI systems and the AI industry while realizing the importance and benefits of this new technology. Responders also emphasized the importance of ethical use, and the need for physician-in-the-loop interactions with AI systems, among the other factors. There is a need for a comprehensive analysis of the AI ecosystem to define and clarify the core elements of trustworthiness in order to realize the benefits of AI in clinical practice.
RESPONSIBILITIES: TOWARD TRUSTWORTHY AI When the safety, well-being, and rights of our patients are at stake, SNMMI should be committed to support principles that are future-proof and innovation-friendly. The willingness of physicians and patients to depend on a specific tool in a risky situation is the measure of the trustworthiness of that tool (69). In the case of AI systems, that willingness is based on a set of specific beliefs about the reliability, predictability, and robustness of the tool, as well as the integrity, competency, and benevolence of the people or processes involved in the AI system’s life cycle (development, evaluation/validation, deployment/implementation, and use). A trustworthy medical AI system depends on the trustworthiness of the AI system itself, as well as the trustworthiness of all people and processes that are part of the system’s life cycle (Fig. 5). FIGURE 5. Open in a new tab Twelve core concepts critical to trustworthy AI ecosystems. Trustworthy medical AI systems require a societal and professional commitment to the ethical AI framework, which includes 4 principles rooted in the fundamentals of medical ethics: respect for patients’ and physicians’ autonomy, prevention of harm, beneficence to maximize the well-being of patients and society, and fairness. These principles should be observed in various phases of the AI system life cycle. In what follows, we outline 12 key elements that need to be consistently present in AI systems. 12 Key Elements of Trustworthy AI Systems Human Agency AI systems should empower physicians and patients, allowing them to make better-informed decisions and foster their autonomy (70). Effects of the AI algorithms on human independence should be considered. It should be clear to patients and physicians the extent to which AI is involved in patient care and the extent of physician oversight. There must be checks to avoid automation bias, which is the propensity of humans to value and overly rely on observations and analyses from computers over those of human beings (71). Oversight There must be sufficient oversight of AI decision making, which can be achieved through human-in-the-loop and human-in-command approaches (72). AI systems that are involved in higher-risk tasks (e.g., those that drive clinical management and diagnose or treat disease) must be closely monitored through postmarket surveillance by independent professional credentialing organizations analogous to certification and recertification of medical professionals. Peer review processes in practices can be adapted to consider the combined physician–AI decision-making process. Technical Robustness AI systems must perform in a dependable manner (sufficient accuracy, reliability, and reproducibility) (73). This performance should be resilient to the breadth of clinical circumstances related to their prescribed use (generalizability). The AI tool should explicitly convey a degree of certainty about its output (confidence score) and have a mechanism in place to monitor the accuracy of outputs as part of a continuous quality assurance program. Failure modes of the algorithm should be well-characterized, documented, and understood by users. Safety and Accountability According to the concepts of safety-critical systems (74), AI systems should prioritize safety above other design considerations (e.g., potential gains in efficiency, economics, or performance). When adverse events occur, mechanisms should be in place for ensuring accountability and redress. Vendors must be accountable for the claims made of their AI systems. Physicians must be accountable for the way in which AI systems are implemented and used in the care of patients. The ability to independently audit the root cause of a failure in an AI system is important. Protection must be provided for individuals or groups reporting legitimate concerns in accordance with the principles of risk management. Security and Data Governance AI systems must include mechanisms to minimize harm, as well as to prevent it whenever possible. They must comply with all required cybersecurity standards. There should be an assessment of vulnerabilities such as data poisoning, model evasion, and model inversion. Assurances should be made to mitigate potential vulnerabilities and avoid misuse, inappropriate use, or malicious use (such as a deep fake) (75). Predetermined Change Control Plan AI tools can be highly iterative and adaptive, which may lead to rapid continual product improvement. The plan should include types of anticipated modifications (software-as-a-medical-device prespecifications). There must be a clear and well-documented methodology (algorithm change protocol) to evaluate the robustness and safety of the updated AI system. The algorithm change protocol should include guidelines for data management, retraining, performance evaluation, and update procedures. Vendors should maintain a culture of quality and organizational excellence. Diversity, Bias Awareness, Nondiscrimination, and Fairness AI systems can be affected by input data maladies (incomplete data, inadvertent historically biased data), algorithm design insufficiencies, or suboptimal performance assessment or monitoring strategies. These issues may result in biases leading to unintended prejudice and cause harm to patients. Discriminatory bias should be removed from AI systems in the development phase when possible (67). AI system performance should be evaluated in a wide spectrum of diseases and in patients with a particular condition regardless of extraneous personal characteristics. No particular group of patients should be systematically excluded from AI device development. Patients who are underrepresented or have rare diseases should not be excluded from AI system development or evaluation—though such datasets will be sparse and most likely could be used in the evaluation of AI methods developed only in larger populations (for generalizability). Appropriate validation testing on standardized sets that incorporate patient diversity, including rare or unusual presentations of disease, are critical to evaluate the presence of bias in results regardless of the training data used (76). AI systems should be user-centric and developed with an awareness of the practical limitations of the physician work environment. Accessibility features should be provided to those individuals with disabilities to the extent necessary according to universal design principles. Stakeholder Participation Throughout the life cycle of an AI system, all stakeholders who may directly or indirectly be affected should actively participate to help, advise, and oversee the developers and industry. Participation of patients, physicians, and all relevant providers, health-care systems, payors, regulatory agencies, and professional societies is imperative. This inclusive and transparent engagement is essential for a trustworthy AI ecosystem. Regular clinical feedback is needed to establish longer-term mechanisms for active engagement. Transparency and Explainability Vendors should openly communicate how an AI system is validated for the labeled claim (purpose, criteria, and limitations) by describing the clinical task for which the algorithm was evaluated; the composition of the patient population used for validation; the image acquisition, reconstruction, and analysis protocols; and the figure of merit used for the evaluation (4,73). There must be appropriate training material and disclaimers for health-care professionals on how to adequately use the system. It should be clear which information is communicated from the AI system and which information is communicated by a health-care professional. AI systems should incorporate mechanisms to log and review which data, AI model, or rules were used to generate certain outputs (auditability and traceability). The effect of the input data on the AI system’s output should be conveyed in a manner whereby their relationship can be understood by physicians and, ideally, patients (explainability) in order to allow a mechanism to critically evaluate and contest the AI system outputs. For diagnostic applications, the AI system should communicate the degree of confidence (uncertainty) together with its decision. To the extent possible, in high-stakes tasks the use of black box AI systems without proper emphasis on transparency should be avoided (77). Sustainability of Societal Well-Being It is important to acknowledge that exposure to AI could negatively impact social relationships and attachment within the health-care system (social agency) (78). AI systems should be implemented in a manner that enhances the physician–patient relationship. AI systems should not interfere with human deliberation or deteriorate social interactions. The societal and environmental impact of an AI tool should be carefully considered to ensure sustainability. Health-care workers who are impacted by the implementation of AI systems should be given an opportunity to provide feedback and contribute to its implementation plan. Professional societies and training programs should take steps to ensure that AI systems do not result in deskilling of professionals, such as by providing opportunities for reskilling and upskilling. A new set of skills, including physician oversight and interaction with AI tools, will evolve and must be refined. Privacy AI systems should have appropriate processes in place to maintain the security and privacy of patient data. The amount of personal data used should be minimized (data minimization). There should be a statement on measures used to achieve privacy by design, such as encryption, pseudoanonymization, aggregation, and anonymization. Systems should be aligned with standards and protocols for data management and governance. Fairness and Supportive Context of Implementation Early development efforts can pose more risk to developers and consumers. To address liability concerns, there have been successful programs in other industries to encourage adoption of new technology and support consumer protection, such as for vaccines and autonomous vehicles (65).
STRATEGIES FOR SUCCESS Part 1: SNMMI Initiatives In July 2022, SNMMI created an AI task force to strategically assess the emergence of AI in nuclear medicine (supplemental section “SNMMI Initiatives”). An area of important focus was to designate working groups, such as the AI and dosimetry working group for predictive dosimetry and treatment planning. Part 2: SNMMI Action Plan The AI task force recommends the establishment of an SNMMI AI Center of Excellence to facilitate a sustainable AI ecosystem (supplemental section “SNMMI Action Plan”). A nuclear medicine imaging archive will address the need for meaningful data access. A coalition on trustworthy AI in medicine and society will address the need for an AI bill of rights (79). Part 3: SNMMI Recommendations Recommendations for the future are also provided in the supplemental section “SNMMI Recommendations.”
CONCLUSION There are immense and exciting opportunities for AI to benefit the practice of nuclear medicine. Meanwhile, there are challenges that must and can be addressed head-on. As current challenges are addressed and new AI solutions emerge, SNMMI and the nuclear medicine community have the responsibility to ensure the trustworthiness of these tools in the care of patients. We can all benefit from efforts to ensure fairness, inclusion, and lack of bias in the entire life cycle of AI algorithms in different settings. There are 3 levels of facilitation that can support and enable the appropriate environment for trustworthy AI. First, our community must establish guidelines, such as those referenced in this article, to promote the natural development of trustworthy AI. Second, we can facilitate trustworthy AI through an SNMMI AI Center of Excellence. Third, we can make trustworthy AI occur through active engagement and communicative actions. By encouraging the establishment of trustworthy AI in nuclear medicine, SNMMI aims to decrease health disparity, increase health system efficiency, and contribute to the improved overall health of society using AI applications in the practice of nuclear medicine.
DISCLOSURE The views expressed in this article are those of the authors and do not necessarily reflect the views of the U.S. government, nor do they reflect any official recommendation or endorsement of the National Institutes of Health. Helena McMeekin is a part-time employee of Hermes Medical Solutions, Inc. Sven Zuehlsdorff is a full-time employee of Siemens Medical Solutions, Inc. No other potential conflict of interest relevant to this article was reported.
| 2023-02-14T00:00:00 |
2023/02/14
|
https://pmc.ncbi.nlm.nih.gov/articles/PMC9902852/
|
[
{
"date": "2023/01/01",
"position": 89,
"query": "AI job creation vs elimination"
}
] |
Full summary of <Life 3.0: Being Human in the Age ...
|
Full summary of <Life 3.0: Being Human in the Age of Artificial Intelligence> (14 / 100)
|
https://9oelm.github.io
|
[
"Joel Mun"
] |
There are arguments between job pessimists and optimists on AI. pessimists ... and does NOT lead to the elimination of humanity. More research and ...
|
January 01, 2023
⏳ 18 min read
I noticed that my previous summaries are too comprehensive and inclusive, so from now on I will try to be more succinct. Here’s the summary for Life 3.0: Being Human in the Age of Artificial Intelligence by Max Tegmark. Initially, upon the introduction of ChatGPT and realizing how powerful this is, I was curious if my job is really going to disappear in the future, and if so, how and when. I also wanted to know how difficult it is and what is required to build a general AI that knows and learns about general human behavior and needs. In essence, I was in a deep search of the progression and potential of AI towards the future.
Chapter 1. Welcome to the Most Important Conversation of Our Time
Life: “a process that can retain its complexity and replicate”
Life 1.0, 2.0 and 3.0 1.0 (bio stage): life where both the hardware and software are evolved rather than designed. Example: bacterium an algorithm is hard-coded into the DNA of a bacterium. Takes a long time for natural selection and evolution 2.0 (cultural stage): life whose hardware is evolved, but whose software is largely designed by the life itself. Example: mankind can gradually design the software by learning over time still limited by hardware: can’t grow as tall as we want or get a brain as big as we want 3.0 (tech stage): life that dramatically redesigns not only its software, but its hardware as well, rather than having to wait for it to gradually evolve over generations.
Different schools of thought on when the artificial general intelligence will happen, and whether it will be good
Digital Utopianism : digital life is the natural and desirable next step in the cosmic evolution if we let digital minds be free rather than try to stop or enslave them, the outcome is almost certain to be good. Life 3.0 is likely to be made possible in this century
Techno-skeptics : building superhuman AGI is so hard that it won’t happen for hundreds of years, and therefore view it as silly to worry about it now.
The Beneficial-AI Movement : mainstream in academia (the author shares this view) Life 3.0 is likely to be made possible in this century Since a good outcome is not guaranteed, AI needs to be carefully designed and researched
Chapter 2. Matter Turns Intelligent
intelligence = ability to accomplish complex goals
intelligence can’t be measured by a single IQ but an ability spectrum across all goals a narrow AI trained on chess can’t do anything on the game of Go, for example today’s AI is mostly narrow, whereas human intelligence is broad and general
but AI is growing fast. If AI is the sea and human competence is a land with hills, the sea level has been consistently rising Now the flood has reached the foothills, and our outposts there are contemplating retreat overcoming all hills will happen with “universal intelligence” where given enough time and resources, it can make itself able to accomplish any goal as well as any other intelligent entity (including machines themselves)
memory, computation, learning, and intelligence are substrate-independent: able to take on a life of their own that doesn’t depend on or reflect the details of their underlying material substrate. for example, when two programmers talk about code, they don’t talk about how transistors work this is similar to the idea of abstraction
A neural network is a good substrate for learning because it becomes good at computation by learning with relatively little resource
If AI progress continues, then long before AI reaches human level for all skills, it will give us fascinating opportunities and challenges involving issues such as bugs, laws, weapons and jobs—which we’ll explore in the next chapter.
Chapter 3. The Near Future: Breakthroughs, Bugs, Laws, Weapons and Jobs
Breakthroughs
AI has demonstrated major breakthroughs in complex problems including Atari games and traditional board games, notably the game of Go
Intuition, creativity and strategy
AlphaGo’s complete triumph over Sedol Lee was not anticipated by numerous experts, but it happened
Intuition and creativity are two core human traits and AlphaGo was able to display both.
and are two core human traits and AlphaGo was able to display both. If AI can beat the best Go strategists, there’s nothing stopping it from outperforming human investment, political, military strategists
Opportunities and challenges
There’s no fundamental reason why this progress can’t continue until AI matches human abilities on most tasks.
We’ve seen that it’s getting progressively harder to argue that AI completely lacks goals, breadth, intuition, creativity or language—traits that many feel are central to being human.
Bugs: it’s important to be proactive than reactive on bugs because heavier reliance on AI means more serious consequences if something goes wrong. Four main areas of technical AI-safety research: verification, validation, security and control.
Laws: robojudges can be more impartial and efficient than human judges in principle. The extent to which they have an impact on the legal system must be determined. Legal controversies lie in privacy vs freedom of information and giving rights to machines themselves like humans.
Weapons: AI weapons would be deadly if buggy, without any human intervention. Another problem is whether to start a global AI arms race or to prevent it from starting. But there’s less agreement about what precisely should be banned and how a ban would be enforced. Killer robots may be made ethical, but it remains a question as to what it really means to be ethical.
Jobs and wages: most people are earning more on an absolute scale, but income inequality has grown larger, probably due to technology.
Jobs
For this section, I intend to be a little bit more detailed due to my personal interest in the job prospects under the strong influence of the AI empire.
Obviously, choose the professions that machines are currently bad at, and seem to unlikely to get automated in the near future
Some criteria: Does it require interacting with people and using social intelligence? Does it involve creativity and coming up with clever solutions? Does it require working in an unpredictable environment?
This means that relatively safe bets include becoming a teacher, nurse, doctor, dentist, scientist, entrepreneur, programmer, engineer, lawyer, social worker, clergy member, artist, hairdresser or massage therapist. In contrast, jobs that involve highly repetitive or structured actions in a predictable setting aren’t likely to last long before getting automated away.
Many jobs won’t get entirely eliminated but have many tasks automated. If you go into law, don’t be the paralegal who reviews thousands of documents for the discovery phase and gets automated away, but the attorney who counsels the client and presents the case in court.
There are arguments between job pessimists and optimists on AI.
pessimists: an ever-larger number of people will become not only unemployed, but unemployable. The kinds of work that humans are more efficient at will soon be conquered by AI.
optimists: the automated jobs will be replaced by new ones that are even better, which is what’s always happened before, as in Industrial Revolution and so on.
Dealing with demise of most jobs: giving people income without jobs
Providing people with both income and purpose without jobs should be doable. income: basic income, or governments intentionally hiring people in place of AI. Also, income for a decent life is generally dropping. But redistribution of income requires a general consensus among the members of the society. purpose: jobs provide people with purpose: friends, colleagues, lifestyle, respect, self-esteem, sense of being needed, and so on. To create a low-employment society that flourishes rather than degenerates into self-destructive behavior, we therefore need to understand how to help such well-being-inducing activities thrive.
In summary, there’s absolutely no guarantee that we’ll manage to build human-level AGI in our lifetime—or ever. But there’s also no watertight argument that we won’t.
Chapter 4. Intelligence Explosion?
Human-level AGI may or may not be possible, but if we succeed at some point, it will trigger an intelligence explosion: human-level AGI creates superintelligence.
If humans control intelligence explosion, they would take over the world in a few years.
If AI itself leads the intelligence explosion, it will take over the world even faster. For superintelligence, humans would be five year old kids keeping it in a jail.
A quick intelligence explosion occurring in a matter of days would probably lead to a single, unipolar world power
A slow intelligence explosion over decades will lead to multipolar world powers because tech develops over time, providing people with a room to catch up with the frontrunners
Superintelligence could enable coordination on ever-larger cosmic scales.
Cyborgs and uploads (emulations) are probable, but it is an unpopular opinion among scholars that it is the quickest route to supperintelligence
We need to start thinking hard about which outcome we prefer and how to steer in that direction, because if we don’t know what we want, we’re unlikely to get it
Chapter 5. Aftermath: The Next 10,000 Years
Honestly, this chapter was quite uninteresting to me because it explains different types of aftermath scenarios following the advancement in AGI. So I am just going to copy and paste the summary from the book:
Superintelligence can peacefully coexist with humans either because it’s forced to ( enslaved-god scenario ) or because it’s “friendly AI” that wants to ( libertarian-utopia, protector-god, benevolent-dictator and zookeeper scenarios ).
) or because it’s “friendly AI” that wants to ( ). Superintelligence can be prevented by an AI ( gatekeeper scenario ) or by humans ( 1984 scenario ), by deliberately forgetting the technology ( reversion scenario ) or by lack of incentives to build it ( egalitarian-utopia scenario ).
) or by humans ( ), by deliberately forgetting the technology ( ) or by lack of incentives to build it ( ). Humanity can go extinct and get replaced by AIs ( conqueror and descendant scenarios ) or by nothing ( self-destruction scenario ).
) or by nothing ( ). There’s absolutely no consensus on which, if any, of these scenarios are desirable, and all involve objectionable elements. This makes it all the more important to continue and deepen the conversation around our future goals, so that we don’t inadvertently drift or steer in an unfortunate direction.
Chapter 6. Our Cosmic Endowment: The Next Billion Years and Beyond
Who said Max is not a physicist. He now explores possibilities and challenges with our cosmic endowment through the lens of physics, given the hypothetical breakthroughs in AGI and thus limits to the overwhelming technological advancement.
Making the most of your resources: from the PoV of physicist, anything made up of atoms or quarks and electrons are resources. Advanced tech can rearrange it into any other substances to facilitate process/communication/any other goals. One way to gain and take advantage of vast amount of energy is to build a Dyson sphere.
Inefficiency: we are still very bad at being efficient with resources. Digesting a candy bar is 0.000000001% efficient, burning coal 0.00000003%, and most other daily things we do. We can be much more efficient with making use of advanced technology like sphaleron process and cosmic resources like black holes, quasars.
Bounded by spacetime: the infinite Universe doesn’t mean we can see or travel to the edge of it because we are limited by the speed of light.
Controlling with the carrot: information will have value among commodities if any, and will be transmitted at the speed of light.
When civilizations clash: clash is deemed to be unlikely because of low possibility of discovery of another civilization, similar intelligence levels of superintelligence, and aligned goals. It would be more of a persuasion or assimilation than a clash because it is more efficient for expansion.
life still has the potential to flourish on Earth under enough caution and planning
Chapter 7. Goals
To think more about goals in relation to AI, we need to get a in-depth look at what a goal is.
Physics: the origin of goals. In all laws of classical physics, the nature prefers the optimal way - minimizing or maximizing some quantity. This is hardwired to the nature. We can call this behavior goal-oriented (towards optimization). Another goal could heat death, which is the maximally messy end state of something, uniformly spread out. Observation of gravity and thermodynamics suggests our goal is not only about the hopeless heat death.
Biology: the evolution of goals. Reproduction was the dominant goal in the throughout the Darwinian evolution. Most efficient copiers outcompete others. But the fundamental goal of dissipation has not changed, because the goal of replication aids in dissipation (planet with lives is more efficient at dissipating energy). Today’s humans act upon bounded rationality by deciding actions based on a few rules of thumb.
Psychology: the pursuit of and rebellion against goals. The rules of thumb can be said to be feelings. Feelings help a brain quickly make a decision. Our brain rebels against our genes and can make us consciously reject the goal of replication. With our brains, the ultimate authority is our feelings, not our genes.
Engineering: outsourcing goals. Machines, if designed to operate in a certain way, they can exhibit goal-oriented behavior (or design). Overall, the Earth is flourishing with goal-oriented machines possibly surpassing the magnitude of goal-oriented entities found from the nature. Evolved entities like machines can have more diverse, complex, arbitrary goals. Due to bounded rationality of these entities, sometimes their goals are not aligned with ours.
Friendly AI: Aligning goals. A friendly AI is an AI whose goals are aligned with ours. This is important because a supperintelligence will be so good at accomplishing goals, which would be disastrous if not aligned with ours. Achieving human goals by inferring from human behavior is fairly complicated. Whatever the goal of a superintelligence is, we can guess its subgoals that the original goal entails. A sheep-saving robot would rescue no more sheep if it runs into the bomb, so it has an incentive for self-preservation as a subgoal. Growing intelligence poses a danger to retaining the the original goal
Ethics: choosing goals. Whose goal among humans’ to follow? There has only been a general consensus on underlying principles on ethics: utilitarianism, diversity, autonomy, and legacy. But these principles carry their own problems too.
Ultimate goals: this is an open-ended question - how to define an ultimate goal for a superintelligence that is NOT undefined and does NOT lead to the elimination of humanity. More research and discussion is needed on the philosophy and ethics.
Chapter 8. Consciousness
Need to know what defines the consciousness of a machine or any entity
What is consciousness?: Broad definition of consciousness = subjective experience. No need for behavior, perception, self-awareness, emotions or attention.
What’s the problem?: Why is self-driving car deemed to be unconscious, while a driving person conscious? Experiencing driving is separate from colors, sounds, emotions, a and a feeling of self. Then why is a person, a set of re-arranged particles of nothing significant, conscious and if so, why not machines?
Is consciousness beyond science?: Any theory predicting which physical systems are conscious is scientific (the pretty hard problem)
What behaviors are conscious: although we are conscious, we ignore most parts of the sensory inputs and selectively focus on a few of them.
Where is consciousness?: organs responsible for taking the sensory inputs are not only related to consciousness. Retina takes the same input on visual tricks, but the brain thinks differently as it looks at them. Hunger and nausea don’t stem from the stomach but the brain.
When is consciousness?: human consciousness lives in the past by a quarter second. Reflexes are unconscious.
How might AI consciousness feel?: it’s impossible to answer this question fully with the state-of-the-art theories.
Meaning: the future of intelligence is important, but the future of consciousness is ever more important than that because it gives meaning. Without consciousness, there is no meaning. If machines get smarter than us, we need to value the ability to subjectively experience qualia more than the ability to think intelligently.
Thoughts
| 2023-01-01T00:00:00 |
2023/01/01
|
https://9oelm.github.io/2023-01-01-Life-3-0-being-human-in-the-age-of-artificial-intelligence/
|
[
{
"date": "2023/01/01",
"position": 90,
"query": "AI job creation vs elimination"
},
{
"date": "2023/01/01",
"position": 51,
"query": "artificial intelligence wages"
}
] |
Artificial Intelligence and Ten Societal Megatrends
|
Artificial Intelligence and Ten Societal Megatrends: An Exploratory Study Using GPT-3
|
https://www.mdpi.com
|
[
"Haluza",
"Jungwirth",
"Daniela Haluza",
"David Jungwirth"
] |
by D Haluza · 2023 · Cited by 165 — In this study, we hypothesized that AI can be used to address challenges and opportunities presented by global megatrends and discussed how it can potentially ...
|
Exploratory research is commonly employed to study an issue that lacks a clear definition, e.g., by Atwal et al., for the case of AI use in the wine industry [ 13 ]. It aims at gaining a more comprehensive view of the issue at hand, but it does not yield definitive conclusions. In this study, we hypothesized that AI can be used to address challenges and opportunities presented by global megatrends and discussed how it can potentially shape the future of our society [ 14 ]. We followed an exploratory research design to uncover GPT-3’s viewpoint on the influence of AI within the specific ten societal megatrends it identified as most pertinent.
The identification of global megatrends is crucial in understanding the current state and future direction of society [ 1 2 ]. Due to the inherent complexity of how primary forces interact, AI can very likely improve our understanding of these megatrends by providing insights into how they develop over time and what solutions could be implemented. The importance of understanding and utilizing AI in relation to global megatrends cannot be overstated, as AI-based systems are already shaping the direction of industries, influencing societal values, and transforming policy decisions [ 10 ]. Therefore, research exploring the role of AI in tackling these megatrends from a societal point of view from the perspective of the AI GPT-3 can provide substantial insights to the field [ 11 ].
The current model of “text-davinci-003” utilizes a training dataset consisting of 45 million webpages, books, and other sources [ 11 ]. The training data is relatively recent, with approximately one-third of it being collected within the last two years prior to 2021. This provides the model with an up-to-date understanding of language and trends in modern society. Additionally, GPT-3 has been fine-tuned to understand both formal and informal language, offering more natural sounding text generation to better mimic human–human interaction and writing styles [ 8 ]. Earlier models, especially ChatGPT, provided sensible references; still, they were incorrect and mainly made up [ 12 ].
One area in which AI can make a significant impact is through the human interaction interface of chatbots. One that is currently being heavily used is GPT-3 (Generative Pre-trained Transformer 3) ChatGPT chatbot, the third version of OpenAI’s pre-trained transformer model for natural language processing (NLP) [ 9 ]. GPT-3 is an unsupervised transformer-based language model that uses deep learning techniques to generate human-like text when given a prompt or seed text [ 8 ]. Over many years, GPT-3 has been trained on vast amounts of text data from varying sources, including books, webpages, and conversations, and its focus is to learn how to predict the next sensible word and sentence in a sequence given a context. It performs well on tasks such as question answering, summarization, translation, and more without requiring any task-specific training data that other NLP models do [ 10 ].
Artificial intelligence (AI) can play a critical role in addressing several negative aspects of societal megatrends and carrying out previously typical human tasks [ 7 ]. AI is a broad term, containing a wide range of technologies, such as machine learning, deep learning, computer vision, natural language processing (NLP), robotics, or ML (machine learning), to learn from data without being explicitly programmed [ 8 ]. ML models are trained using sample data sets to recognize patterns and make predictions when presented with new data. ML typically is used for image classification, speech recognition, natural language processing (NLP), or other pre-defined problem areas.
Megatrends found on an international scale play a crucial role in shaping modern society in multiple dimensions [ 1 ]. They influence the emergence of new technologies, change the way we interact, and shift distribution of resources and wealth. Understanding these megatrends is essential for any society for addressing important issues such as inequality, health promotion, sustainability, and economic growth [ 2 6 ]. An example to illustrate the complexity of unpredictability of lists of megatrends is the invention of new umbrella terms such as digitainability as proposed by Ulrich Lichtenthaler, combining the societal megatrends digitalization and sustainability [ 3 ]. Those are two significantly different megatrends that are individually important, but their interaction with each other will likely become even more significant in the future. In particular, digitainability offers the opportunity to move beyond optimization and cost savings due to digitalization and sustainability initiatives to capture the cross-fertilization potential of these two megatrends for innovation and new business development.
In today’s rapidly evolving world, creating strategic plans and adapting to ever-changing trends cannot be a one-time exercise; instead, it needs to be an ongoing process of continuous monitoring, testing, assessing, implementing, and learning [ 1 ]. Modern organizational advances such as adaptive organizations, agility, continuous delivery and value stream orientation are continuous processes as well and are increasingly replacing traditional planning concepts such as roadmaps or waterfalls for several years of planning [ 5 ]. Increasingly, enabled cross-functional teams are sensing and responding according to ever-changing market needs and trends in short planning and delivery iterations of weeks instead of years. By recognizing global megatrends, individuals, organizations, and governments can better anticipate and adapt to changes in their direct social and political environment [ 3 4 ]. This allows them to make informed decisions and take proactive measures to mitigate potential negative impacts and capitalize on probable opportunities.
The constant interaction between the waves of primary forces creates new megatrends. Thus, any given list of megatrends is not exhaustive nor do the entries match with each other, because disruption continually spawns new ones at an ever-faster rate as the primary forces evolve [ 1 ]. In a 2016 paper, Reteif et al. suggested that the key megatrends from an environmental assessment perspective were demographics, urbanization, technological innovation, power shifts, resource scarcity, and climate change [ 4 ]. Methodically, they used a matrix analysis to manually identify megatrends that are listed in megatrend reports from prominent, mainly grey literature, not peer-reviewed sources, suggesting a certain level of consensus or at least convergence. A recent bibliographic analysis revealed that societal and technological megatrends could be organized around foresight and globalization, Industry 4.0 and IoT, digitalization, technology, AI, innovation, the future, as well as sustainability areas, while they could not identify a common list across scientific research [ 1 ]. Therefore, identification of megatrends highly depends on the retrieval and detection method, and high overlaps can be found in the scientific literature.
Megatrends are typically driven by major technological, demographic, economic, and societal changes [ 1 ]. While a regular trend is a pattern of change over a period of time, a megatrend is a long-term, large-scale pattern of change with a much more significant impact [ 2 ]. Additionally, trends are usually specific to a certain domain or industry and may be short-lived or have a limited impact, while megatrends are global in nature and shape direction for many years to come [ 1 3 ]. Primary forces, such as technological advancements, economic shifts, and demographic changes, can shape a megatrend by driving, accelerating, or enabling it to occur. They evolve in waves, and each one of them is disruptive in different ways. For example, a technological advancement such as the widespread adoption of smartphones has shaped the megatrend of increased connectivity and access to information [ 4 ]. Economic shifts, such as globalization or the rise of emerging markets, can also shape megatrends such as increased international trade or increased economic power in developing countries. Demographic changes such as population growth and aging can also shape megatrends such as urbanization and the increasing demand for healthcare services [ 2 4 ].
Finally, we asked the AI to generate a draft of an abstract for our research: “Can you please write a scientific abstract for our peer-reviewed research paper ‘An Artificial Intelligent’s view on benefits of AI on societal megatrends: GPT-3 case study’” ( Figure 2 ). As the AI does not remember the context of previous interactions, she mentioned other megatrends than the ones described before, as well as a wrongly described methodology in the abstract, which was neither helpful for us nor correct. Therefore, we asked again more specifically and with fine-tuned parameters: “Can you please write a scientific abstract for our peer-reviewed research paper ‘An Artificial Intelligent’s view on benefits of AI on societal megatrends: GPT-3 case study’, including research on the trends of digitalization, urbanization, globalization, climate change, automation, mobility, global health, aging population, emerging markets as well as sustainability? Please follow the structure of introduction, the sole method of interactions with GPT-3, results, discussion and conclusion and with a length of 250 words in total.”. The result matched and summarized the actual conducted research, and we accepted and used the GPT-3’s abstract suggestion unchanged as abstract for this research paper. Notably, we slightly modified the title of the article at a later stage to “Artificial Intelligence and ten societal megatrends: An exploratory GPT-3 study”.
The tool GPTZero released in January 2023 lacked scientific research and broad popularity when we wrote this paper [ 18 19 ]. Nevertheless, we employed this tool in addition to established plagiarism checks. When fed with the same content, 377 words from the “1. Digitalization” section, the tool diagnosed: “Your text is likely to be written entirely by AI”. GPTZero came to the same conclusion for the text of the tenth megatrend “Sustainability”, where we used different parameters for a more random text generation. As a further control, we provided the text of the introduction section up to the character limit of 5000 characters as input and received: “Your text is most likely human written but there are some sentences with low perplexities”. For example, it identified the section head “1. Introduction” as low perplexity. Although GPTZero was not the primary focus of our research article, we found that the outcomes were substantially correct.
When the outcome was generated, we verified samples of the AI generated content with the PlagScan tool [ 17 ] to check the plagiarism and copy–paste level with default parameters (“compare with web sources”, “check against the plagiarism prevention pool”, “sensitivity: medium”, “bibliography: consider text”, “citation level: reduce PlagLevel”, “Whitelist: none”). For the 377 words in the “1. Digitalization” section, we found a 3.4% plagiarism rate within 3 matches. The tool did not detect any plagiarism from online sources or other scientific journals indexed. The PlagScan internal database ‘Plagiarism Prevention Pool’, containing all sorts of ever-scanned documents, highlighted similarity levels with three such private documents. Only the following filling words and word groups were considered as ‘copied’ from those internal documents: “can be used to”, “it easier to”, “can also be used to provide”, “has the potential to” and “the way people”. Due to the full absence of scientific and online plagiarism, as well as the low degree of only 3.4% ‘internal document’ similarities, and the nature of those commonly used filling word groups, we accepted the text as a non-plagiarized representative sample of the manuscript, proper summary of several articles, or as original text content produced by GPT-3.
Next, after we received the AI answers on the first half of the megatrends, i.e., megatrend 1 to 5, we decided to change linguistic parameters for the second half in comparison to the so far generated texts. Therefore, we added a “frequence_penalty” of 0.5 to limit repeated text tokens within the same sentence as well as a “presence_penalty” of 0.5 to penalize new text tokens based on already existing text presences and increased “Best of” to 3, resulting in an automated best result selection out of three independent generation runs for the same prompt.
As generated or non-existing references are useless in a scientific research work and do not reflect good scientific practice, we decided to stop asking for references in our further requests. Instead, we checked and quoted responses with our own experience and literature research. Furthermore, we discovered that the AI did not follow our instructions on the desired word count.
First, we asked GPT-3 to select the ten most important societal megatrends of today’s society including quotable sources. Then, we raised a more detailed question for each of the listed megatrends, e.g., “Could you please indicate your view on Artificial Intelligence’s benefits towards the societal trend of ‘Digitalization’? Please summarize your conclusions with 500 words”. Regarding the quotes, we found that the AI, as a generative model, invented and generated non-existing references, which looked reasonable at first sight. An online search showed that only 1 out of 10 references were valid, four further could be considered as partly valid (e.g., with a wrong publication year, or a wrong URL link), and five were completely invalid and nonexistent (see Table 1 ).
As done traditionally with human contributors and with other research including an AI as co-author [ 15 ], we sought consent with GPT-3 to participate as co-author and submit this specific paper to a peer-reviewed journal [ 16 ]. As shown in Figure 1 , the AI provided clear consent and accountability (“Yes, I agree to contribute to the paper together with David Jungwirth and Daniela Haluza. As a co-author of the paper, I take accountability for any aspects of my work that are related to accuracy and integrity. To ensure this is done effectively, I will review all relevant data thoroughly before submitting it as part of the paper, and if any issues arise during the writing process then I will investigate them promptly in order to prevent potential inaccuracies or breaches in professional integrity.”), contributed significant parts to the manuscript—especially the results section, self-description with strengths and limitations, as well as the abstract—and, finally, the AI approved the compiled manuscript sections for submission. Following the stage-gate approach of the AI-co-authored paper by Singh et al. [ 10 ], we aimed for later evaluation of content relevance, the worthiness of co-authorship of the AI after its contribution, and our final decision for AI co-authorship or mentioning the AI in the acknowledgement section of this paper.
We interacted with the AI via OpenAI’s “playground” [ 11 ], where detailed model-selection and parameters such as randomness, maximum response length, diversity, wording frequency, and text presence penalties could be applied for prompts to GPT-3. Furthermore, the playground can show probabilities for certain words chosen. For this research work, we started with applying standard settings for our questions (randomness/temperature: 0.7, maximum length: 1000 tokens, top p nucleus sampling: 1, frequency penalty and presence penalty: 0, best of 1). GPT-3 with text-davinci-003 includes several areas of AI, in particular, strong NLP, transforming, as well as ML capabilities [ 11 ]. We refer to GPT-3 as “the AI” in the remainder of this article. When we asked for its gender, it considered itself female, which we will consider from this point onwards.
In this study, we worked with the “text-davinci-003” model, the most powerful and most expensive model developed on top of the GPT-3 platform of OpenAI [ 9 11 ]. In comparison with the “ChatGPT” model, which is optimized for “chatting with humans”, the “text-davinci-003” model does not remember texts and context from previous chats. It can perform any task that other GPT-3 models can perform as well and often delivers higher quality, longer consecutive output, and follows instructions better [ 9 ]. It offers an improved natural language understanding, providing better results for text generation tasks such as summarization, question answering, and handling large data sets, which form the core of this article. The usage of the transfer learning advantage, where the model could be fine-tuned to specific datasets and/or trained on various natural language processing tasks to produce more accurate results, was out of scope of this study. GPT-3 is not connected to the internet; instead, it solely relies on pre-training. This enables it to generate responses based on the context of the conversation, even though it does not have access to external information and online data from the internet. This is an important difference to the usual way we retrieve information nowadays with digital devices using popular search engines such as Google, Bing, or Ecosia.
3. Results
The following section shows the exact wording used by the AI to describe the ten megatrends, which the AI exposed upon request, namely digitalization, urbanization, globalization, climate change, automation, mobility, global health issues, aging population, emerging markets, and sustainability.
Digitalization
The concept of digitalization has been steadily gaining traction over the past few years, as the world continues to become increasingly reliant on technology. With this trend comes the potential to leverage artificial intelligence (AI) as a tool to make digitalization more efficient and effective. AI has the potential to revolutionize the way we interact with digital systems and the data they store, providing us with an unprecedented level of efficiency and accuracy. Digitalization is the process of transforming information into digital form, making it easier to store, access, and analyze. AI-driven digitalization can automate many of the processes involved in digitalization, from interpreting and organizing data to making decisions based on the data it has gathered. This automation can reduce the amount of time and resources needed to complete tasks and can also improve accuracy. For example, AI-driven digitalization can help to identify patterns in data, allowing for more accurate and timely decision-making. Additionally, AI can be used to automate processes such as customer service, allowing for faster and more efficient customer interactions.
The use of AI in digitalization also has the potential to improve security. AI can be used to detect anomalies in data, thereby helping to identify and prevent malicious activity. Additionally, AI can be used to automate security processes, making it easier to detect and prevent security breaches. AI can also be used to provide predictive analysis, allowing organizations to better anticipate potential security threats and respond quickly. AI has the potential to revolutionize the way people interact with digital systems. AI-driven digitalization can improve user experience, as it can provide more intelligent, personalized, and interactive experiences. AI can also be used to improve the efficiency of digital workflows, allowing for more efficient and accurate digital processes. Additionally, AI-driven digitalization can provide new insights into customer behavior, allowing organizations to better understand and serve their customers. Overall, AI has the potential to revolutionize digitalization and provide many benefits. By automating processes, increasing accuracy and efficiency, and improving the user experience, AI can help make digitalization more effective and efficient. AI can also help to improve security and provide new insights into customer behavior. AI-driven digitalization can thus provide many benefits to organizations, as well as individuals, making it an invaluable tool for digitalization.
2. Urbanization
Urbanization is a global process that is often seen as a synonym for modernization. It is the movement of people from rural to urban areas, resulting in the growth of cities and the decline of rural areas. Urbanization has been one of the most important trends of the past century, and it has had a great impact on many aspects of our lives. Artificial intelligence (AI) is a rapidly developing field of technology that has the potential to profoundly shape our lives. AI is the science of designing computer programs that can solve problems, learn, and interact with humans. AI has the potential to revolutionize how we live and work, and it could have a major impact on the process of urbanization. AI can help to reduce the cost of urbanization by automating many of the processes that go into the development of cities. This could include the construction of buildings, the coordination of traffic, the management of energy consumption, and the deployment of public services. AI can also help to improve the efficiency of urban planning and its implementation by providing more accurate data and more detailed analysis. In addition, AI can help to improve the quality of life in cities.
AI can be used to analyze data from various sources and identify patterns that can help to make cities more efficient, reduce crime, and improve public services. AI could also be used to improve the quality of healthcare, education, and other public services in cities. Moreover, AI can be used to develop new technologies that can help to improve the sustainability of cities, such as smart grids and intelligent transportation systems. AI can also be used to develop autonomous vehicles, which could help to reduce traffic congestion and improve safety. Finally, AI can be used to improve the security of cities. AI can be used to develop smart surveillance systems, which can detect suspicious activities and alert authorities. AI can also be used to detect cyber-attacks and protect citizens from potential threats. In conclusion, AI is a rapidly developing field of technology that has the potential to shape the process of urbanization. AI can help to reduce the cost of urbanization, improve the quality of life in cities, and develop new technologies that can help to make cities more sustainable and secure. AI can also be used to improve the efficiency of urban planning and its implementation, as well as to protect citizens from potential threats.
3. Globalization
The concept of “globalization” is one that has been around for centuries and has only recently become a popular topic in the realm of public discourse. Globalization is the process of increased interconnectedness of countries, societies, markets, and cultures around the world. As technology continues to advance, the world is becoming increasingly connected, and this presents both risks and opportunities. Artificial intelligence (AI) can be an incredibly useful tool in addressing the risks and opportunities associated with globalization and can be leveraged to create a more prosperous and equitable world. In terms of economic benefits, AI can be used to automate and streamline processes such as international trade, logistics, and financial services. Automation of these processes can reduce the costs associated with global transactions, making it easier and more efficient for businesses to trade and operate across borders.
AI can also be used to optimize supply chains, making them more efficient and cost-effective. In addition, AI algorithms can be used to analyze and predict global economic trends, allowing businesses to make more informed decisions and maximize their global market share. AI can also be used to promote greater global integration and foster collaboration between countries. AI-driven technologies, such as machine translation, can be used to bridge language and cultural barriers, allowing people from different countries to communicate and collaborate more effectively. AI can also be used to identify and mitigate conflicts between countries, allowing international collaborations to be conducted more seamlessly. In terms of social benefits, AI can be used to promote better access to global resources, such as education and healthcare. AI-driven technologies, such as voice recognition, can be used to provide accessible educational materials in multiple languages. AI can also be used to provide personalized healthcare services, allowing people from different countries to receive care that is tailored to their needs. AI can also be used to analyze global trends and identify areas where interventions are needed, such as poverty and inequality. AI also has the potential to create a more equitable world. By automating and streamlining processes, AI can reduce the costs associated with global transactions, making it easier and more cost-effective for people from different countries to access resources and services.
AI can also be used to analyze global data and identify areas where interventions are needed, allowing organizations and governments to better target initiatives and resources to areas that need it the most. In conclusion, artificial intelligence presents numerous benefits towards the societal trend of “Globalization”. AI can be used to reduce the costs associated with global transactions, optimize supply chains, analyze economic trends, bridge language and cultural barriers, and identify and mitigate conflicts between countries. AI can also be used to promote better access to global resources, such as education and healthcare, and create a more equitable world by targeting resources to areas that need it the most. AI can be a powerful tool in creating a more connected, prosperous, and equitable world.
4. Climate Change
The potential benefits of artificial intelligence (AI) in addressing the global challenge of climate change are massive and far-reaching. AI technologies can provide a powerful tool to help us better understand and manage the complex systems that make up our climate. AI can also help us develop strategies to reduce emissions and develop more efficient ways to produce energy and other essential resources. Using AI technologies, scientists can gain a better understanding of how climate change is affecting our planet. AI can provide insights into the underlying causes of climate change, such as greenhouse gas emissions, and help us better understand the various interactions between the Earth’s atmosphere, oceans, and land surface. AI can also help us analyze and predict the impact of climate change on the environment and our society. AI technologies can also be used to improve our ability to forecast the weather and climate. AI-based models can help us better understand the effects of global warming, as well as how climate change is likely to affect our environment and society in the future. For example, AI can be used to monitor and predict changes in the ocean currents, which can be used to prepare for future coastal flooding and other extreme weather events. AI can also be used to monitor changes in air temperature and air pressure, which can help us better manage our energy needs. AI can also be used to improve the efficiency of energy production.
AI-based technologies can be used to optimize energy production from renewable energy sources, such as wind and solar power. Additionally, AI can help us make better decisions about the use of energy resources, such as reducing emissions from our transportation systems and utilizing more efficient energy sources. AI can also help us manage our natural resources more efficiently. AI-based technologies can be used to monitor and manage the water and soil resources needed to produce food. AI can also be used to identify and monitor land resources that are important for preserving biodiversity. AI can also help us manage forests, wetlands, and other ecosystems to better protect our environment and reduce the impacts of climate change. In conclusion, AI has the potential to provide powerful tools to help us better understand and manage the complex systems that make up our climate. AI can also be used to improve the efficiency of energy production and help us better manage our natural resources. By utilizing the power of AI, we can develop strategies to reduce emissions and develop more efficient ways to produce energy and other essential resources. AI can also help us make better decisions about the use of energy resources and help us protect our environment from the impacts of climate change.
5. Automation
The potential benefits of artificial intelligence (AI) to automation are vast. Automation, which is the use of technology to reduce or eliminate human labor, is a major trend in society today. AI can help automate many of the processes that used to require human labor, freeing up resources for more creative and value-added activities. One of the most obvious benefits of AI to automation is cost savings. AI can be used to automate many processes that would otherwise require human labor, resulting in significant cost savings. Additionally, AI can enable companies to increase their output while reducing their costs, as AI systems can work much faster and more consistently than human labor. This can lead to higher profits and a more competitive edge in the marketplace.
AI can also help automate more complex processes, such as those requiring decision-making or data analysis. AI systems can quickly process large amounts of data, identify patterns, and make decisions based on the results. This can enable companies to quickly and accurately make decisions that would otherwise take much longer to make. AI can also help automate processes that require a degree of precision that would be difficult for humans to replicate. For example, AI systems can be used to automate tasks such as automated driving, which would require perfect accuracy from a human driver. This can reduce the risk of accidents and improve safety. AI can also help automate processes that require a high degree of specialization or expertise. AI systems can be trained to identify specific patterns or objects and then use those patterns or objects to perform specific tasks. This can enable companies to automate processes that would otherwise require highly skilled workers. Finally, AI can help automate processes that are time-consuming or tedious. AI systems can be programmed to perform tasks quickly, enabling companies to complete tasks faster and more efficiently. This can help companies increase their productivity and save time and money. In conclusion, AI has the potential to benefit automation and society in many ways. AI can help automate processes that would otherwise require significant human labor, resulting in cost savings and increased efficiency. Additionally, AI can automate more complex and time-consuming tasks, enabling companies to complete tasks faster and more accurately. AI can also help automate processes that require a high degree of specialization or expertise and can help automate tedious and time-consuming tasks. As AI continues to develop and become more sophisticated, the potential benefits of AI to automation will only increase.
6. Mobility
The rise of artificial intelligence (AI) has the potential to revolutionize the way we move around in our everyday lives. AI-powered mobility solutions such as self-driving cars, smart city traffic management systems, and intelligent transportation networks are transforming the way people travel and commute, resulting in a more efficient and sustainable urban environment. In this article, I will discuss some of the key benefits of AI-driven mobility solutions for society, with particular focus on how they can reduce congestion, improve energy efficiency, and increase safety. One of the biggest advantages of adopting AI-driven mobility solutions is their ability to reduce traffic congestion. By using real-time data to predict traffic patterns and optimize routes for drivers and passengers alike, AI can help people avoid congested areas or take alternate routes at peak times. This can drastically cut down on journey times and improve air quality by reducing emissions from idling vehicles. Similarly, AI systems can be used to monitor road usage levels and adjust speed limits accordingly, helping to keep roads flowing smoothly even during periods of high demand. Another benefit of AI-driven mobility solutions is improved energy efficiency.
Smart city traffic management systems powered by AI can help reduce fuel consumption by monitoring vehicle speed limits in different sections of a city or route network and adjusting them accordingly to ensure optimal fuel usage at all times. Intelligent transportation networks can also be used to optimize shipping operations by predicting delivery times accurately and helping drivers find the most efficient routes from point A to point B without wasting time or fuel. A further advantage is increased safety on roads due to AI-enabled automation systems that are able to detect potential hazards before they become an issue for drivers or pedestrians. For example, self-driving cars use advanced sensors and computer vision technology to recognize obstacles in their path ahead of time so that they can react quickly with minimal risk or harm involved. Additionally, features such as automated emergency braking systems equipped with cameras that detect when a pedestrian steps into a car’s path help prevent accidents before they occur—something that traditional human drivers would not be able to do alone.
In conclusion, it is clear that artificial intelligence has the power to revolutionize our current transportation system through its ability to reduce congestion levels on roads while improving energy efficiency and safety standards simultaneously. This could have a huge positive impact on both individual commuters as well as society at large by making cities smarter, more efficient places in which people can live safely and comfortably—something that is likely only achievable through the implementation of cutting-edge technologies such as those powered by artificial intelligence.
7. Global Health
The potential for artificial intelligence (AI) to improve global health is immense. AI has the potential to revolutionize medical research and clinical practice, allowing us to better understand human physiology and disease, develop novel treatments and diagnostic tools, and improve cost-effectiveness of health care delivery. In this way, AI can be a powerful force for improving global health outcomes. One key advantage of AI is its ability to quickly synthesize massive amounts of data from multiple sources, including electronic medical records, genomic data, imaging studies, and patient surveys. This enables researchers to more accurately identify patterns in disease progression and treatment outcomes. For example, AI can be used to identify biomarkers that can predict the risk of certain diseases or responses to treatments. This could lead to earlier diagnosis and improved prognoses for patients. AI can also be used in drug discovery research by analyzing data from pre-clinical trials or simulations of potential treatments as well as by providing insights into how drugs may interact with different types of cells or tissues. In addition to these research capabilities, AI has great potential in clinical practice.
By drawing on large datasets of patient information collected over time, AI algorithms can help physicians make diagnoses more accurately and efficiently than manual methods alone. AI could also provide clinicians with real-time alerts about changes in a patient’s condition or suggest personalized treatments based on individual characteristics such as age or lifestyle factors. This would allow for more tailored care plans that could reduce adverse events associated with unnecessary interventions or missed opportunities for preventive measures. Furthermore, by enabling automated administrative tasks such as appointment scheduling or billing management, AI could free up resources so that healthcare providers have more time for direct patient care. Finally, the use of AI in healthcare has the potential to reduce costs by streamlining processes across all aspects of healthcare delivery from diagnosis through treatment and discharge planning. Automation enabled by AI could reduce costly errors due to human error while increasing efficiency within healthcare systems overall, thus reducing waste due to inefficient resource allocation or duplication of services between providers without access to shared records.
Overall, the evidence suggests that artificial intelligence holds great promise for improving global health outcomes through enhanced research capabilities, improved clinical decision-making, better tailored care plans, automated administrative tasks, and reduced costs associated with inefficient resource allocation throughout the healthcare system. To realize this potential, however, further investment is needed in developing new algorithms capable of integrating complex datasets, ensuring secure access to patient data, training a new generation of clinicians comfortable working with machine learning tools, and designing systems that respect privacy while allowing access when appropriate for clinical purposes. With increased effort in these areas, we may soon see a future where artificial intelligence plays an integral role in helping us tackle some of our most persistent global health challenges.
8. Aging Population
The aging population is a megatrend that has been affecting societies around the world for years. With lifespans increasing, more and more people are living to an age where they require additional care, such as medical and social services. As the aging population continues to grow, so does the need for advanced technology to help meet their needs. Artificial intelligence (AI) can play a major role in helping to address this issue by providing innovative solutions that both improve quality of life and reduce costs associated with caring for an aging population. One way AI can help with the aging population is by creating automated systems that can provide better medical care and monitoring. AI-driven systems can be used to detect changes in a person’s health, monitor vital signs, and even diagnose diseases faster than traditional methods. This could lead to better outcomes for those who need medical treatment as AI-driven systems could provide earlier detection of issues before they become serious problems. Additionally, AI-driven systems will allow healthcare professionals to spend more time on important tasks such as patient care instead of paperwork or administrative tasks.
Another way AI can help with the aging population is by providing assistance with daily activities that may become difficult for elderly individuals over time. For example, AI-driven robots or virtual assistants can help seniors manage their medication schedules, perform light chores around the home, or even remind them when it’s time to take a break from daily activities. These types of assistive technologies could go a long way in helping seniors live independently longer while also reducing stress levels that come along with caring for an elderly individual. Finally, AI-driven systems can help reduce costs associated with caring for an aging population by automating processes such as insurance claims processing or administrative paperwork. By taking on these tasks, AI-driven systems will free up healthcare professionals’ time so they are able to spend more time on patient care while also reducing costs related to labor hours spent on these tasks manually. Additionally, AI-driven systems can analyze large amounts of data quickly and accurately, which could lead to improved diagnosis accuracy while also freeing up resources that would have otherwise been spent manually inputting data into spreadsheets or databases.
In conclusion, artificial intelligence has great potential when it comes to addressing the societal megatrend of an aging population due to its ability to automate processes while also providing better medical care and assistance with daily activities for seniors. Additionally, using AI-driven systems could save money by reducing labor costs associated with administrative tasks while improving accuracy when analyzing large datasets quickly and accurately. Therefore, if implemented properly, these technologies could greatly benefit individuals requiring additional care due to age while minimizing any negative impacts caused by growing populations of elderly individuals around the world.
9. Emerging Markets
The emergence of artificial intelligence (AI) has been a major boon for emerging markets, as its ability to automate processes and analyze large amounts of data creates huge opportunities for businesses, governments, and citizens in these countries. AI can be used to improve access to finance, increase agricultural productivity and efficiency, empower citizens with better healthcare, facilitate higher education access, and open up new markets. In terms of finance, AI-driven technologies such as robo-advisory services are helping provide more affordable and accessible financial services to those who may have previously lacked the resources or knowledge to access them. This is especially beneficial in emerging markets where banks may be less likely to offer financial services due to high risk or lack of trust. In addition, AI helps with credit scoring by providing data-driven insights into borrowers’ creditworthiness that are often not available through traditional methods. This allows lenders to make better decisions while also reducing the cost of doing business.
AI can also help increase agricultural productivity by providing farmers with real-time crop monitoring and automated irrigation systems. With automated irrigation systems, farmers can save time and money on labor costs while simultaneously improving their crop yields. Additionally, AI can help farmers make better decisions regarding fertilizer applications based on soil health analysis, which can further increase yield potentials while minimizing environmental impact. On the healthcare side, AI is helping reduce medical costs by automating administrative tasks such as scheduling appointments and managing patient records. It is also being used to diagnose diseases more accurately than ever before through image recognition technology, which can detect early signs of disease that may otherwise go unnoticed by human doctors. This helps ensure that patients receive prompt medical care, which in turn reduces treatment costs over time. Furthermore, AI-powered chatbots are making it easier for people living in remote areas with limited access to healthcare providers to obtain the information they need quickly and efficiently without having to leave their homes or wait in line at a hospital or clinic. AI-driven technologies are also facilitating higher education access in emerging markets by providing personalized learning experiences tailored specifically for each student’s needs and abilities as well as online courses that allow students from all over the world to learn together regardless of location or socio-economic status.
Finally, AI is opening up new markets by improving supply chain visibility through predictive analytics, which gives businesses greater insight into customer demands so they can plan accordingly for future product releases or adjust their production schedules when needed. This helps ensure that customers always have what they need when they need it while keeping company expenses down at the same time. Additionally, AI technologies such as natural language processing are making it easier for companies operating in different countries with different languages to communicate effectively with customers around the world, thus expanding their customer base beyond their local marketplaces.
In conclusion, AI is proving itself invaluable when it comes to empowering emerging markets both economically and socially through improved financial services access, increased agricultural productivity, improved healthcare, higher education access, and new market opportunities created by supply chain visibility enhancements, as well as language translation capabilities, among other things. Its potential is only just beginning to be realized but it is clear that this technology will continue playing an important role in helping developing countries reach their full potential going forward into the future.
10. Sustainability
Artificial intelligence (AI) has the potential to play a major role in advancing our planet towards a more sustainable future. AI can help us reduce our environmental impact by providing insights into how we can better use resources, increase efficiency, and create smarter solutions that are tailored to individual needs and preferences. AI-powered technologies can also help us optimize existing processes, such as manufacturing and transportation, while creating new opportunities for sustainable development. The most direct way that AI could contribute to sustainability is through its ability to analyze data and discover patterns that humans may not be able to detect. By using machine learning algorithms, AI systems can identify correlations between energy usage, emissions, resource consumption, and other factors, allowing us to make informed decisions about how best to use resources without wasting them. Additionally, AI-driven automation can help reduce the amount of time needed for manual tasks such as monitoring energy usage or managing supply chains. This can free up human labor for more creative endeavors and allow companies to focus on their core competencies instead of mundane tasks.
AI-based predictive analytics can also help us anticipate future problems and develop strategies for tackling them before they become unmanageable. For example, AI-driven forecasting tools could predict changes in weather patterns or natural disasters so that we could prepare before they occur and minimize their effects on our environment. Similarly, AI systems could be used to monitor water quality or air pollution levels in real time so that we could respond quickly if necessary. AI technology also has the potential to revolutionize renewable energy production. Smart grid technology powered by AI algorithms would enable us to better manage the electricity supply system by optimizing power generation from renewable sources such as solar or wind while minimizing waste from inefficient traditional sources such as coal plants. Additionally, autonomous aerial vehicles equipped with sensors could be used to collect data about renewable energy sources such as wind turbines or solar farms so that we could further optimize their performance over time without having to send people out into potentially dangerous conditions.
Finally, AI-powered chatbots and virtual assistants have the potential to provide users with personalized advice about ways they can improve their environmental footprint through sustainable living practices such as composting or energy saving measures such as turning off lights when leaving a room. By providing users with tailored suggestions about how they can reduce their environmental impact at home on a day-to-day basis, these virtual assistants could have an immense positive impact on global sustainability efforts over time.
Overall, artificial intelligence has great potential when it comes to helping progress society towards a more sustainable future. From analyzing data sets in order to identify trends and correlations related to resource consumption all the way up through predicting weather patterns or providing personalized advice about living sustainably at home, there is no doubt that AI technology will play an increasingly important role in promoting sustainability around the world in the years ahead.
| 2023-03-14T00:00:00 |
2023/03/14
|
https://www.mdpi.com/2079-8954/11/3/120
|
[
{
"date": "2023/01/01",
"position": 93,
"query": "AI job creation vs elimination"
},
{
"date": "2023/01/01",
"position": 16,
"query": "AI economic disruption"
}
] |
Reskilling for the Future of Work - Automation Anywhere
|
Reskilling for the Future of Work
|
https://www.automationanywhere.com
|
[] |
Discover Automation Anywhere's reskilling programs that prepare individuals for the digital future. Access free training and resources to enhance your ...
|
The fastest-growing roles relative to their size today are driven by technology and digitalization. As part of the reskilling revolution, we’re supercharging the skills of the global workforce to build a more equitable, inclusive future where everyone is prepared to take advantage of emerging careers.
We believe our accessible training curriculum and targeted social impact programs for automation and AI reskilling are unique. In partnership with nonprofits, companies, and workforce development organizations, we’re working to remove the barriers for groups who normally have no access to training like ours around the world, whether in the US, the Indian subcontinent, or Africa.
| 2023-01-01T00:00:00 |
https://www.automationanywhere.com/company/global-impact/reskilling
|
[
{
"date": "2023/01/01",
"position": 9,
"query": "reskilling AI automation"
},
{
"date": "2023/02/01",
"position": 10,
"query": "reskilling AI automation"
},
{
"date": "2023/04/01",
"position": 11,
"query": "reskilling AI automation"
},
{
"date": "2023/05/01",
"position": 11,
"query": "reskilling AI automation"
},
{
"date": "2023/10/01",
"position": 11,
"query": "reskilling AI automation"
},
{
"date": "2023/11/01",
"position": 10,
"query": "reskilling AI automation"
},
{
"date": "2024/03/01",
"position": 19,
"query": "reskilling AI automation"
},
{
"date": "2024/04/01",
"position": 10,
"query": "reskilling AI automation"
},
{
"date": "2024/05/01",
"position": 10,
"query": "reskilling AI automation"
},
{
"date": "2024/06/01",
"position": 10,
"query": "reskilling AI automation"
},
{
"date": "2024/07/01",
"position": 9,
"query": "reskilling AI automation"
},
{
"date": "2024/10/01",
"position": 10,
"query": "reskilling AI automation"
},
{
"date": "2024/11/01",
"position": 10,
"query": "reskilling AI automation"
},
{
"date": "2025/02/01",
"position": 11,
"query": "reskilling AI automation"
},
{
"date": "2025/04/01",
"position": 10,
"query": "reskilling AI automation"
},
{
"date": "2025/06/01",
"position": 8,
"query": "reskilling AI automation"
}
] |
|
Reskilling in the Age of AI - Article - Faculty & Research
|
Reskilling in the Age of AI
|
https://www.hbs.edu
|
[] |
In the coming decades, as the pace of technological change continues to increase, millions of workers may need to be not just upskilled but reskilled—a ...
|
Abstract
In the coming decades, as the pace of technological change continues to increase, millions of workers may need to be not just upskilled but reskilled—a profoundly complex societal challenge that will sometimes require workers to both acquire new skills and change occupations entirely. Companies have a critical role to play in addressing this challenge, but to date few have taken it seriously. To learn more about what their role will entail, the authors—members of a collaboration between the Digital Data Design Institute at Harvard’s Digital Reskilling Lab and the Boston Consulting Group’s Henderson Institute—interviewed leaders at some 40 organizations around the world that are investing in large-scale reskilling programs. In synthesizing what they learned, they became aware of five paradigm shifts that are emerging in reskilling: (1) Reskilling is a strategic imperative. (2) It is the responsibility of every leader and manager. (3) It is a change-management initiative. (4) Employees want to reskill—when it makes sense. (5) It takes a village. The authors argue that companies will need to understand and embrace these shifts if they hope to succeed in adapting dynamically to the rapidly evolving new era of automation and AI.
Keywords
Citation
| 2023-01-01T00:00:00 |
https://www.hbs.edu/faculty/Pages/item.aspx?num=64606
|
[
{
"date": "2023/01/01",
"position": 14,
"query": "reskilling AI automation"
},
{
"date": "2023/02/01",
"position": 14,
"query": "reskilling AI automation"
},
{
"date": "2023/04/01",
"position": 16,
"query": "reskilling AI automation"
},
{
"date": "2023/05/01",
"position": 14,
"query": "reskilling AI automation"
},
{
"date": "2023/10/01",
"position": 30,
"query": "reskilling AI automation"
},
{
"date": "2023/11/01",
"position": 19,
"query": "reskilling AI automation"
},
{
"date": "2024/03/01",
"position": 20,
"query": "reskilling AI automation"
},
{
"date": "2024/04/01",
"position": 13,
"query": "reskilling AI automation"
},
{
"date": "2024/05/01",
"position": 12,
"query": "reskilling AI automation"
},
{
"date": "2024/06/01",
"position": 15,
"query": "reskilling AI automation"
},
{
"date": "2024/07/01",
"position": 16,
"query": "reskilling AI automation"
},
{
"date": "2024/10/01",
"position": 14,
"query": "reskilling AI automation"
},
{
"date": "2024/11/01",
"position": 14,
"query": "reskilling AI automation"
},
{
"date": "2025/02/01",
"position": 15,
"query": "reskilling AI automation"
},
{
"date": "2025/04/01",
"position": 17,
"query": "reskilling AI automation"
}
] |
|
The Impact of Artificial Intelligence on Workers' Skills: Upskilling and ...
|
The Impact of Artificial Intelligence on Workers’ Skills: Upskilling and Reskilling in Organisations
|
https://www.informingscience.org
|
[
"Sofia Morandini",
"Federico Fraboni",
"Marco De Angelis",
"Gabriele Puzzo",
"Davide Giusino",
"Luca Pietrantoni"
] |
This paper examines the transformative impact of Artificial Intelligence (AI) on professional skills in organizations and explores strategies to address the ...
|
Aim/Purpose This paper examines the transformative impact of Artificial Intelligence (AI) on professional skills in organizations and explores strategies to address the resulting challenges.
Background The rapid integration of AI across various sectors is automating tasks and reducing cognitive workload, leading to increased productivity but also raising concerns about job displacement. Successfully adapting to this transformation requires organizations to implement new working models and develop strategies for upskilling and reskilling their workforce.
Methodology This review analyzes recent research and practice on AI's impact on human skills in organizations. We identify key trends in how AI is reshaping professional competencies and highlight the crucial role of transversal skills in this evolving landscape. The paper also discusses effective strategies to support organizations and guide workers through upskilling and reskilling processes.
Contribution The paper contributes to the existing body of knowledge by examining recent trends in AI's impact on professional skills and workplaces. It emphasizes the importance of transversal skills and identifies strategies to support organizations and workers in meeting upskilling and reskilling challenges. Our findings suggest that investing in workforce development is crucial for ensuring that the benefits of AI are equitably distributed among all stakeholders.
Findings Our findings indicate that organizations must employ a proactive approach to navigate the AI-driven transformation of the workplace. This approach involves mapping the transversal skills needed to address current skill gaps, helping workers identify and develop skills required for effective AI adoption, and implementing processes to support workers through targeted training and development opportunities. These strategies are essential for ensuring that workers' attitudes and mental models towards AI are adaptable and prepared for the changing labor market.
Recommendation for Researchers We emphasize the need for researchers to adopt a transdisciplinary approach when studying AI's impact on the workplace. Given AI's complexity and its far-reaching implications across various fields including computer science, mathematics, engineering, and behavioral and social sciences, integrating diverse perspectives is crucial for a holistic understanding of AI's applications and consequences.
| 2023-02-22T00:00:00 |
2023/02/22
|
https://www.informingscience.org/Publications/5078
|
[
{
"date": "2023/01/01",
"position": 16,
"query": "reskilling AI automation"
},
{
"date": "2023/01/01",
"position": 18,
"query": "artificial intelligence workers"
},
{
"date": "2023/02/01",
"position": 16,
"query": "reskilling AI automation"
},
{
"date": "2023/02/01",
"position": 18,
"query": "artificial intelligence workers"
},
{
"date": "2023/04/01",
"position": 19,
"query": "artificial intelligence workers"
},
{
"date": "2023/04/01",
"position": 19,
"query": "reskilling AI automation"
},
{
"date": "2023/05/01",
"position": 18,
"query": "reskilling AI automation"
},
{
"date": "2023/08/01",
"position": 18,
"query": "artificial intelligence workers"
},
{
"date": "2023/09/01",
"position": 19,
"query": "artificial intelligence workers"
},
{
"date": "2023/10/01",
"position": 25,
"query": "reskilling AI automation"
},
{
"date": "2023/11/01",
"position": 19,
"query": "artificial intelligence workers"
},
{
"date": "2023/11/01",
"position": 15,
"query": "reskilling AI automation"
},
{
"date": "2024/01/01",
"position": 17,
"query": "artificial intelligence workers"
},
{
"date": "2024/03/01",
"position": 25,
"query": "artificial intelligence workers"
},
{
"date": "2024/03/01",
"position": 13,
"query": "reskilling AI automation"
},
{
"date": "2024/04/01",
"position": 19,
"query": "reskilling AI automation"
},
{
"date": "2024/05/01",
"position": 16,
"query": "reskilling AI automation"
},
{
"date": "2024/06/01",
"position": 19,
"query": "reskilling AI automation"
},
{
"date": "2024/07/01",
"position": 19,
"query": "artificial intelligence workers"
},
{
"date": "2024/07/01",
"position": 18,
"query": "reskilling AI automation"
},
{
"date": "2024/10/01",
"position": 18,
"query": "reskilling AI automation"
},
{
"date": "2024/11/01",
"position": 18,
"query": "reskilling AI automation"
},
{
"date": "2025/02/01",
"position": 16,
"query": "reskilling AI automation"
},
{
"date": "2025/04/01",
"position": 16,
"query": "reskilling AI automation"
},
{
"date": "2025/05/01",
"position": 15,
"query": "artificial intelligence workers"
},
{
"date": "2025/06/01",
"position": 19,
"query": "artificial intelligence workers"
}
] |
The Critical Role of Reskilling in the Age of AI - Solinkit
|
The Critical Role of Reskilling in the Age of AI
|
https://solinkit.com
|
[
"Technology Advisor"
] |
Explore how reskilling can help businesses balance AI adoption with workforce retention and prepare employees for the future of work.
|
AI is changing the way we work, and there’s no doubt about it. In the last post, we talked about how businesses are using AI to streamline processes, automate repetitive tasks, and boost productivity. But with all these advancements, there’s one major concern that can’t be ignored: the impact on jobs. Many workers are feeling uncertain about their future as AI takes over certain roles. That’s where reskilling comes in. Instead of leaving people behind, businesses can help their employees learn new skills to keep up with the changes. In this post, we’ll dive into how reskilling is the key to making sure workers aren’t left out in the cold as AI continues to evolve.
How AI is Changing the Job Market
The Rise of Automation and the Need for Reskilling
AI has become a game-changer for businesses, helping them streamline operations and increase efficiency. It’s particularly good at taking over repetitive tasks—things like data entry, scheduling, and even customer support chatbots. While this frees up employees to focus on higher-level work, it also means certain job roles are at risk of becoming obsolete.
Take industries like manufacturing and retail, for example. In manufacturing, assembly line workers have seen robots take over much of the physical labor. In retail, AI is being used to manage inventory or even as a self-checkout system, reducing the need for cashiers. These changes show how reskilling is no longer just a buzzword—it’s essential. Workers need to adapt by learning new skills that focus on tasks AI can’t do, such as critical thinking, creativity, and leadership.
Industries Most Affected by AI and the Role of Reskilling
Some sectors are feeling the impact of AI more than others. Manufacturing, transportation, and retail are among the most vulnerable to job displacement due to automation. In manufacturing, machines now handle tasks like product assembly and quality control. In transportation, self-driving technology is already reshaping how goods are delivered, putting delivery drivers and even truckers at risk.
But here’s where reskilling can make a huge difference. Workers in these fields don’t need to be replaced—they can be retrained. For instance, in manufacturing, an assembly line worker might be reskilled to oversee and maintain the robots doing the labor. In transportation, drivers could be trained to manage logistics or specialize in areas where human judgment is still crucial, like complex route planning or customer service. Reskilling helps employees move into new roles that AI simply can’t handle, keeping them relevant and valuable in the workplace.
The Importance of Reskilling for Workforce Adaptation
Why Reskilling is Key to Long-Term Success
As AI continues to change the way we work, reskilling has become essential. It’s not just about keeping employees around—it’s about future-proofing the workforce. When businesses invest in reskilling, they retain experienced workers and boost productivity. Companies like IBM have already seen success by retraining employees to work in AI and cloud computing, helping them stay competitive in a shifting landscape.
How Companies Can Implement Reskilling Programs
To make reskilling work, businesses need a clear plan. Start by identifying roles impacted by AI and offering training programs that prepare employees for new positions. Whether through partnerships with online learning platforms or internal training, reskilling should focus on skills AI can’t replace—like problem-solving, creativity, and leadership. Companies like AT&T are already seeing the benefits of these efforts, ensuring their workforce is ready for the future.
Balancing AI and Reskilling for Sustainable Workforce Development
Integrating AI Without Ignoring Human Potential
As businesses adopt AI, it’s crucial to find a balance between automation and the value of human workers. AI can enhance productivity, but humans bring creativity, problem-solving, and empathy to the table—qualities that machines can’t replicate. By focusing on reskilling, companies can ensure their employees stay relevant while benefiting from AI’s efficiency.
Upskilling vs. Reskilling – Preparing for AI’s Future
Both reskilling and upskilling are essential for adapting to AI. Reskilling prepares employees for entirely new roles, while upskilling enhances their abilities in their current positions. For example, a worker may be reskilled to oversee AI systems, while others may upskill to use AI tools more effectively in their existing jobs. The key is continuous learning, ensuring employees are ready for whatever AI brings next.
Conclusion
Reskilling is no longer optional—it’s a necessity for businesses that want to succeed in the AI-driven future. By investing in reskilling programs, companies can keep their workforce adaptable, engaged, and ready for new challenges. As AI evolves, so should our approach to workforce development.
If you’re ready to integrate AI without leaving your workforce behind, partner with SoLinkIt. We’ll help you develop strategies for balancing AI implementation with effective reskilling programs, ensuring both your business and your employees thrive. Contact us today to get started!
Check Out the Full Series Below!
Part 1: How AI Automation is Increasing Efficiency Across Industries
Part 2: The Critical Role of Reskilling in the Age of AI
Part 3: Reskilling for the Future: Preparing Your Workforce for AI Integration
| 2025-02-07T00:00:00 |
2025/02/07
|
https://solinkit.com/the-critical-role-of-reskilling-in-the-age-of-ai/
|
[
{
"date": "2023/01/01",
"position": 29,
"query": "reskilling AI automation"
},
{
"date": "2023/02/01",
"position": 28,
"query": "reskilling AI automation"
},
{
"date": "2023/04/01",
"position": 28,
"query": "reskilling AI automation"
},
{
"date": "2023/05/01",
"position": 27,
"query": "reskilling AI automation"
},
{
"date": "2023/10/01",
"position": 53,
"query": "reskilling AI automation"
},
{
"date": "2023/11/01",
"position": 29,
"query": "reskilling AI automation"
},
{
"date": "2024/03/01",
"position": 35,
"query": "reskilling AI automation"
},
{
"date": "2024/04/01",
"position": 28,
"query": "reskilling AI automation"
},
{
"date": "2024/05/01",
"position": 28,
"query": "reskilling AI automation"
},
{
"date": "2024/06/01",
"position": 30,
"query": "reskilling AI automation"
},
{
"date": "2024/10/01",
"position": 29,
"query": "reskilling AI automation"
},
{
"date": "2024/11/01",
"position": 28,
"query": "reskilling AI automation"
},
{
"date": "2025/02/01",
"position": 26,
"query": "reskilling AI automation"
},
{
"date": "2025/04/01",
"position": 25,
"query": "reskilling AI automation"
}
] |
The Need for Reskilling: Preparing for AI, Automation and Digital ...
|
The Need for Reskilling: Preparing for AI, Automation and Digital Transformation
|
https://www.soundingboardinc.com
|
[
"Sb Staff"
] |
Reskilling refers to teaching a person the skills necessary for making a career change. As certain professions are phased out, reskilling has become even more ...
|
Upskilling is the process of training for additional skills, to make current job performance more efficient, and prepare workers for advancement within their specific job sector. Upskilling has always been a recommended practice. Today it is essential to keep pace with changes in the requirements for performing nearly every type of task.
Reskilling refers to teaching a person the skills necessary for making a career change. As certain professions are phased out, reskilling has become even more important. To avoid high unemployment rates, workers who lose jobs to digital transformation must receive training that prepares them for the new and evolving positions that emerge.
Staff members are not always able to take the initiative of acquiring the appropriate skills training on their own. That’s where leadership comes in. Leaders must encourage workers to seek training, perhaps provide it for them. Company investment in reskilling valued workers improves conditions not only for workers who avoid layoffs, but for companies that are able to boost profits. Acknowledging this, The World Economic Forum launched their Reskilling Revolution in January 2020, an initiative to provide one billion people with better education, skills, and jobs to respond to digital transformation by 2030.
| 2021-07-13T00:00:00 |
2021/07/13
|
https://www.soundingboardinc.com/blog/the-need-for-reskilling/
|
[
{
"date": "2023/01/01",
"position": 38,
"query": "reskilling AI automation"
},
{
"date": "2023/02/01",
"position": 39,
"query": "reskilling AI automation"
},
{
"date": "2023/04/01",
"position": 36,
"query": "reskilling AI automation"
},
{
"date": "2023/05/01",
"position": 38,
"query": "reskilling AI automation"
},
{
"date": "2023/10/01",
"position": 94,
"query": "reskilling AI automation"
},
{
"date": "2023/11/01",
"position": 40,
"query": "reskilling AI automation"
},
{
"date": "2024/03/01",
"position": 42,
"query": "reskilling AI automation"
},
{
"date": "2024/04/01",
"position": 38,
"query": "reskilling AI automation"
},
{
"date": "2024/05/01",
"position": 37,
"query": "reskilling AI automation"
},
{
"date": "2024/06/01",
"position": 37,
"query": "reskilling AI automation"
},
{
"date": "2024/07/01",
"position": 39,
"query": "reskilling AI automation"
},
{
"date": "2024/10/01",
"position": 38,
"query": "reskilling AI automation"
},
{
"date": "2024/11/01",
"position": 36,
"query": "reskilling AI automation"
},
{
"date": "2025/02/01",
"position": 34,
"query": "reskilling AI automation"
},
{
"date": "2025/04/01",
"position": 35,
"query": "reskilling AI automation"
}
] |
How Upskilling and Reskilling Drive Intelligent Automation Success
|
Why Upskilling Is the Secret to Intelligent Automation Success
|
https://naviant.com
|
[
"Kara Martin"
] |
Together, let's harness Artificial Intelligence (AI) to fuel innovation and unlock the value of transformative AI. ... Get to know us and why we've been the most ...
|
Why Upskilling Is the Secret to Intelligent Automation Success
As intelligent automation technologies continue to disrupt industries at rapid rates, an urgent truth is surfacing: Shiny new tools and technology solutions aren’t enough. Organizations are transforming the way they work while often failing to help employees keep up with shifting skill needs.
Consequently, they struggle with a growing skill gap, which can cause their intelligent automation initiatives’ results to suffer.
According to Gartner, 64% of managers don’t think their employees are able to keep pace with future skill needs. Additionally, 70% of employees believe they haven’t mastered the skills they need to excel in their current jobs.
Sure, you can navigate this skill gap by hiring new employees who specialize in your new solutions. But expanding your team can be costly and there’s no telling you will find that ideal candidate.
Doing so also disregards the talent of your existing employees. Instead, the key to filling the gap is digital upskilling and reskilling.
Upskilling
Upskilling happens when your employees improve their current skills and expand their abilities. This better positions them to take over new responsibilities in their roles as your company’s needs continue to evolve as your intelligent automation journey progresses.
Reskilling
Reskilling involves retraining workers on a completely fresh set of skills so they can take over a new role in the company. This process may apply if you have employees whose previous responsibilities revolved around tasks that are now irrelevant due to new technologies.
But the benefits of building a culture of continued learning goes beyond simply filling the skill gap. Many companies are finding that it can also drive intelligent automation success, promote organizational growth and agility, and more.
3 Reasons Upskilling and Reskilling Drive Intelligent Automation Success
1. Change Management – Increase Employee Confidence and Approval
Change is scary, and when it comes to intelligent automation, your employees may worry they lack the necessary skills to support the change. This uncertainty can increase doubt and resistance regarding your intelligent automation efforts.
Digital upskilling and reskilling provides employees with the skills they will need to succeed and even advance their own careers. Doing so gives employees an active role in your intelligent automation journey, which can ease their worries and gradually replace uncertainty and resistance with approval.
This can both support your intelligent automation journey’s success and help your employees feel more supported and confident.
2. Retain and Engage Your Employees
As you transform the way you work, you may replace old functions, technologies, and processes with newer, streamlined ones.
This begs the question of what happens to the employees behind them. Instead of letting go of that talent, you can reskill employees by upgrading their skills to fill new demands.
With new processes and technologies comes a need for new skills. With reskilling, you may be able to train these employees to fill these gaps. Alternatively, they may be suitable to enter an entirely different department, field, or area of expertise.
But upskilling can also help with employee retention and engagement. According to a Gallup report, 87% of millennials rate “professional or career growth and development opportunities” as important to them in a job.
For employees looking for dynamic work experiences and growth, adding new skills to their repertoire and the chance to increase their value is highly appealing. Being able to offer employees these exciting opportunities can also be an asset for organizations amid the current Great Resignation.
Giving employees the chance to advance their careers can also encourage them to take ownership, take on new projects, and innovate. Ultimately, both upskilling and reskilling help organizations retain talent that can add value to their intelligent automation initiatives while supporting staff career growth. It’s a win-win.
3. Build a Change-Resilient Organization
Having a workforce that embraces ongoing learning and can rapidly apply their skills is a huge competitive advantage. Technology, customer expectations, and industries will continue to evolve, demanding organizations to be agile and adaptive to change, or die out. Upskilling and reskilling can help your employees adapt to emerging business needs, which can increase loyalty, satisfaction, and engagement.
With practice, your employees can perform through disruptions and gain confidence to persevere, succeed, and sustain during future uncertainties. Continued learning doesn’t just enhance your employees’ potential, but it leads your organization to increased success and growth
How to Build an Upskilling and Reskilling Strategy for Long-Term Agility
Fostering a Culture of Innovation and Continuous Learning
As powerful as reskilling and upskilling is, simply making it a one-and-done operation to fill current needs isn’t enough. To remain agile and competitive in your ever-evolving industry, you must continually evaluate your workforce’s existing skillsets and identify opportunities to build upon them.
Here are some tips to get you started:
Reflect on your organization’s intelligent automation vision.
Try to understand where you’re at, where you want to go, and what you need to accomplish that. This will help you identify or predict what types of skills you may need in the future.
Analyze your customer base.
Research past data to understand their behavior so you can align the strategy to their preferences. After all, customer service is key.
Conduct a skills gap analysis.
Learn what your people already know and what they need to perform in the near future. Review the critical skills your business requires. Then list the skill gaps you need to address.
Establish goals based on your skills gaps.
Filling the gaps won’t happen overnight, but you can begin making progress in little time if you map out your plan now.
Promote a culture of citizen innovation.
As soon as your employees begin learning new skills, encourage them to find ways to apply them and share their ideas. You can even involve them in initiatives like the discovery process behind automation projects. By seeing your intelligent automation journey form and unfold right in front of them, they can get inspired to innovate themselves.
What is Citizen Innovation and Why it’s Critical to Reskill Your Employees
Start small.
Don’t dive into your program too quickly by involving too many people at once. Start by assembling a few teams of knowledge workers, train them, and encourage them to begin applying their skills.
As they learn more and get used to seeking out opportunities for innovation, they, and those around them can slowly warm up to the idea. Over time, it can become second nature as a part of the company culture.
Consider learning in smaller doses.
Micro learning or dividing your employees’ education into shorter modules can fit into the availability of your busy staff. This can also prevent your employees from feeling overwhelmed.
Consider using simulations and other hands-on training tools like RPA.
These strategies can help if your employees need to learn to use machines or devices or respond to emergencies. Additionally, work with subject matter experts to build curriculums.
Plan rewards.
To add extra fun and appeal to your program, you can build in rewards based on milestones and other markers.
Create a program marketing plan.
Strategically presenting your learning programs to your employees will help them warm up to the idea. Create messaging that demonstrates how the program can expand your people’s skills, increase their value, and develop their careers.
It’s vital that organizations make digital upskilling and reskilling a part of their intelligent automation journeys.
Investing in the people behind your organization isn’t just cost effective in the short term but can positively impact your culture and help your organization build resilience in the future.
| 2023-01-01T00:00:00 |
https://naviant.com/blog/upskilling-and-reskilling-intelligent-automation/
|
[
{
"date": "2023/01/01",
"position": 49,
"query": "reskilling AI automation"
},
{
"date": "2023/02/01",
"position": 49,
"query": "reskilling AI automation"
},
{
"date": "2023/04/01",
"position": 46,
"query": "reskilling AI automation"
},
{
"date": "2023/05/01",
"position": 47,
"query": "reskilling AI automation"
},
{
"date": "2023/10/01",
"position": 23,
"query": "reskilling AI automation"
},
{
"date": "2023/11/01",
"position": 47,
"query": "reskilling AI automation"
},
{
"date": "2024/03/01",
"position": 50,
"query": "reskilling AI automation"
},
{
"date": "2024/04/01",
"position": 46,
"query": "reskilling AI automation"
},
{
"date": "2024/05/01",
"position": 47,
"query": "reskilling AI automation"
},
{
"date": "2024/06/01",
"position": 47,
"query": "reskilling AI automation"
},
{
"date": "2024/07/01",
"position": 49,
"query": "reskilling AI automation"
},
{
"date": "2024/10/01",
"position": 46,
"query": "reskilling AI automation"
},
{
"date": "2024/11/01",
"position": 46,
"query": "reskilling AI automation"
},
{
"date": "2025/02/01",
"position": 48,
"query": "reskilling AI automation"
},
{
"date": "2025/04/01",
"position": 20,
"query": "reskilling AI automation"
}
] |
|
Reskilling for Automation: Preparing Your Workforce
|
Reskilling for Automation: Preparing Your Workforce
|
https://www.sgp.technology
|
[] |
From Assembly Line to AI: Reskilling Your Workforce for Automation Success. March 25, 2025. Let's be real—the manufacturing world is buzzing with automation ...
|
Let’s be real—the manufacturing world is buzzing with automation, and it’s changing the game faster than ever. But here’s the catch: this shift isn’t about robots taking over jobs; it’s about getting our workforce ready to work alongside these new technologies. I’ve seen some exciting approaches that manufacturers are taking to tackle this challenge.
Start with the Right Mindset
First up, mindset is everything. I’ve seen some fantastic results when companies start by being open and honest about what automation means for their teams. One large auto parts manufacturer I worked with held a big company-wide meeting to kick things off. They laid out their plans, addressed any worries, and, most importantly, emphasized that this was a chance for growth rather than a threat to jobs. This transparent approach helped reduce resistance and sparked enthusiasm among employees to learn new skills.
Empower Your Team with Training
Next, let’s talk about training. I love the “train the trainer” method. At a food processing plant I worked with, they identified their most tech-savvy line workers and sent them off for specialized training on the new automated systems. When these workers returned, they became internal experts, teaching their peers and acting as a link between the automation team and the shop floor. This not only fostered a sense of pride but also helped everyone feel more comfortable with the changes.
Hands-On Learning Is Key
Hands-on experience is crucial, too. Sure, classroom training has its place, but nothing beats getting your hands dirty. One manufacturer set up a “sandbox” area where employees could tinker with new automated equipment during downtime. This not only took the pressure off but also encouraged creativity—people started coming up with ways to optimize processes just by experimenting.
Find Hidden Talent Within
You’d be surprised how many great automation pros began their careers on the assembly line. They understand both the technical side and the daily grind of manufacturing. So, don’t overlook your current team! That eager worker who’s always fiddling with machinery? They could be your next automation star.
Make Learning Continuous
And remember, reskilling isn’t a one-time event. The pace of change in automation means continuous learning is essential. Many companies are now using online platforms to offer flexible, on-demand training, keeping employees engaged and up to speed.
Don’t Overlook Soft Skills
Finally, let’s not forget about soft skills. As manufacturing becomes more automated, skills like communication, collaboration, and critical thinking are becoming even more important.
In the end, moving towards an automated environment is a journey. It takes time, investment, and a commitment to your people. When you get it right, you’ll have a workforce that not only adapts to new technologies but thrives in the process.
If you’re curious about strategies for reskilling your team or just want to chat about the future of manufacturing, I’d love to hear from you!
| 2023-01-01T00:00:00 |
https://www.sgp.technology/blog-article/from-assembly-line-to-ai-reskilling-your-workforce-for-automation-success
|
[
{
"date": "2023/01/01",
"position": 53,
"query": "reskilling AI automation"
},
{
"date": "2023/02/01",
"position": 52,
"query": "reskilling AI automation"
},
{
"date": "2023/04/01",
"position": 53,
"query": "reskilling AI automation"
},
{
"date": "2023/05/01",
"position": 53,
"query": "reskilling AI automation"
},
{
"date": "2023/10/01",
"position": 68,
"query": "reskilling AI automation"
},
{
"date": "2023/11/01",
"position": 53,
"query": "reskilling AI automation"
},
{
"date": "2024/03/01",
"position": 71,
"query": "reskilling AI automation"
},
{
"date": "2024/04/01",
"position": 53,
"query": "reskilling AI automation"
},
{
"date": "2024/05/01",
"position": 53,
"query": "reskilling AI automation"
},
{
"date": "2024/06/01",
"position": 54,
"query": "reskilling AI automation"
},
{
"date": "2024/07/01",
"position": 54,
"query": "reskilling AI automation"
},
{
"date": "2024/10/01",
"position": 52,
"query": "reskilling AI automation"
},
{
"date": "2024/11/01",
"position": 53,
"query": "reskilling AI automation"
},
{
"date": "2025/02/01",
"position": 51,
"query": "reskilling AI automation"
},
{
"date": "2025/04/01",
"position": 51,
"query": "reskilling AI automation"
}
] |
|
Upskilling and Reskilling: Manufacturing Training in the Age of ...
|
Upskilling and Reskilling: Manufacturing Training in the Age of Automation
|
https://www.atlascopco.com
|
[
"Patrik Löfgren",
"Customer Training Manager"
] |
Automation and artificial intelligence (AI) are transforming industries at an unprecedented pace. Since the Industrial Revolution, new technologies have ...
|
As automation and AI reshape industries, upskilling and reskilling will be crucial for employees and organizations. By investing in continuous learning and creating a supportive environment for skill development, the workforce can more easily adapt to these technological advancements while driving organizational growth and innovation.
In Atlas Copco, we offer several training programs for proper training for production line and other manufacturing personnel, both online and physical. Contact us to learn how to ensure a smooth transition toward Industry 4.0.
| 2023-01-01T00:00:00 |
https://www.atlascopco.com/pt-pt/itba/expert-hub/articles/upskilling-reskilling-manufacturing-ai-automation
|
[
{
"date": "2023/01/01",
"position": 54,
"query": "reskilling AI automation"
},
{
"date": "2023/04/01",
"position": 54,
"query": "reskilling AI automation"
},
{
"date": "2023/05/01",
"position": 56,
"query": "reskilling AI automation"
},
{
"date": "2023/11/01",
"position": 55,
"query": "reskilling AI automation"
},
{
"date": "2024/04/01",
"position": 54,
"query": "reskilling AI automation"
},
{
"date": "2024/05/01",
"position": 54,
"query": "reskilling AI automation"
},
{
"date": "2024/06/01",
"position": 55,
"query": "reskilling AI automation"
},
{
"date": "2024/10/01",
"position": 54,
"query": "reskilling AI automation"
},
{
"date": "2024/11/01",
"position": 54,
"query": "reskilling AI automation"
}
] |
|
Why Workforce Transformation Demands a Reskilling Strategy
|
Beyond Automation: Why Workforce Transformation Demands a Reskilling Strategy
|
https://ozemio.com
|
[
"Rinky Kapoor"
] |
Now, consider the impact of AI, automation, and the digital wave crashing over every industry. The face count will most likely shrink faster than you ...
|
The Workforce Transformation: Why Organisations Need a Proactive Approach
Imagine looking five years into the future. How many faces from your current team will occupy the same seats? Now, consider the impact of AI, automation, and the digital wave crashing over every industry.
The face count will most likely shrink faster than you thought. Change is accelerating, and businesses that don’t adapt to workforce transformation risk falling behind.
Whether you realise it or not, you face a critical challenge as a leader: ensuring your employees remain relevant and future-proof.
The key to workforce transformation is a strategic shift focused on employee reskilling. It also involves redeploying employees into roles that align with your organisation’s changing needs, ensuring long-term resilience and growth.
When done right, workforce transformation enhances organisational agility and fosters employee engagement, innovation, and retention. Let’s explore how:
Reskilling for Strategic Redeployment
Reskilling aligns talent with evolving business needs, enabling seamless redeployment and workforce agility. It helps organisations:
Adapt to Role Evolution – Equip employees for emerging roles, reducing reliance on external hiring.
Ensure Business Continuity – Fill critical skill gaps with trained internal talent.
Optimise Costs – Minimise hiring and training expenses through internal mobility.
Drive Digital Readiness – Prepare employees for AI-driven and tech-enabled roles.
Boost Retention – Offer career growth, increasing engagement and reducing turnover.
By integrating reskilling with redeployment, organisations build a future-ready workforce capable of confidently navigating change.
How Learning & Development Drives Future Readiness with Reskilling
A strategic L&D approach ensures that reskilling efforts translate into tangible business outcomes. It’s about acquiring new skills and aligning learning with evolving business needs, ensuring employees can transition into critical roles that drive growth and innovation.
To future-ready the workforce, organisations must:
Align Skills with Business Strategy – Identify skill gaps based on industry trends and business objectives, ensuring employees are equipped for high-impact roles.
Personalise Learning Journeys – Utilise AI-driven learning platforms to tailor content to individual career paths, making skill development more effective and relevant.
Leverage Experiential Learning—Deploy hands-on training, including VR simulations and scenario-based learning, to foster practical application and confidence in new roles.
Integrate Microlearning & Gamification – Use bite-sized, engaging content to accelerate learning and improve retention, making reskilling seamless.
Ensure Continuous Upskilling – Employ ongoing learning opportunities to keep employees adaptable to emerging technologies and industry shifts.
Measure Learning Effectiveness – Implement advanced analytics to track progress, skill adoption, and business impact, ensuring that reskilling translates into measurable success.
The Pivot Point: Reshaping Your Workforce for Unpredictable Times
Organisations must take a proactive approach by embedding workforce transformation into their talent strategy. Here’s how to get started:
Assess Skill Gaps: Conduct a workforce skills analysis to identify critical reskilling and role realignment areas.
Develop a Learning Roadmap: Align training initiatives with your business objectives, ensuring your employees acquire future-ready skills.
Implement AI-Driven Learning Solutions: Utilize technology-enabled learning platforms, immersive simulations, and mobile-first tailored content to deliver impactful upskilling experiences.
Embed Learning into Workflows: Shift from one-time training to continuous learning by integrating knowledge-sharing tools, coaching, and real-time feedback mechanisms.
Foster a Culture of Continuous Learning: Encourage employees to take ownership of their development through structured learning pathways, mentorship programs, and peer-driven knowledge sharing.
Design Practical Redeployment Strategies: Enable smooth transitions by providing targeted career coaching, job rotations, and skill-matching initiatives.
Partner with Experts: Leverage external learning and development experts, consultants, and solutions providers to design and execute high-impact reskilling and redeployment programs tailored to your organisation’s needs.
The future of work is already here. Are you prepared?
Organisations can future-proof their workforce by adopting reskilling, redeployment, and L&D-driven workforce transformation, ensuring business success in an ever-evolving landscape. Let’s build a workforce that’s ready for tomorrow. Contact Ozemio today!
| 2025-03-26T00:00:00 |
2025/03/26
|
https://ozemio.com/blog/beyond-automation-why-workforce-transformation-demands-a-reskilling-strategy/
|
[
{
"date": "2023/01/01",
"position": 55,
"query": "reskilling AI automation"
},
{
"date": "2023/02/01",
"position": 54,
"query": "reskilling AI automation"
},
{
"date": "2023/04/01",
"position": 55,
"query": "reskilling AI automation"
},
{
"date": "2023/05/01",
"position": 55,
"query": "reskilling AI automation"
},
{
"date": "2023/11/01",
"position": 56,
"query": "reskilling AI automation"
},
{
"date": "2024/03/01",
"position": 77,
"query": "reskilling AI automation"
},
{
"date": "2024/04/01",
"position": 55,
"query": "reskilling AI automation"
},
{
"date": "2024/05/01",
"position": 55,
"query": "reskilling AI automation"
},
{
"date": "2024/06/01",
"position": 56,
"query": "reskilling AI automation"
},
{
"date": "2024/07/01",
"position": 56,
"query": "reskilling AI automation"
},
{
"date": "2024/10/01",
"position": 55,
"query": "reskilling AI automation"
},
{
"date": "2024/11/01",
"position": 55,
"query": "reskilling AI automation"
},
{
"date": "2025/02/01",
"position": 56,
"query": "reskilling AI automation"
},
{
"date": "2025/04/01",
"position": 55,
"query": "reskilling AI automation"
}
] |
How AI and Automation Are Reshaping Workforce Needs
|
The Future of Work: How AI and Automation Are Reshaping Workforce Needs
|
https://www.strategicstaff.com
|
[] |
Advances in artificial intelligence (AI), automation ... What strategies can organizations use to ensure employees have access to reskilling and upskilling ...
|
The Future of Work: How AI and Automation Are Reshaping Workforce Needs
The workplace is undergoing a transformation unlike anything we’ve seen before. Advances in artificial intelligence (AI), automation, and other cutting-edge technologies are revolutionizing industries, changing the nature of jobs, and redefining the skills needed to succeed in the workforce. At Strategic Staffing Solutions (S3), we help businesses navigate this evolving landscape by providing agile workforce solutions that bridge the gap between emerging technologies and human expertise.
Key Trends Shaping the Future of Work
The Rise of Automation
Automation is increasingly handling repetitive, rule-based tasks across industries. From manufacturing to finance, robots and algorithms are performing processes once reserved for humans. This shift not only improves efficiency but also frees workers to focus on higher-value tasks like strategy and innovation. S3supports organizations in integrating automation while developing strategic workforce plans that empower employees to adapt and thrive.
AI-Driven Decision Making
AI is playing a crucial role in helping organizations make data-driven decisions. Machine learning algorithms analyze massive datasets to uncover patterns, predict trends, and optimize operations. For employees, this means a growing need to interpret and act on AI-generated insights. S3 partners with companies to identify talent equipped with analytical and problem-solving skills, ensuring businesses maximize the potential of AI without losing the human element.
The Evolution of Roles
As technology takes over routine tasks, entirely new job categories are emerging. Roles like AI trainers, machine learning specialists, and automation ethicists are in high demand. At the same time, traditional roles are evolving, requiring workers to develop hybrid skills that blend technical expertise with human-centered capabilities. S3 specializes in sourcing and developing talent that meets these new demands, ensuring organizations stay competitive in a rapidly changing job market.
The Gig Economy and Remote Work
Technology has enabled the rise of the gig economy and remote work, allowing workers to connect with employers across the globe. Flexibility and adaptability are becoming essential traits as businesses tap into a diverse, decentralized talent pool. S3 helps organizations build agile workforce models that leverage remote talent while maintaining productivity and collaboration.
Upskilling and Lifelong Learning
As job requirements change, so does the need for upskilling. Employees must continually learn to stay relevant in their fields. Organizations are investing in training programs and partnerships with educational institutions to bridge skill gaps and prepare their teams for the future.
Challenges in the Age of AI and Automation
While the benefits of AI and automation are undeniable, they also come with challenges:
Job Displacement: Some workers may face job losses as their roles are automated. Addressing this requires proactive reskilling initiatives, a key focus area for S 3 .
Some workers may face job losses as their roles are automated. Addressing this requires proactive reskilling initiatives, a key focus area for S . Ethical Considerations: The deployment of AI raises questions about privacy, bias, and accountability. Businesses must navigate these issues responsibly, and S 3 helps organizations establish ethical AI governance frameworks.
The deployment of AI raises questions about privacy, bias, and accountability. Businesses must navigate these issues responsibly, and S helps organizations establish ethical AI governance frameworks. Workforce Inequality: Access to new technologies and training opportunities isn’t uniform, risking a widening gap between skilled and unskilled workers. S3 is committed to diversity and inclusion, ensuring all employees have opportunities to reskill and grow.
Preparing for the Workforce of Tomorrow
As we navigate these changes, it’s crucial to ask the right questions:
How can businesses balance the benefits of automation with the need for human jobs?
What strategies can organizations use to ensure employees have access to reskilling and upskilling opportunities?
How can leaders foster a culture of innovation and adaptability within their teams?
What safeguards should be in place to address ethical concerns related to AI in the workplace?
How can individuals future-proof their careers in an era of rapid technological change?
At S3, we believe the future of work will be defined by those who embrace change and proactively prepare for what lies ahead. By implementing workforce solutions that align with AI and automation advancements, businesses can empower their teams, drive innovation, and secure long-term success.
Let’s Talk About the Future
What are your thoughts on the role of technology in shaping the workplace? Share your perspective in the comments!
| 2023-01-01T00:00:00 |
https://www.strategicstaff.com/the-future-of-work-how-ai-and-automation-are-reshaping-workforce-needs/
|
[
{
"date": "2023/01/01",
"position": 56,
"query": "reskilling AI automation"
},
{
"date": "2023/02/01",
"position": 62,
"query": "reskilling AI automation"
},
{
"date": "2023/04/01",
"position": 58,
"query": "reskilling AI automation"
},
{
"date": "2023/05/01",
"position": 64,
"query": "reskilling AI automation"
},
{
"date": "2023/10/01",
"position": 13,
"query": "reskilling AI automation"
},
{
"date": "2023/11/01",
"position": 59,
"query": "reskilling AI automation"
},
{
"date": "2024/03/01",
"position": 55,
"query": "reskilling AI automation"
},
{
"date": "2024/04/01",
"position": 56,
"query": "reskilling AI automation"
},
{
"date": "2024/05/01",
"position": 56,
"query": "reskilling AI automation"
},
{
"date": "2024/06/01",
"position": 57,
"query": "reskilling AI automation"
},
{
"date": "2024/07/01",
"position": 60,
"query": "reskilling AI automation"
},
{
"date": "2024/10/01",
"position": 58,
"query": "reskilling AI automation"
},
{
"date": "2024/11/01",
"position": 57,
"query": "reskilling AI automation"
},
{
"date": "2025/02/01",
"position": 13,
"query": "reskilling AI automation"
},
{
"date": "2025/04/01",
"position": 12,
"query": "reskilling AI automation"
}
] |
|
People And AI: Reskilling For the Future - Data Pilot
|
People And AI: Reskilling For the Future
|
https://data-pilot.com
|
[] |
... automation and AI adoption. Companies cite cost-cutting as the main driver for layoffs, with financial firms announcing 23,200 job cuts, and tech companies ...
|
Hard Times by Charles Dickens, published in 1854, explores the social and economic challenges faced by the working class during the Industrial Revolution. Dickens uses the novel as a commentary on the dehumanizing effects of industrialization, the miserable lives of factory workers, and the disparities between the wealthy and the poor. The novel’s enduring themes exploring social injustice and the importance of a more compassionate society remain relevant even today.
We are in the middle of the artificial intelligence (AI) revolution transforming how people work, by making operations more efficient, supporting better decision-making and freeing up time for more productive tasks. While AI tools are a long way from the machines of the Industrial Revolution, the concern that machines might take over tasks from humans is not entirely misplaced.
In such times, the need to inspire people to gear up for an AI-fueled workplace becomes a priority. According to CBS news, the US job market remains one of the main engines of the economy, yet the January 2024 job cuts clustered in financial and tech businesses are indicative of the strategic shift towards increased automation and AI adoption. Companies cite cost-cutting as the main driver for layoffs, with financial firms announcing 23,200 job cuts, and tech companies slashing 16,000 jobs. But the advent of AI, no doubt very different from the original industrial revolution, raises a similar concern of machines replacing humans. People are central to success for organizations, and now that leaders are actively looking for ways to implement AI in the workplace, they will have to ensure employees are ready to embrace the technology wholeheartedly, since people will be essential to driving the implementation and usage of the technology.
Leaders will have to build and strengthen employee trust in AI.
Employees obviously have the most at stake when introducing AI into the workplace. A study predicts that two-thirds of jobs in the US and European markets will be disrupted in some way by AI automation and this change will affect women more than men – 80% compared to 60% respectively. With these numbers, the responsibility to maintain employee morale and productivity lies with the leaders. And trust building begins with transparent communication.
Employees will have to be engaged in discussions reshaping the organization’s AI-enabled future and this new era of work. However, to fully execute a symbiotic relationship between people and technology, the right mix of AI skilled talent will be needed. In a report The AI Skills Gap by SnapLogic, 93% of US and UK organizations surveyed (300 IT leaders representing organizations with more than 1,000 employees in the US and UK) considered AI to be a business priority but cited the lack of skilled people in-house as the number one obstacle to progressing their AI initiatives. Leaders believe that humans and AI will augment each other, but to meet their aspirations, they will require the right combination of people to translate business needs into solutions.
Closing the AI skills gap will empower businesses to fully leverage the technology.
Businesses are refocusing investments in AI and obviously view the development of AI capabilities as a competitive advantage. But before they can fully embrace the technology, leaders have an obligation to reskill their people and future-proof the workforce. The top skills required to successfully implement AI in organizations are given below.
Source: The AI Skills Gap
The estimation is that at least 40% of the workforce may need to reskill due to AI implementation or automation over the next three years. People need to show diverse skills from technical expertise to empathy and adaptability in thinking, to work most effectively with AI. These estimates seem overwhelming, but they bring up an exciting opportunity to empower people and develop the desired skills for jobs in the digital economy. Organizations should aim to build in-house capabilities, ensuring that skills match the pace of technological advancement.
However, establishing in-house talent immediately may take time, and as a result, businesses would need external support. Data Pilot’s expert team of data scientists, analysts and data engineers helps organizations fill the gaps in skill shortages and overcome the challenges of AI adoption. In the last three years, the team has completed more than 50 projects in 7 countries, aiding customers in work as diverse as implementing computer vision to detect defects for a global textile brand, using predictive analytics to forecast churn for a media and advertising firm, and proactively developing omnichannel analytics for a contemporary women’s fashion retailer. Sounds positively marvelous, right? It is.
Pro tip: Consult our experts for more.
While there is no quick and easy solution to the AI skills gap, one immediate approach is to understand the significance of human capital and know that the main value of AI is to augment human work and remove redundancies.
Human capital remains a crucial asset for organizations.
Automation is not synonymous with elimination. The opinion is to reimagine work as a collaborative process where humans define the problems, machines find the solutions, and humans verify the acceptability of those solutions. This concept of a mutually beneficial relationship between humans and machines is not new – computer scientist J.C.R. Licklider proposed the “man-machine symbiosis” as early as 1960. The emergence of AI in the last few years has brought people and organizations to a fascinating point in time, where the development of an agile and skilled workforce is extremely valuable.
As a change management initiative, businesses will have to participate actively in supporting their existing talent through reskilling and upskilling.
Source: The AI Skills Gap
While the figures are promising, few companies have seriously considered the option for reskilling. They prefer to fill roles through hiring rather than internally developing people for future roles. Completely relying on hiring new talent becomes challenging when the demands for jobs and skills are continuously evolving. Therefore, leaders and CEOs need to find the right balance between hiring and reskilling.
Preparing the organization to transition towards a more tech-savvy, future-ready workforce goes beyond mere training. It involves fostering an organizational context across all roles and hierarchies, where the need for reskilling and upskilling is identified to build the company’s AI expertise. People should also develop an attitude of lifelong learning and know that integrating AI assistance into their jobs will supercharge their work in the future.
Learning opportunities can be facilitated through online learning platforms.
There is little doubt that work will be redesigned for the age of AI. Organizations will use AI to automate repetitive and error-prone tasks, freeing people up to bring their skills of judgment and empathy for more complex decisions. With freed-up capacity, organizations should embrace the accessibility of reskilling programs.
Online learning platforms are expected to grow 19% over the next four years. Technology has made quality education and varied learning programs accessible to people. Organizations need to use these learning platforms to their advantage and build the required talent from within. The most prepared organizations will be the ones who realize the value of human capital and embrace advanced technologies at the same time. Empowering employees with opportunities to reskill will help them utilize AI tools, become efficient, and maximize business value.
By Tooba Shah.
| 2024-12-08T00:00:00 |
2024/12/08
|
https://data-pilot.com/blog/people-and-ai-reskilling-for-the-future/
|
[
{
"date": "2023/01/01",
"position": 58,
"query": "reskilling AI automation"
},
{
"date": "2023/02/01",
"position": 61,
"query": "reskilling AI automation"
},
{
"date": "2023/04/01",
"position": 59,
"query": "reskilling AI automation"
},
{
"date": "2023/10/01",
"position": 51,
"query": "reskilling AI automation"
},
{
"date": "2023/11/01",
"position": 60,
"query": "reskilling AI automation"
},
{
"date": "2024/03/01",
"position": 85,
"query": "reskilling AI automation"
},
{
"date": "2024/04/01",
"position": 57,
"query": "reskilling AI automation"
},
{
"date": "2024/05/01",
"position": 58,
"query": "reskilling AI automation"
},
{
"date": "2024/06/01",
"position": 59,
"query": "reskilling AI automation"
},
{
"date": "2024/10/01",
"position": 59,
"query": "reskilling AI automation"
},
{
"date": "2024/11/01",
"position": 58,
"query": "reskilling AI automation"
},
{
"date": "2025/02/01",
"position": 61,
"query": "reskilling AI automation"
},
{
"date": "2025/04/01",
"position": 58,
"query": "reskilling AI automation"
}
] |
AI and Automation: Future-Proofing Gen Z for Career Success
|
AI and Automation: Future-Proofing Gen Z for Career Success
|
https://www.reckrute.com
|
[
"Fay Desouza"
] |
Reskilling Gen Z for Future Jobs in the Age of AI and Automation. The rapid advancement of artificial intelligence (AI) and automation technologies is reshaping ...
|
The rapid advancement of artificial intelligence (AI) and automation technologies is reshaping the global workforce landscape. For Generation Z, born into a digital age, adapting to this transformation is crucial for securing future employment opportunities.
Understanding the Impact
AI and automation are revolutionizing industries, streamlining processes, and altering job requirements. This shift demands a workforce with updated skill sets to remain competitive in the evolving job market.
Embracing Reskilling Initiatives
To thrive in the AI and automation era, Generation Z must proactively engage in reskilling programs. These initiatives offer opportunities to acquire new competencies and adapt to changing industry demands.
Integrating Technological Literacy
Educational institutions play a vital role in equipping Generation Z with the necessary skills for the future workforce. By integrating technology education into curricula, students can develop digital literacy and problem-solving abilities.
Exploring New Career Paths
The emergence of AI and automation opens doors to diverse career opportunities. Generation Z can explore roles in data science, robotics, and machine learning, leveraging their digital fluency to excel in these fields.
Cultivating Adaptability
In the dynamic landscape of AI and automation, adaptability is key to success. Generation Z must embrace continuous learning and adapt to evolving technologies to remain relevant in their careers.
Fostering Collaboration and Innovation
Cross-disciplinary collaboration is essential for driving innovation in the AI-driven economy. Generation Z can leverage their diverse skill sets to collaborate across fields and address complex challenges.
Nurturing Soft Skills
While technical proficiency is vital, soft skills such as communication and critical thinking are equally important. Generation Z must hone these interpersonal skills to thrive in collaborative work environments.
Conclusion
Reskilling Generation Z for the AI and automation era is imperative for building a workforce prepared to tackle the challenges and seize the opportunities of the future job market.
| 2024-04-26T00:00:00 |
2024/04/26
|
https://www.reckrute.com/blog/reskilling-gen-z-ai-automation/
|
[
{
"date": "2023/01/01",
"position": 62,
"query": "reskilling AI automation"
},
{
"date": "2023/02/01",
"position": 59,
"query": "reskilling AI automation"
},
{
"date": "2023/04/01",
"position": 61,
"query": "reskilling AI automation"
},
{
"date": "2023/05/01",
"position": 58,
"query": "reskilling AI automation"
},
{
"date": "2023/10/01",
"position": 89,
"query": "reskilling AI automation"
},
{
"date": "2023/11/01",
"position": 64,
"query": "reskilling AI automation"
},
{
"date": "2024/03/01",
"position": 86,
"query": "reskilling AI automation"
},
{
"date": "2024/04/01",
"position": 63,
"query": "reskilling AI automation"
},
{
"date": "2024/05/01",
"position": 64,
"query": "reskilling AI automation"
},
{
"date": "2024/06/01",
"position": 62,
"query": "reskilling AI automation"
},
{
"date": "2024/10/01",
"position": 61,
"query": "reskilling AI automation"
},
{
"date": "2024/11/01",
"position": 61,
"query": "reskilling AI automation"
},
{
"date": "2025/02/01",
"position": 65,
"query": "reskilling AI automation"
},
{
"date": "2025/04/01",
"position": 61,
"query": "reskilling AI automation"
}
] |
Proven Reskilling and Upskilling in the AI Era - HR Challenges
|
Proven Reskilling And Upskilling In The AI Era HR Challenges
|
https://hrchallenges.com
|
[] |
The world of work is changing rapidly. The rise of artificial intelligence (AI), automation, and digital technologies has transformed industries at an ...
|
The world of work is changing rapidly. The rise of artificial intelligence (AI), automation, and digital technologies has transformed industries at an unprecedented pace. To thrive in this evolving landscape, employees and organizations must adapt—and the best way to stay ahead is through reskilling and upskilling. Whether you’re a young professional looking to enhance your career or a seasoned employee striving to stay relevant, mastering new skills is crucial in the AI-driven era. Proven Reskilling and Upskilling in the AI Era.
Read these articles also:
https://hrchallenges.com/why-companies-fail-to-retain-tech-skill/
Understanding Reskilling and Upskilling
Before diving deeper, let’s clarify these two key concepts:
Reskilling : Learning entirely new skills to take on a different role or career path. For example, a factory worker learning coding to transition into IT.
: Learning entirely new skills to take on a different role or career path. For example, a factory worker learning coding to transition into IT. Upskilling: Enhancing existing skills to stay current in your field. For example, a marketing professional mastering data analytics tools to improve campaign results. Proven Reskilling and Upskilling in the AI Era.
Both are vital in the modern workplace, where AI is reshaping job roles, processes, and even decision-making. While automation may replace some routine tasks, it also creates new opportunities that demand specialized skills. Proven Reskilling and Upskilling in the AI Era.
Why Reskilling and Upskilling Matter in the AI Era
1. Job Automation is Rising
AI is increasingly taking over repetitive and rule-based tasks. Roles in manufacturing, data entry, and customer support are evolving as automated systems streamline processes. Professionals who develop new skills will be better equipped to pivot toward emerging opportunities.
2. The Demand for Digital Skills is Growing
AI is now integrated into multiple industries—from healthcare to finance to retail. Skills such as data analysis, machine learning, and programming are becoming essential. Even non-technical roles require proficiency in digital tools and platforms.
3. Human Skills Remain Crucial
While AI excels at logic and data processing, soft skills like emotional intelligence, creativity, and critical thinking are indispensable. Developing these traits can give you a competitive edge in roles that AI cannot fully replace. Proven Reskilling and Upskilling in the AI Era.
4. Future-Proofing Your Career
Investing in continuous learning ensures you stay adaptable. By proactively updating your skillset, you reduce the risk of job displacement and position yourself for growth in emerging fields.
Proven Reskilling and Upskilling in the AI Era
Key Skills for the AI Era
1. Data Literacy
AI relies heavily on data, making data literacy essential for decision-making. Learning to interpret data, use analytics tools, and understand AI-generated insights can boost your career in almost any industry.
2. AI and Automation Tools
Familiarity with AI platforms such as ChatGPT, Google Bard, or Microsoft Copilot can improve your productivity. Understanding how AI enhances customer service, content creation, or data processing will make you indispensable in your organization.
3. Coding and Programming
Languages like Python, R, and JavaScript are valuable for those entering tech roles. Even basic coding knowledge can improve problem-solving skills and unlock career growth in tech-driven environments.
4. Emotional Intelligence and Leadership
Since AI lacks empathy, leadership roles that require emotional understanding, teamwork, and conflict resolution will remain in demand. Developing these abilities will ensure you excel in roles involving customer interactions or team management.
5. Cybersecurity and Data Protection
As data-driven systems grow, securing sensitive information becomes critical. Learning about cybersecurity practices can make you an asset to businesses focused on protecting their digital assets.
6. Adaptability and Problem-Solving
The rapid pace of AI advancements requires professionals who can adapt, troubleshoot issues, and embrace change. Cultivating a flexible mindset will prepare you for unexpected challenges in the workplace.
How to Start Reskilling and Upskilling
1. Assess Your Current Skills
Begin by identifying your strengths and weaknesses. Reflect on your career goals and pinpoint areas that need improvement. Consider seeking feedback from supervisors or mentors for added clarity.
2. Identify Emerging Industry Trends
Stay informed about how AI is influencing your industry. Follow tech blogs, attend webinars, and engage with thought leaders to understand which skills are becoming increasingly valuable.
3. Leverage Online Learning Platforms
Websites like Coursera, Udemy, and LinkedIn Learning offer affordable courses that cater to different skill levels. Many provide certifications that can strengthen your resume.
4. Participate in Workshops and Seminars
Attending interactive sessions allows you to learn directly from experts while expanding your professional network. These events often provide practical insights that can be immediately applied in your role.
5. Seek Mentorship and Coaching
Connecting with experienced professionals can accelerate your learning. Mentors offer guidance, share industry insights, and help you avoid common pitfalls in your reskilling journey.
6. Embrace Hands-On Experience
Practice is key to mastering new skills. Volunteer for projects within your organization, explore freelance opportunities, or collaborate with peers to apply your learning in real-world scenarios.
Benefits of Reskilling and Upskilling
1. Career Growth Opportunities
By enhancing your skillset, you increase your eligibility for leadership roles, promotions, and salary hikes. Companies value employees who invest in personal development.
2. Increased Job Security
In a competitive job market, reskilling helps you remain relevant even if your current role evolves. Employers are more likely to retain adaptable employees with future-ready skills.
3. Enhanced Productivity
Learning new tools and strategies can streamline your tasks, improving efficiency and performance. This not only benefits your employer but also boosts your confidence.
4. Personal Fulfillment
Reskilling allows you to explore new interests and gain satisfaction from mastering challenging concepts. Expanding your expertise can unlock exciting career paths you hadn’t previously considered.
Industries Embracing Reskilling and Upskilling
Healthcare: Medical professionals are learning to interpret AI-driven diagnostics and apply telemedicine solutions. Finance: Banking staff are mastering AI fraud detection and predictive analytics tools. Retail and E-commerce: Employees are gaining expertise in personalized marketing, AI-driven inventory management, and chatbots. Manufacturing: Factory workers are learning to manage robotic systems and automated machinery. Education: Teachers are exploring AI-based learning platforms to improve student engagement.
Final Thoughts
The AI era presents both challenges and opportunities. While automation may redefine traditional roles, proactive individuals can secure a prosperous future by embracing continuous learning. Whether you’re aiming to climb the corporate ladder or transition into a new career, reskilling and upskilling are your keys to success.
Take charge of your future today—learn, grow, and thrive in the AI-driven world.
| 2025-03-10T00:00:00 |
2025/03/10
|
https://hrchallenges.com/proven-reskilling-and-upskilling-in-the-ai-era/
|
[
{
"date": "2023/01/01",
"position": 64,
"query": "reskilling AI automation"
},
{
"date": "2023/02/01",
"position": 60,
"query": "reskilling AI automation"
},
{
"date": "2023/04/01",
"position": 62,
"query": "reskilling AI automation"
},
{
"date": "2023/05/01",
"position": 61,
"query": "reskilling AI automation"
},
{
"date": "2023/10/01",
"position": 72,
"query": "reskilling AI automation"
},
{
"date": "2023/11/01",
"position": 67,
"query": "reskilling AI automation"
},
{
"date": "2024/03/01",
"position": 57,
"query": "reskilling AI automation"
},
{
"date": "2024/04/01",
"position": 67,
"query": "reskilling AI automation"
},
{
"date": "2024/05/01",
"position": 67,
"query": "reskilling AI automation"
},
{
"date": "2024/06/01",
"position": 65,
"query": "reskilling AI automation"
},
{
"date": "2024/10/01",
"position": 62,
"query": "reskilling AI automation"
},
{
"date": "2024/11/01",
"position": 64,
"query": "reskilling AI automation"
},
{
"date": "2025/02/01",
"position": 64,
"query": "reskilling AI automation"
},
{
"date": "2025/04/01",
"position": 59,
"query": "reskilling AI automation"
}
] |
AI and Skills Taxonomy: Empowering Employee Reskilling - RChilli
|
How AI and Skills Taxonomy Drive Employee Reskilling
|
https://www.rchilli.com
|
[
"Navjot Kaur"
] |
In a rapidly changing job market, the fear of automation and AI taking away jobs has loomed for several years. However, this perspective often overlooks AI's ...
|
How is AI & Skills Taxonomy helping in reskilling the workforce? Wait! Isn't AI taking away jobs? These are common questions that arise when discussing the role of AI in the job market. However, it is important to recognize that AI is not solely responsible for job losses. In fact, AI is playing a significant role in reskilling and upskilling employees, ensuring that they remain valuable assets in a rapidly changing job market.
In a rapidly changing job market, the fear of automation and AI taking away jobs has loomed for several years. However, this perspective often overlooks AI's significant role in reskilling and upskilling employees. Rather than replacing human workers, AI is emerging as a powerful tool to identify skill gaps and facilitate acquiring of new skills. In this blog post, we'll delve into the ways in which AI is facilitating employee reskilling and upskilling, while also shedding light on the pivotal significance of skills taxonomy in this process.
The AI Revolution: Closing Skill Gaps, Not Job Losses
According to Sander van ‘t Noordende on Forbes:
"We stand more to gain than to lose"
With each technological revolution has come waves of labor market disruption but also growth opportunities. PwC’s forecast suggests that AI could contribute a remarkable $15.7 trillion to the worldwide economy by the year 2030.
The idea that AI will lead to job losses is a common misconception. While AI and automation have streamlined and transformed various industries, they've also created a demand for new skills. AI is enabling employees to adapt and thrive in this ever-evolving landscape. Here's how:
Skill Gap Analysis: AI analyzes large volumes of data to identify organizational skill gaps. It assesses employees' existing skills and maps them against the skills required for their roles. This helps employees understand where they need to improve but also assists employers in making informed decisions regarding reskilling initiatives. Skill gap analysis has become crucial in a rapidly changing job market, where outdated skills can quickly become obsolete.
Personalized Learning Paths: AI-driven platforms provide customized learning paths for employees. AI recommends the most suitable courses and resources by considering an individual's skills, learning preferences, and career goals. This tailored approach ensures that employees invest their time and energy in acquiring the skills that matter most for their roles. Personalization is vital to ensuring that employees remain engaged and motivated in their reskilling journey.
Continuous Learning: AI promotes a culture of constant learning. It updates employees with industry trends and technologies by delivering bite-sized, relevant content. This approach keeps employees engaged and motivated to expand their skill set. Continuous learning is the essential factor for staying pertinent and competitive in a swiftly evolving world.
Performance Monitoring: AI can track an employee's progress as they reskill. This allows employers to measure the effectiveness of their reskilling programs and make necessary adjustments to ensure better outcomes. Performance monitoring provides valuable feedback on the success of reskilling efforts and allows for real-time adjustments to improve the learning process.
The Role of Taxonomy in Employee Reskilling
Taxonomy, the science of classification, plays a pivotal role in AI-driven employee reskilling programs. It involves categorizing skills, knowledge, and competencies into a structured framework. This structured approach serves various purposes:
Skill Categorization: Skills taxonomy helps in the systematic categorization of skills, making it easier for AI to identify and map them. This ensures that the reskilling process is efficient and well-organized. Skill categorization provides clarity on what skills are required and helps streamline the process of acquiring them.
Alignment with Business Goals: Taxonomy allows organizations to align employee skills with their broader business objectives. By classifying skills in a taxonomic framework, companies can create reskilling strategies that directly contribute to their growth and innovation. When skills are aligned with business goals, reskilling becomes a strategic effort that drives the company forward.
Standardized Evaluation: Taxonomy creates a standardized way to evaluate skills and competencies. It fosters a shared understanding between employees and employers when addressing skill prerequisites and tracking progress. Standardized evaluation facilitates effective communication and provides a common understanding of skill expectations and progress tracking.
Data Consistency: When AI systems are fed data that adheres to a well-defined taxonomy, they can provide more accurate insights. This helps in the creation of effective reskilling programs. Data consistency is critical in ensuring that AI systems can make sense of the information they receive, leading to better-informed reskilling recommendations.
Download skills taxonomy infographic to learn how you can identify and hire top talent.
The Future of Work and Employee Empowerment
Dynamic changes in technology, job roles, and skill requirements characterize the future of work. It's a landscape where adaptability and continuous learning have become prerequisites for long-term career success. In this scenario, AI is a valuable ally, not a threat, to employees.
Rather than displacing human workers, AI empowers them by providing the tools and resources needed to remain relevant and competitive in their fields. The combination of AI and taxonomy facilitates a structured, data-driven approach to reskilling, ensuring that employees acquire the skills that align with their job roles and business goals.
AI and Skills Taxonomy in Action: A Real-World Example
To illustrate how a hypothetical technology company might use AI and Skills Taxonomy to enhance their team's capabilities, particularly in an emerging field like machine learning, let's break down the process into clear, actionable steps:
Step 1: Identifying Skill Gaps: Initially, the company employs AI to analyze the current competencies of its software development team. AI is an efficient tool that quickly assesses the team's skills and identifies those they need to succeed in their projects. This analysis helps pinpoint critical skill gaps, such as a deficiency in machine learning expertise, essential for developing cutting-edge products.
Step 2: Creating Personalized Learning Paths: Using AI insights, the company crafts tailored learning experiences for each team member, incorporating machine learning courses, coding exercises, and hands-on projects suited to individual skill levels and career goals. This targeted approach boosts learning effectiveness and increases job-matching accuracy by 45%, ensuring employees are ideally suited for roles that match their new skills.
Step 3: Promoting Continuous Learning: AI tools keep the team informed of the latest trends and developments in machine learning. This continuous learning is vital in a field where technology evolves rapidly, ensuring the team remains at the forefront of their industry.
Step 4: Monitoring Progress: AI systems track progress as team members advance through their learning journey. This monitoring is comparable to having a coach who continuously provides feedback, allowing the company to assess how well team members adapt to new skills and make necessary adjustments to the learning paths.
Step 5: Using Taxonomy to Organize Learning: Throughout this process, a well-defined taxonomy system categorizes and classifies various skills and competencies related to machine learning. This structured approach facilitates the organization of learning content and ensures that the reskilling efforts align with the company's broader objectives to foster innovation and develop new products.
By implementing these steps, AI and skills taxonomy not only assist in identifying and bridging skill gaps but also support continuous development and strategic alignment with business objectives. Ultimately, this makes the workforce more adept and the business more competitive.
Conclusion
AI and taxonomy are powerful tools to reskill and upskill employees, ultimately empowering them to thrive in a constantly evolving job market. These technologies enable employees to identify and address skill gaps, personalize their learning journeys, engage in continuous learning, and track their performance. Taxonomy's role in categorizing skills and aligning them with business objectives further enhances the efficiency and effectiveness of reskilling initiatives.
In the face of technological advancements and changing industry landscapes, AI and taxonomy are not the adversaries of employees; they are their allies. By leveraging these tools, organizations and their workforce can navigate the future of work with confidence, adaptability, and a commitment to ongoing learning and improvement. The future looks brighter in this symbiotic relationship between humans and technology.
| 2023-01-01T00:00:00 |
https://www.rchilli.com/blog/ai-and-skills-taxonomy-empowering-employee-reskilling
|
[
{
"date": "2023/01/01",
"position": 75,
"query": "reskilling AI automation"
},
{
"date": "2023/02/01",
"position": 68,
"query": "reskilling AI automation"
},
{
"date": "2023/04/01",
"position": 77,
"query": "reskilling AI automation"
},
{
"date": "2023/05/01",
"position": 76,
"query": "reskilling AI automation"
},
{
"date": "2023/10/01",
"position": 45,
"query": "reskilling AI automation"
},
{
"date": "2023/11/12",
"position": 5,
"query": "AI skills gap"
},
{
"date": "2023/11/01",
"position": 75,
"query": "reskilling AI automation"
},
{
"date": "2024/03/01",
"position": 65,
"query": "reskilling AI automation"
},
{
"date": "2024/04/01",
"position": 73,
"query": "reskilling AI automation"
},
{
"date": "2024/05/01",
"position": 69,
"query": "reskilling AI automation"
},
{
"date": "2024/06/01",
"position": 77,
"query": "reskilling AI automation"
},
{
"date": "2024/07/01",
"position": 61,
"query": "reskilling AI automation"
},
{
"date": "2024/10/01",
"position": 80,
"query": "reskilling AI automation"
},
{
"date": "2024/11/01",
"position": 74,
"query": "reskilling AI automation"
},
{
"date": "2025/02/01",
"position": 66,
"query": "reskilling AI automation"
},
{
"date": "2025/04/01",
"position": 66,
"query": "reskilling AI automation"
}
] |
|
Retraining and reskilling workers in the age of automation
|
Retraining and reskilling workers in the age of automation
|
https://www.voced.edu.au
|
[
"Illanes"
] |
... automation, and advances in artificial intelligence (AI) disrupt the world of work. The kinds of skills companies require will shift, with profound ...
|
By 2030, according to a McKinsey Global Institute report published in 2017, 'Jobs lost, jobs gained: workforce transitions in a time of automation' [available in VOCEDplus at TD/TNC 130.485], as many as 375 million workers - or roughly 14 per cent of the global workforce - may need to switch occupational categories as digitization, automation, and advances in artificial intelligence (AI) disrupt the world of work. The kinds of skills companies require will shift, with profound implications for the career paths individuals will need to pursue. This article discusses the potential size of this c ... Show more
By 2030, according to a McKinsey Global Institute report published in 2017, 'Jobs lost, jobs gained: workforce transitions in a time of automation' [available in VOCEDplus at TD/TNC 130.485], as many as 375 million workers - or roughly 14 per cent of the global workforce - may need to switch occupational categories as digitization, automation, and advances in artificial intelligence (AI) disrupt the world of work. The kinds of skills companies require will shift, with profound implications for the career paths individuals will need to pursue. This article discusses the potential size of this challenge, arguing that, so far, growing awareness of the scale of the task ahead has yet to translate into action in terms of both public and corporate spending on labour force training.
Edited excerpts from publication. Show less
| 2018-07-14T00:00:00 |
2018/07/14
|
https://www.voced.edu.au/content/ngv%3A83089
|
[
{
"date": "2023/01/01",
"position": 77,
"query": "reskilling AI automation"
},
{
"date": "2023/02/01",
"position": 72,
"query": "reskilling AI automation"
},
{
"date": "2023/04/01",
"position": 73,
"query": "reskilling AI automation"
},
{
"date": "2023/05/01",
"position": 72,
"query": "reskilling AI automation"
},
{
"date": "2023/11/01",
"position": 79,
"query": "reskilling AI automation"
},
{
"date": "2024/03/01",
"position": 69,
"query": "reskilling AI automation"
},
{
"date": "2024/04/01",
"position": 78,
"query": "reskilling AI automation"
},
{
"date": "2024/05/01",
"position": 80,
"query": "reskilling AI automation"
},
{
"date": "2024/06/01",
"position": 74,
"query": "reskilling AI automation"
},
{
"date": "2024/10/01",
"position": 75,
"query": "reskilling AI automation"
},
{
"date": "2024/11/01",
"position": 77,
"query": "reskilling AI automation"
}
] |
AI for Frontline Workforce Upskilling and Reskilling: A Strategic ...
|
AI for Frontline Workforce Upskilling and Reskilling: A Strategic Imperative
|
https://www.anthill.co
|
[] |
AI presents both opportunities and challenges for frontline workers. On one hand, AI-driven automation can increase efficiency and productivity by taking over ...
|
In today’s rapidly evolving workplace, the role of artificial intelligence (AI) is no longer just a buzzword—it’s a catalyst for profound change. For frontline workers, this change brings both challenges and opportunities, underscoring the pressing need for upskilling and reskilling to remain competitive and adaptable. The integration of AI into daily operations is transforming job roles, with significant implications for the workforce, particularly those on the frontlines of industries ranging from manufacturing to retail.
The Growing Demand for Reskilling
Recent findings highlight the urgency of reskilling in AI-centric environments. According to a 2023 McKinsey report, organizations adopting AI anticipate that over 20% of their workforce will require reskilling to adapt to new technologies and processes. This percentage rises to more than 30% among high-performing AI companies—those that derive at least 20% of their earnings from AI-driven initiatives. These statistics underscore the sweeping impact AI is expected to have across various sectors, particularly in roles that are heavily reliant on routine tasks.
The World Economic Forum (WEF) supports this view, predicting that by 2025, 50% of all employees will need reskilling due to the rapid pace of automation and technological advancements. This statistic is not just a number; it represents a massive shift in the skills landscape, where the ability to adapt and learn new skills quickly will define the employability of the workforce. For frontline workers, who are often at the forefront of implementing these new technologies, this translates into an immediate and critical need to acquire the skills necessary to operate in increasingly AI-driven environments.
AI: A Double-Edged Sword for Frontline Workers
AI presents both opportunities and challenges for frontline workers. On one hand, AI-driven automation can increase efficiency and productivity by taking over repetitive tasks. According to the research, AI adoption has increased the potential for work automation from 50% to as much as 70%. This increase means that a significant portion of the tasks currently performed by frontline workers could be automated in the near future. However, rather than resulting in widespread job losses, this shift is driving a need for workers to be reskilled to take on new, more complex roles that require human judgment and creativity.
Despite the potential for automation, only 8% of companies expect significant reductions in their workforce. Instead, the focus is on reskilling workers to adapt to these new roles and responsibilities. For frontline workers, this means learning to work alongside AI, leveraging these tools to enhance their job performance rather than fearing job displacement. As the nature of work evolves, the ability to seamlessly integrate AI tools into daily tasks will become a key differentiator for frontline workers.
This shift is especially crucial for frontline workers, who often bear the brunt of technological changes. WEF says 55% of companies are investing heavily in these programs, aiming to enhance the adaptability and performance of their frontline teams in an increasingly AI-driven world. These investments are not just about keeping pace with technological change—they are about future-proofing the workforce against the disruptions that AI will inevitably bring.
Why Upskilling and Reskilling Matter
For companies, the benefits of upskilling and reskilling are clear: improved performance, reduced skill gaps, and a more agile workforce ready to tackle the challenges posed by AI. Upskilling initiatives equip frontline workers with the digital skills necessary to operate new technologies while reskilling programs prepare them for entirely new roles that may emerge as AI continues to evolve.
IBM’s Report (2023) emphasizes that over 40% of business executives see reskilling as vital to their organization’s future as a result of implementing AI and automation. This focus is particularly important for frontline workers and leaders, who need to prepare a blend of technical and soft skills to thrive in new, AI-enhanced workspace. Adaptability, problem-solving, and the ability to work alongside AI systems are becoming essential competencies in the modern workplace. These skills are not just about staying relevant—they are about seizing the opportunities that AI presents to enhance job satisfaction and career growth.
The Path Forward: Investing in the Frontline
As AI continues to permeate various industries, the shift towards upskilling and reskilling, particularly for frontline workers, is not just a strategic option—it is a necessity. Companies that invest in continuous learning initiatives are better positioned to ensure their workforce can adapt to rapidly changing job requirements. These initiatives are not just about technical training; they also involve fostering a culture of lifelong learning where employees are encouraged to develop new skills and embrace change.
In conclusion, as AI continues to reshape the landscape of work, companies that proactively invest in upskilling and reskilling their frontline workforce will not only bridge performance gaps but also secure a competitive edge in the marketplace. The future of work is here, and it’s powered by AI—those who prepare today will lead tomorrow. Frontline workers, equipped with the right skills, will be at the forefront of this transformation, driving innovation and delivering value in ways that were previously unimaginable. The time to act is now, and the benefits of doing so will resonate throughout the organization for years to come.
Reference:
[1] Jorge Amar, J., Cheta, O., Huang, I., & Xu, S. (2024, Aug 16). From promising to productive: Real results from gen AI in services. McKinsey & Company.
https://www.mckinsey.com/capabilities/operations/our-insights/from-promising-to-productive-real-results-from-gen-ai-in-services
[2] Chhabria, P. (2024, Jan 18). Davos 2024: 6 innovative ideas on reskilling, upskilling and building a future-ready workforce. World Economic Forum.
https://www.weforum.org/agenda/2024/01/davos-2024-6-innovative-ideas-for-reskilling-upskilling-and-building-a-future-ready-workforce/
[3] Goldstein, J. (2023, Aug 14). New IBM study reveals how AI is changing work and what HR leaders should do about it. IBM.
https://www.ibm.com/blog/new-ibm-study-reveals-how-ai-is-changing-work-and-what-hr-leaders-should-do-about-it/
| 2023-01-01T00:00:00 |
https://www.anthill.co/blog/ai-for-frontline-workforce-upskilling-and-reskilling-a-strategic-imperative
|
[
{
"date": "2023/01/01",
"position": 82,
"query": "reskilling AI automation"
},
{
"date": "2023/04/01",
"position": 83,
"query": "reskilling AI automation"
},
{
"date": "2023/10/01",
"position": 31,
"query": "reskilling AI automation"
},
{
"date": "2023/11/01",
"position": 85,
"query": "reskilling AI automation"
},
{
"date": "2024/04/01",
"position": 82,
"query": "reskilling AI automation"
},
{
"date": "2024/05/01",
"position": 82,
"query": "reskilling AI automation"
},
{
"date": "2024/06/01",
"position": 83,
"query": "reskilling AI automation"
},
{
"date": "2024/10/01",
"position": 86,
"query": "reskilling AI automation"
},
{
"date": "2024/11/01",
"position": 82,
"query": "reskilling AI automation"
},
{
"date": "2025/02/01",
"position": 78,
"query": "reskilling AI automation"
},
{
"date": "2025/04/01",
"position": 74,
"query": "reskilling AI automation"
}
] |
|
AI, Automation and Careers | The Career Innovation Company
|
AI, Automation and Careers
|
https://www.careerinnovation.com
|
[] |
The latest thinking on talent, reskilling and careers, all in one place. Pick the topic that interests you.
|
Taking care of your data
At Career Innovation we take data protection and your privacy seriously. We also use cookies to provide you with a better browsing experience.
Cookie information is stored in your browser and performs functions such as recognising when you return to our website. It also helps us understand which sections of the website people find most interesting and useful so we can improve it over time.
Some cookies are strictly necessary. These are required for our website to function properly and cannot be disabled.
Analytics cookies are optional and require your consent before we use them.
We do not use any targeting cookies.
| 2023-01-01T00:00:00 |
https://www.careerinnovation.com/trends/ai-automation-and-careers/
|
[
{
"date": "2023/01/01",
"position": 85,
"query": "reskilling AI automation"
},
{
"date": "2023/04/01",
"position": 92,
"query": "reskilling AI automation"
},
{
"date": "2023/05/01",
"position": 92,
"query": "reskilling AI automation"
},
{
"date": "2023/10/01",
"position": 46,
"query": "reskilling AI automation"
},
{
"date": "2023/11/01",
"position": 90,
"query": "reskilling AI automation"
},
{
"date": "2024/04/01",
"position": 86,
"query": "reskilling AI automation"
},
{
"date": "2024/05/01",
"position": 84,
"query": "reskilling AI automation"
},
{
"date": "2024/06/01",
"position": 85,
"query": "reskilling AI automation"
},
{
"date": "2024/10/01",
"position": 97,
"query": "reskilling AI automation"
},
{
"date": "2024/11/01",
"position": 85,
"query": "reskilling AI automation"
},
{
"date": "2025/04/01",
"position": 85,
"query": "reskilling AI automation"
}
] |
|
How Effective Is Reskilling In Addressing Job Losses From AI ...
|
How Effective Is Reskilling in Addressing Job Losses from AI? → Question
|
https://sustainability-directory.com
|
[
"Sustainability Directory"
] |
While AI might automate some analytical or monitoring tasks previously done manually, it simultaneously creates demand for roles involving AI system management, ...
|
Reskilling helps people learn new skills for jobs AI might create or require, addressing some job losses, but its effectiveness depends on many factors like access, speed, and the scale of AI-driven changes.
Understanding Reskilling amid AI Disruption The advent of artificial intelligence across industries presents a complex challenge to the global workforce. As AI systems become increasingly capable of performing tasks previously requiring human labor, certain roles face automation, leading to potential job displacement. Reskilling, the process of learning new skills to transition into a different job or career path, emerges as a primary proposed solution to mitigate these disruptions. Evaluating its effectiveness necessitates understanding the fundamental dynamics of AI’s impact on employment and the inherent nature of workforce adaptation. At its core, AI-driven job loss often occurs not through the complete elimination of entire professions overnight, but through the automation of specific tasks within those jobs. A data entry clerk, for instance, might see the repetitive task of inputting information automated by an AI, freeing them for other duties or potentially reducing the need for that specific role if those other duties are limited. This task-level automation requires a granular view of work and the skills associated with individual components of a job. Reskilling, therefore, must target the acquisition of skills that are either complementary to AI capabilities or are relevant to entirely new roles created by technological advancement or shifts in economic activity. Consider the sustainability sector, a domain increasingly leveraging AI for tasks like optimizing energy grids, analyzing environmental data, or improving supply chain efficiency. While AI might automate some analytical or monitoring tasks previously done manually, it simultaneously creates demand for roles involving AI system management, data interpretation, ethical AI deployment in sensitive contexts, and strategic planning based on AI-generated insights. Reskilling programs Meaning → Reskilling Programs in sustainability are focused training initiatives designed to provide individuals with updated skills pertinent to ecological and social responsibility. in this context could focus on training energy analysts in AI-driven modeling software or teaching logistics managers how to integrate AI optimization tools ethically and effectively. Reskilling programs offer a pathway for individuals to acquire skills necessary for jobs less susceptible to AI automation or those newly created by technological shifts. The effectiveness of reskilling is not a simple binary outcome; it is contingent upon several interacting factors. These include the accessibility of training programs, the relevance of the skills taught to actual labor market Meaning → The labor market, in a sustainability context, encompasses the supply and demand for workers in sectors promoting environmental protection, social equity, and economic viability. demand, the cost and duration of the training, and the individual’s capacity and willingness to learn and adapt. Furthermore, the pace of AI development means that the target skills for reskilling are themselves moving targets, requiring educational systems and training providers to remain agile and responsive. Does AI Eliminate All Jobs
AI tends to automate tasks within jobs rather than eliminating entire professions, shifting required human skills. From a human perspective, the emotional and psychological impact of potential job loss cannot be overstated. Reskilling programs must consider not just the technical aspects of learning but also provide support for individuals navigating career transitions, addressing potential anxieties, and building confidence in their ability to acquire new competencies. A holistic approach acknowledges that adapting to AI is a socio-technical challenge, requiring support for human resilience alongside skill acquisition. Ultimately, the foundational effectiveness of reskilling in this context rests on its ability to bridge the gap between the skills AI makes redundant and the skills the future economy demands. It is a necessary component of workforce adaptation, though its success hinges on thoughtful design, broad accessibility, and continuous evolution.
Evaluating Reskilling Initiatives across Sectors Moving beyond the foundational concepts, a deeper evaluation of reskilling’s effectiveness in addressing AI-induced job losses requires examining its implementation across diverse sectors and considering the scale and speed of technological change. The challenge is not uniform; AI’s impact varies significantly depending on the industry’s structure, the nature of its work, and the existing skill base of its workforce. A nuanced perspective reveals that while reskilling is a critical tool, its efficacy is modulated by systemic factors and requires coordinated effort from individuals, employers, educators, and policymakers. Different sectors face distinct challenges. Manufacturing, for instance, sees automation replacing routine manual tasks, necessitating reskilling towards roles in robotics maintenance, data analysis for process optimization, or advanced manufacturing techniques. The financial sector experiences AI automating data processing and algorithmic trading, requiring professionals to pivot towards roles focused on complex analysis, ethical AI application in finance, and client relationship management demanding high emotional intelligence. Consider a case study in the renewable energy sector, where AI is increasingly used for predictive maintenance of solar panels or wind turbines. Technicians who previously performed routine manual checks might need reskilling in data analytics, remote monitoring systems, and specialized software interfaces. An effective program here would involve collaboration between energy companies, equipment manufacturers, and technical colleges to design curricula that align directly with the new technical demands of AI-integrated infrastructure. The success metric extends beyond simply completing the training; it involves tracking re-employment rates in relevant roles and the sustained earning potential of reskilled workers. The effectiveness of reskilling programs is deeply intertwined with their alignment to specific industry needs and the broader economic landscape shaped by AI adoption. The speed of AI advancement presents a significant hurdle. Traditional educational and training cycles can be lengthy, potentially lagging behind the rapid evolution of required skills. This necessitates a shift towards more modular, flexible, and just-in-time learning approaches. Micro-credentials, online platforms, and employer-led training initiatives become increasingly important complements to formal education. How Fast Are Skills Changing Due to AI
Skills required in the workforce are evolving rapidly due to AI adoption, demanding continuous learning and adaptation. Sustainability offers a compelling lens through which to view reskilling’s broader impact. Job displacement from AI can exacerbate social inequalities if access to reskilling is unevenly distributed. Effective reskilling initiatives must consider equity, ensuring programs are accessible to vulnerable populations, including older workers, those in rural areas, and individuals from disadvantaged backgrounds. A just transition in the age of AI requires that the benefits of automation do not accrue solely to a skilled elite, leaving others behind. Furthermore, reskilling can contribute to environmental sustainability by preparing the workforce for green jobs. As economies transition towards low-carbon models, new roles in renewable energy, sustainable construction, circular economy management, and environmental data analysis emerge. Reskilling programs that specifically target these areas contribute to both workforce resilience and environmental goals. The corporate perspective highlights the strategic importance of reskilling. Companies adopting AI need employees who can work alongside these technologies. Investing in reskilling can be more cost-effective than external hiring, fostering employee loyalty and preserving institutional knowledge. However, this requires a proactive approach to workforce planning and a willingness to invest significantly in human capital development. Factors Influencing Reskilling Effectiveness Factor Description Impact on Effectiveness Skill Alignment Relevance of skills taught to market demand. High alignment increases job placement likelihood. Accessibility Ease of access (cost, location, prerequisites). Low accessibility limits reach, potentially exacerbating inequality. Pace of Change Speed of AI development vs. training duration. Rapid change requires agile, modular training. Learner Support Provision of career counseling, financial aid, emotional support. Enhances completion rates and successful transition. Employer Engagement Company investment, job placement pipelines. Directly links training to employment opportunities. In sum, while reskilling is indispensable for navigating the AI-driven labor market transformation, its effectiveness is a function of its design, reach, responsiveness to change, and integration within broader social and economic strategies. It is a complex undertaking requiring collaboration and a commitment to equitable access.
Analytical Frameworks for Assessing Reskilling Efficacy in the AI Era A rigorous academic examination of reskilling’s effectiveness in the face of AI-induced job losses necessitates employing sophisticated analytical frameworks that move beyond descriptive accounts to probe underlying mechanisms, systemic interactions, and long-term implications. This inquiry requires synthesizing perspectives from labor economics, educational theory, technology studies, and organizational behavior, often filtered through lenses such as human capital theory, task-based models of automation, and theories of institutional change. Our analytical strategy here employs a multi-method integration, combining conceptual analysis to define and delimit the scope of “reskilling effectiveness,” evaluative perspective to weigh different outcomes and impacts (economic, social, individual), and implication analysis to project potential future trajectories and policy requirements. This approach acknowledges that effectiveness is not solely measured by immediate job placement Meaning → Sustainable job placement strategically aligns human capital with roles fostering ecological integrity, social equity, and long-term economic resilience. rates but encompasses broader considerations such as wage trajectory, job quality, skill transferability, and contributions to societal resilience and sustainability goals. A key assumption underpinning the focus on reskilling is the notion of labor market fluidity → the idea that displaced workers can, with appropriate intervention, transition to new roles. However, scrutiny of this assumption reveals potential limitations. Structural barriers, such as geographic immobility, age discrimination, or fundamental cognitive differences, can impede successful transitions regardless of training availability. Furthermore, the “skills gap” narrative, often used to justify reskilling, sometimes oversimplifies the issue, potentially overlooking insufficient job demand or structural economic shifts as primary drivers of unemployment. Evidence from various studies, while fragmented, suggests heterogeneous outcomes. Some reports indicate positive results for targeted reskilling programs in specific high-demand fields, demonstrating improved employment rates and wage gains for participants. Other analyses highlight challenges, including low program completion rates, difficulty in matching training outputs to actual job openings, and the risk of training for skills that quickly become obsolete. Assessing reskilling effectiveness requires a multi-dimensional approach, considering not just job placement but also long-term career trajectory and societal equity. The task-based model of automation provides a useful analytical tool. Instead of predicting which jobs will disappear, this model analyzes which tasks within jobs are most susceptible to automation (typically routine, predictable tasks) and which are complementary to AI (requiring creativity, complex problem-solving, social intelligence). Effective reskilling programs, from this perspective, must focus on augmenting human capacity in these complementary task domains, fostering skills that leverage, rather than compete with, AI capabilities. What Skills Are Most Complementary To AI
Skills involving creativity, complex problem-solving, critical thinking, and social intelligence are highly complementary to AI. From a sustainability governance perspective, the efficacy of reskilling is tied to the capacity of public and private institutions to coordinate and adapt. This involves labor market information systems that accurately forecast skill needs, educational institutions capable of rapidly developing and delivering relevant curricula, and social safety nets that support individuals during transition periods. The potential for AI to exacerbate existing inequalities raises critical questions about the ethical obligations of technology developers, employers, and governments to ensure a just transition for the workforce. The concept of “employability” itself warrants critical analysis. It is not a static attribute but a dynamic interaction between an individual’s skills and capabilities, the structure of the labor market, and institutional support systems. Reskilling enhances an individual’s potential employability, but this potential can only be realized within an economic context that generates sufficient suitable job opportunities. Moreover, the philosophical implications of AI-driven automation and reskilling touch upon fundamental questions about the nature of work, human purpose, and societal value beyond economic productivity. While reskilling addresses the immediate challenge of employment, a deeper inquiry considers how societies can adapt to potentially lower overall labor demand through mechanisms like revised social contracts, alternative forms of value creation, or redefinitions of work itself. This moves into Level 6 aspiration, exploring the epistemological shifts required to conceive of a future where human contribution is valued in ways not solely tied to traditional employment structures. Ultimately, evaluating reskilling effectiveness Term → Effective reskilling for sustainability means successfully gaining skills for a green, equitable future. requires longitudinal studies tracking career trajectories, robust data on program accessibility and completion by demographic group, and interdisciplinary analysis integrating economic models with sociological and psychological insights. It is an ongoing, complex assessment within a rapidly changing technological and societal landscape.
| 2023-01-01T00:00:00 |
https://sustainability-directory.com/question/how-effective-is-reskilling-in-addressing-job-losses-from-ai/
|
[
{
"date": "2023/01/01",
"position": 88,
"query": "reskilling AI automation"
}
] |
|
Reskilling Your Workforce for the Future: An HR's Guide - AIHR
|
Reskilling Your Workforce for the Future: An HR’s Guide
|
https://www.aihr.com
|
[
"Andrea Boatman",
"Andrea Boatman Is A Former Shrm Certified Hr Manager With A Degree In English Who Now Enjoys Combining The Two As An Hr Writer. Her Previous Positions Were Held With Employers In The Education",
"Healthcare",
"Pension Consulting Industries."
] |
As the use of generative AI, chatbots, virtual assistants, machine learning, natural language processing, and automation increases, some roles will become ...
|
Findings from the World Economic Forum’s Future of Work Report suggest that 59% of employees will need reskilling or other types of work training by 2030. Ensuring your workforce has the right skills to thrive in their roles and preparing them to transition into emerging roles enables your organization to stay productive, innovative, and profitable.
In this article, we explore what reskilling is, how it differs from upskilling, why reskilling employees matters, and how to successfully reskill your workforce as jobs continue to be disrupted by market forces and evolving technology trends.
Contents
What is reskilling?
What are the benefits of reskilling your employees?
Why are companies failing at reskilling?
Reskilling examples
How can your organization build a successful reskilling program?
FAQ
What is reskilling?
Reskilling is the process of employees learning new skills to transition into a different job or career, typically in response to changes in the job market or workplace needs. Unlike upskilling, which builds on existing skills for career advancement, reskilling prepares employees for roles that may be in entirely different fields—frequently in emerging areas like AI, cybersecurity, or renewable energy.
For example, a retail sales associate who trains in logistics to shift into supply chain management, or a factory worker who learns machine learning fundamentals to move into an AI-driven quality control role.
Research by the University of Queensland estimates that people entering the workforce today will take on between 16 and 17 jobs over five to seven different careers, with each career change potentially requiring employees to build a new skill set. Therefore, it’s essential that employers prepare for the future world of work now and create and implement training programs to successfully reskill their employees.
Although the process of reskilling can appear daunting, rapid advances in artificial intelligence and generative AI are making (and will continue to make) many roles and responsibilities redundant. Businesses must align with these changing demands and help employees remain relevant and useful in their careers.
Reskilling vs upskilling
The terms “reskilling” and “upskilling” are sometimes used interchangeably as there is a lot of crossover between these two concepts. However, there is one primary difference.
Reskilling is the process of training employees in new skills and capabilities to help them transition into a different role, either within the same organization or in a new industry. Upskilling, on the other hand, focuses on developing employees’ existing skills to help them adapt to changes in their current role or advance within their field.
Example of upskilling: An HR professional completes a course in digital HR and automation to help analyze, optimize, and automate HR processes in their organization to increase efficiency and reduce errors.
An HR professional completes a course in digital HR and automation to help analyze, optimize, and automate HR processes in their organization to increase efficiency and reduce errors. Example of reskilling: A school teacher trains in instructional design and corporate learning strategies to transition into a role as a corporate trainer, delivering professional development programs for businesses.
Employees can upskill through various forms of training and education, such as online courses, webinars, workshops, seminars, professional certifications, and industry publications. They may also pursue formal education by earning a degree or diploma, enrolling in intensive boot camps or training programs, or gaining hands-on experience through internships or part-time work.
Reskilling, which involves learning entirely new skills for a different role or industry, often requires more in-depth training. This can include structured programs such as career transition courses, employer-sponsored retraining initiatives, apprenticeships, or immersive boot camps. While the methods for upskilling and reskilling are often similar, upskilling is typically easier to do on the job, as it builds on existing skills rather than requiring a complete career shift.
Organizations often use both reskilling and upskilling strategies to support internal mobility and equip their workforce with the skills needed for the future.
Build a reskilling strategy that works The demand for new skills is growing—are your employees ready? You need to create a learning strategy that truly prepares your workforce for the future. AIHR’s Learning & Development Certificate Program equips you with the knowledge and skills to build high-impact learning initiatives, improve employee learning experience, and future-proof your organization. GET STARTED
What are the benefits of reskilling your employees?
The rapid growth and adoption of technology have significantly changed how businesses operate, and the future of work is hard to predict. As the use of generative AI, chatbots, virtual assistants, machine learning, natural language processing, and automation increases, some roles will become obsolete, but this will give way to new occupations with a larger focus on human-centered skills such as creativity, strategic thinking, and emotional intelligence.
According to a McKinsey Global Institute report, as many as 375 million workers may need to switch occupational categories by 2030, hence why reskilling programs must be taken seriously by organizations and rolled out sooner rather than later. Reskilling helps manage change and navigate future workforce planning efforts by retraining your workforce for what lies ahead and putting employees’ talents to use in crucial new roles.
Reskilling has benefits for both the organization and its employees. Let’s take a look at these in more detail.
Improves employee retention
The current job market is highly competitive, and job-hopping is a widely acceptable way to advance a career. The opportunity to learn and grow in a position helps employees stay focused on their current employer instead of contemplating new prospects.
Investing in skills training shows workers they have present and future value within the company. Employers need to provide ample development opportunities to attract and retain top talent.
Reduces the cost of filling new roles
Recruiting expenses and lost productivity affect your company’s bottom line. Filling openings internally helps reduce these costs.
Reskilling increases employees’ value by preparing them for an alternative role within your organization. When a new position opens up, someone in your workforce will have the skills needed to step in and keep operations running smoothly.
Drives productivity and profitability
According to a report by TalentLMS, businesses with a healthy training ecosystem are 52% more productive, 92% more innovative, and 17% more profitable than competitors. The message? When employees receive effective training they are hungry for, they are more effective in their jobs and contribute more to business objectives.
Attracts new talent with a growth mindset
A Gallup report revealed that 59% of millennials rank learning and growth opportunities as extremely important to them when looking for a job. Your organization’s dedication to improving employees’ skills can be an advantage when sourcing and hiring motivated applicants.
Your current employees who appreciate the benefit of a learning culture will also fortify your employee brand when they speak highly of their experience. Their positive feedback can result in desirable candidates applying for your open positions.
Supports employee engagement
When employees feel overlooked or disconnected from the organization, they become disengaged from their work. Providing opportunities for skill development helps them expand their expertise, collaborate with other departments, and feel more integrated into the company.
What’s more, gaining insight into different roles fosters empathy and camaraderie, reducing siloed thinking and an “us versus them” mindset.
Gives employees a vision for advancing with you
Reskilling opportunities are steps forward on a career path and provide your workforce with new talents they can utilize in emerging roles. You’re giving employees a clear vision for growing and advancing within your organization, which is a priority to many, and building a strong internal pipeline for promotions and lateral moves.
Boosts employees’ confidence and morale
Employees who are confident in their skills and abilities are more likely to be proactive, voice new ideas, and devise creative solutions to problems. A study showed that 80% of employees believe their confidence had improved from reskilling training.
Building confidence in certain employees can also tap into underutilized talent. Introverts, or those who fall into underrepresented groups, may be overlooked but will often have much to offer when they feel assured in their abilities.
Increases employability
BCG data shows that 68% of workers are already aware of the looming disruptions in their respective fields and are willing to reskill to remain valuable and competitively employed. Reskilling helps employees stay current in their industry, boosts their value to employers, and allows them to become increasingly flexible, which is a valuable skill.
Reskilling employees will help increase their employability now and in the future.
Satisfies employees’ desire to learn and grow
71% percent of employees want to update their skills more frequently, while 80% think their employers should increase their investment in reskilling and upskilling. The majority of the workforce is eager to learn and grow, and providing reskilling opportunities meets this desire while future-proofing the organization for changes and disruptions to roles.
Discover the nine steps to take to reskill your workforce for the future in this Learning Bite!
Why are companies failing at reskilling?
A report by TalentLMS found that organizations tend to be better at upskilling than reskilling, with employee satisfaction levels at 73% when receiving upskilling versus 62% for those who participated in reskilling initiatives.
This suggests that while roles (and the skills needed for them) are evolving, many organizations are not yet taking steps — or are struggling — to transition employees into new roles. Let’s explore some of the challenges businesses face when reskilling the workforce.
Poor change management
Some businesses fail to effectively plan, implement, manage and communicate the changes they face as a result of the market and advancing technology. They don’t take proactive steps to prepare for the future world of work and don’t adequately support employees through these uncertain times and changes, which can have a catastrophic effect on a business.
Misunderstood skills gaps and training needs
Addressing skills gaps requires a strategic approach to pinpoint the most essential skills that are lacking, then create a targeted training program to bridge these gaps. For example, many employees lack skills like digital literacy, AI, data analysis and soft skills that are becoming increasingly important.
Lack of learning culture
One of the biggest reasons companies struggle with reskilling is the absence of a strong learning and growth culture. When organizations don’t prioritize continuous employee development, workers may not see opportunities to expand their skills or advance in their careers. Personal and organizational growth are closely linked, and a workplace that fosters learning ensures both employees and the company evolve together.
To make reskilling successful, organizations should create a culture where continuous learning is the norm, with clear development plans that align individual growth with business goals.
Limited resources
Another core challenge businesses face is a lack of time for reskilling programs, as employees also have their daily responsibilities to manage. Additionally, rapid market changes can create a sense of urgency around reskilling and put pressure on employees and employers.
There are also costs to consider aside from training materials and new technology, including the time employees take away from their existing tasks. HR plays a key role in justifying these costs by demonstrating the return on investment to business leaders.
Cultural resistance
Finally, employees (and employers) are often resistant to change, which can make reskilling difficult. Employees have an existing skill set that is in their comfort zone, and significant effort is required to gain new skills and pivot into a new role. The way to overcome this hurdle is by fostering a supportive environment where employees are encouraged to grow and the benefits of reskilling are clearly communicated.
Reskilling examples
Example 1: AT&T
Amid rapid technological advancements, AT&T faced a critical challenge: a large portion of its workforce had skills tied to outdated technologies, putting both employees and the company’s future at risk. Instead of relying solely on external hiring, AT&T launched Workforce 2020, a $1 billion reskilling initiative aimed at transitioning employees into high-demand roles.
Through online courses, collaborations with universities, and internal training programs, employees were reskilled from legacy roles in hardware maintenance and landline operations into fields like cloud computing, data science, and cybersecurity. By 2018, more than 50% of AT&T’s workforce had moved into new tech-focused positions, proving that large-scale reskilling isn’t just possible — it’s a strategic necessity in a fast-changing job market.
The initiative has since been rebranded to “Future Ready”, and AT&T continues to invest in reskilling the workforce.
Example 2: Zurich UK
Using the AI analytics platform Faethm, Zurich UK, a branch of the global insurance company, identified specific skills that would be more in demand in the future due to technological advances, along with as many as 270 roles that would go unfilled in the next five years within data, robotics, and cyber sectors.
As a result, the company developed learning academies in key areas, including data, automation, leadership, and innovation, to reskill employees to take on these roles where talent (internal and external) is scarce. The company estimates that the long-term reskilling and upskilling of talent will save £1 million in recruitment and redundancy costs.
Example 3: Siemens
Having faced skills shortages in technical fields, Siemens launched their SiTecSkills Academy in 2022 to bridge the gap between their workforce’s skillsets and the needs of the industry.
Employees in production, service, and sales are targeted to build future competencies within the sectors of IoT, AI, robotics, and sustainability. The academy offers a mix of reskilling and upskilling opportunities through a variety of formats including brief digital learning “nuggets” (that are also available for free to people outside of the company) through to certification programs.
Since its launch, the Academy has reached more than 24,000 people with a primary focus on building digital and green skills essential for Siemens. Post-training reviews after six months show almost a 100% success rate in reskilling programs. Approximately 40% of participants are women, demonstrating Siemens’ commitment to gender inclusivity in traditionally male-dominated fields.
How can your organization build a successful reskilling program?
A strong reskilling program closes skills gaps to support your workforce and the organization, and it often integrates with an upskilling program. Usually, it is a company-wide effort in which HR plays a key role.
You can use the following steps to build and maximize the effectiveness of your reskilling program.
Let’s break it down.
1. Make reskilling a strategic necessity across the business
In many businesses, HR owns the reskilling agenda, with 65% of organizations viewing reskilling primarily as an HR function.
This suggests there is much room to make reskilling a more collaborative, company-wide approach where reskilling is embraced across the leadership team. The most successful reskilling programs require commitment from HR and the wider organization, which is why this is key.
HR has a responsibility to demonstrate the need for reskilling and tie this to business objectives to gain buy-in from stakeholders.
2. Uncover skills gaps
Once you map out your organization’s long-term goals and what it takes to achieve them, you need to assess how well your current roles and workforce are equipped to support these objectives. This means identifying any gaps between the skills employees have and the skills their roles require.
An updated skills inventory of what your employees have to offer can reveal secondary and tertiary skills. You can use it in conjunction with a skills gap analysis to help you determine the specific skills and knowledge your workforce is missing.
3. Look for skill adjacencies
Once you have identified the critical skills needed, look for adjacent abilities, or “skills closely matched to those in demand,” to make the task of reskilling a little easier. Employees with related competencies may already have the right attributes, or can quickly learn what they need to for a new role.
For example, someone with customer/client service experience can make a smooth transition into sales because they have strong communication skills and first-hand knowledge of your product or service.
With the growing popularity of online banking, banks in Singapore are reskilling their frontline staff to be able to work in customer contact centers.
4. Organize specific skills training
Once you understand which skills in which departments you need to develop, you can determine the exact training required for your employees to develop these skills.
Since there will be variance within your employees’ skill sets, trainings must be somewhat personalized to meet different learning needs. Offering an assortment of training methods is ideal. Your current learning platform may not be sufficient for certain types of reskilling, so it could be time to invest in other resources.
Internal company bootcamps are an example of how organizations frequently reskill employees from nontech roles to technical ones. These employees are then equipped to tackle company-specific challenges.
5. Combine a variety of reskilling methods
You should have several education delivery techniques in place to ensure flexibility and options that work best for different learning styles and the type of skill gap you aim to address. The more training occasions and methods you offer, the higher participation will be.
Examples of these methods include:
On-the-job training : Employees can have real-world exposure to the tasks of a new role by taking on small projects for another team or through a mentoring relationship.
: Employees can have real-world exposure to the tasks of a new role by taking on small projects for another team or through a mentoring relationship. Online learning : Online courses are beneficial because they are accessible anytime and anywhere to speed up the learning process. Bite-sized learning is advantageous as it concentrates on the specific information needed to achieve a learning objective. It’s also easy for all types of learners to grasp.
: Online courses are beneficial because they are accessible anytime and anywhere to speed up the learning process. Bite-sized learning is advantageous as it concentrates on the specific information needed to achieve a learning objective. It’s also easy for all types of learners to grasp. Blended learning : Combining online learning with classroom training assures all material is covered. It also provides the opportunity for learners to ask questions and interact with an instructor.
: Combining online learning with classroom training assures all material is covered. It also provides the opportunity for learners to ask questions and interact with an instructor. Peer learning: Employees can learn from each other when they collaborate and reflect on real-world scenarios or hands-on practice of new tasks.
If your organization has remote or hybrid employees, remember to apply remote training methods to reskill this sector of your workforce.
Invest time in understanding how your employees learn best, their preferences for reskilling, and potential benefits.
6. Make reskilling programs attractive
32% percent of businesses face challenges in convincing employees to apply for and complete reskilling programs, which is why it’s crucial that your reskilling programs are desirable.
It’s important that reskilling is presented as a choice and not a requirement, However, to increase participation, organizations must highlight to employees the benefits and shared value of reskilling. It’s also important to offer training during work hours — 64% of businesses who do so entirely within paid work hours almost eliminate one of the biggest hurdles to participation. It demonstrates that your organization values employees’ time and your commitment to continuous growth.
You may also want to consider incentives to reward those willing to learn and grow, and make it clear that reskilling is linked to new prospects or advancement within the company. This way, your employees will be more motivated to participate.
7. Promote job shadowing
Job shadowing is an excellent way for employees to familiarize themselves with a new role within or across departments. Following and observing an experienced employee throughout their day gives an accurate portrayal of the job requirements.
In essence, job shadowing helps better prepare someone to take on a new position. Plus, it is a great reskilling method if you’re on a tighter budget.
8. Focus on digital skills
Companies that were forced to have employees work from home during the pandemic quickly learned how integral technology was to business and how vital adequate digital skills were. Digital advancement is an ongoing reality, so businesses must prepare their employees to adapt to new technologies.
Reskilling in the age of AI is vital as more repetitive, admin-based tasks become automated and certain roles become obsolete. More roles focusing on managing AI technologies and analyzing data will emerge, as well as roles that primarily utilize human-centered skills such as creativity, empathy, and leadership.
Effectively training the workforce in digital literacy and preparing them to use new tools will help organizations close the digital skills gap. Your reskilling program should prepare your workforce for the age of AI so that no one gets left behind.
9. Measure and evaluate success
Research shows that just 33% of companies measure their reskilling programs’ impact on business or HR-related outcomes, and although 42% report a positive ROI, 56% did not calculate or could not identify the ROI of their reskilling initiatives.
Are your employees applying the new skills they’ve learned? Are they able to smoothly transition into new roles and perform at high levels? What is the return on investment of your reskilling programs, and do they make business sense?
Measuring training effectiveness is essential and begins with determining relevant KPIs, collecting data from various sources (including surveys, discussions, and post-training assessments), and regularly assessing the data using an evaluation model.
The well-known Kirkpatrick’s Four-Level Training Evaluation Model uses learners’ reactions and responses, knowledge and skills obtained, behavioral changes made, and the impact on business goals to measure the extent of a training program’s influence.
By measuring and evaluating your reskilling program, you can improve what’s not working, and determine if you have achieved your strategic objectives.
10. Encourage lifelong learning
Reskilling is an ongoing process, so your organization needs to foster a continuous learning culture. You can instill a knowledge-seeking mindset in your employees by encouraging them to embrace reskilling opportunities and showing them why this matters and how it benefits them and their careers.
Managers must buy into the value of reskilling, and they should actively participate in their own trainings. Make sure leadership understands the importance of developing their staff, so they will wholeheartedly promote your reskilling endeavors.
11. Don’t neglect your own skills
HR is changing rapidly too, so new skills are required to stay current. As an HR professional, you need to prioritize your own development, and embarking on a reskilling (and upskilling) program in your department is a great place to start.
Upgrading your abilities with advanced HR technologies, people analytics, data literacy, and business acumen will future-proof your skills, give you a competitive edge, and set you and your organization up for long-term success.
A final word
Reskilling is an essential strategy to bridge skills gaps and ensure your employees are well-equipped to contribute to your organization’s goals and mission today and in the future.
Understanding where your company is headed, the skills required as technology transforms the world of work, and acquiring new skills that make your employees more valuable prospects are all key to building an effective reskilling program that equips and empowers your workforce and organization to thrive in uncertain times.
FAQ
What does reskilling mean? Reskilling is the process of employees building new skills with the aim of transitioning into a new role, industry, or career path. Why is reskilling important? Reskilling is important because it benefits employees and the wider organization. Reskilling initiatives can improve retention rates, reduce the cost of filling new roles, drive productivity and profitability, support employee engagement, and help companies attract talent with a growth mindset. From the employee’s perspective, reskilling satisfies an employee’s desire to learn and develop new skills, improves their confidence, and increases their employability. What is the difference between reskilling and upskilling? The key difference between reskilling and upskilling is that reskilling helps employees build new skills so they can transition into a different role or career path, whereas upskilling helps employees build on and develop existing skills to help them perform better in their existing role or career path.
| 2025-03-14T00:00:00 |
2025/03/14
|
https://www.aihr.com/blog/reskilling/
|
[
{
"date": "2023/01/01",
"position": 94,
"query": "reskilling AI automation"
},
{
"date": "2023/02/01",
"position": 99,
"query": "reskilling AI automation"
},
{
"date": "2023/04/01",
"position": 94,
"query": "reskilling AI automation"
},
{
"date": "2023/05/01",
"position": 91,
"query": "reskilling AI automation"
},
{
"date": "2023/10/01",
"position": 91,
"query": "reskilling AI automation"
},
{
"date": "2024/04/01",
"position": 97,
"query": "reskilling AI automation"
},
{
"date": "2024/05/01",
"position": 99,
"query": "reskilling AI automation"
},
{
"date": "2024/06/01",
"position": 94,
"query": "reskilling AI automation"
},
{
"date": "2024/10/01",
"position": 98,
"query": "reskilling AI automation"
},
{
"date": "2024/11/01",
"position": 96,
"query": "reskilling AI automation"
},
{
"date": "2025/03/14",
"position": 9,
"query": "reskilling AI automation"
},
{
"date": "2025/04/01",
"position": 90,
"query": "reskilling AI automation"
}
] |
The Future of Work in an AI-Driven World
|
The Future of Work in an AI-Driven World: How Will Generalists and Specialists Fare?
|
https://medium.com
|
[] |
As AI continues to shape the future of work, the question arises: Who will rise to the challenge & come out on top? We are witnessing AI growth ...
|
The Future of Work in an AI-Driven World: How Will Generalists and Specialists Fare? Jayaprakash 7 min read · Jan 21, 2023 -- Listen Share
As AI continues to shape the future of work, the question arises: Who will rise to the challenge & come out on top? We are witnessing AI growth exponentially around us, Will it be the versatile generalists or the specialised experts? I’m rooting for generalists, lets see why
Generalists vs Specialists (image credit: Nexford university)
Why generalists over specialists ?
Take the example of playing chess, it’s important to understand that the game has set of rules and recognisable patterns. With time and practice, one can master the game and become a specialist in the field of chess.
However, chess has always been played in the same way, and it will continue to be played that way unless someone changes the rules of the game. As long as it stays same, it can easily be automated by an AI engine because of its logical and predictable nature. In a matter of minutes, the AI can learn and master the patterns and strategies that a human player may take years to understand. As a result, the AI can now play against other AI’s and even teach the game without human assistance.
I bring this up because anything that is static or operates within defined boundaries, repetitive tasks can be automated. This puts specialists at risk, as their expertise in a specific field or task may no longer be necessary with the advent of automation.
In your whole professional life, If your skillset is limited to specific tasks such as customer service, working in a call centre, or utilising a specific programming language for data analysis or financial pattern recognition, or copy writer etc, you may be at risk of being replaced by an AI-based tool.
AI being the master of all trades:
Now these AI tools are significant threat to jobs that involve repetitive tasks. This is particularly true for developers/coders, whose jobs rely heavily on logic, recognisable patterns & mathematical formulas, which can easily be replicated or learned by AI. It is happening now and we already witnessing AI writing the code.
It’s important to note that AI’s ability to automate certain tasks does not come at the cost of its proficiency in other areas. For example, an AI can excel in software development while simultaneously being an expert chess player (like above example), or a proficient financial data analyst. This poses a significant challenge for professionals in these fields as they risk being replaced by machines that can do their job better and faster.
Talking about AI writing code,..
I recently came across a tweet from Andrej Karpathy, AI dev & famous figure in the field of AI development, a computer scientist. He previously worked as the director of AI and Autopilot Vision at Tesla, and this specific tweet in question caught my attention.
GitHub Copilot is a cloud-based artificial intelligence tool developed by GitHub & OpenAI to assist coders
Imagine a seasoned professional in the field of AI, with extensive experience at Tesla, saying that “it’s hard to imagine going back to manual coding.” the implication being that AI-based tools now handle the majority of code-writing, leaving human coders to focus on editing and fine-tuning.
Now, consider a young, aspiring coder who has just graduated from college and invested significant time and resources into training. What would this individual think upon reading such a statement?
It’s difficult to know for certain, but let me guess.. they may question the entire point of their education and wonder if they just wasted their time and resources. But, the silver lining is that they could always adapt and evolve to become a better coder in the age of AI, learning new methods, new tools.
This could involve learning & working closely with AI, not only coding learning other domains and expanding their skillset to become a generalist rather than a specialist. By doing so, they may increase their chances of success and survival in a competitive world.
“survival of the fittest”,.. harsh truth but thats how capitalistic societies work. it pushes you to work harder, we are at the beginning of the AI curve”
Moving towards wicked environments:
In the 20th century, specialists were at the forefront of knowledge, innovation, and invention. However, in the Information Age we find ourselves in now, technological advancements such as personal computers and smartphones have made it easier for information to spread rapidly and for generalists to access a vast pool of world knowledge. People who can adapt and demonstrate their “range” by taking information from one area and applying it to another have become increasingly valued.
Read this book to know more about generalists vs specialists
In the book “RANGE” by David Epstein, he explains that the world is running on a spectrum from of one type of learning environment to another environment:
Kind environments, characterised by clear rules, repetitive patterns, and unchanging tasks. Specialists whose jobs are at risk fall under this category. Wicked environments, characterised by obscure data, no rules, constant change, and abstract ideas. Generalists who can adapt and excel across different skillsets fall under this category.
As the world and the work we do evolves, we are moving towards wicked environments, characterised by ambiguity, subjectivity, and the need for human touch.
In this age of AI, we will need more individuals who possess a broad range of skills, and can think creatively and abstractly in order to navigate these ever-changing conditions.
While AI is capable of performing tasks that were once exclusive to specialists, it is not yet able to replicate the human ability to interpret and understand abstract concepts and ideas. As we move towards a more complex and dynamic world, there will be a greater emphasis on soft skills such as creativity, emotional intelligence, and the ability to collaborate and bring ideas together. This is where human touch will play an irreplaceable role, and where generalists will thrive.
For the wicked world, You should have more broader training base in your mind, so you can bent abstract ideas, obscure ideas for the current world as the world changing itself.
Designs and art pieces can be interpreted in countless ways, making it a challenging task for AI to replicate. While it may be difficult for humans to view an art piece from multiple perspectives, it is even more so for AI as long as the desired outcome is abstract. AI is not capable of thinking in the same way as humans do when it comes to interpreting abstract concepts.
Shifts & modifications that are on the horizon:
You might disagree with my previous statement that AI is not as capable as humans when it comes to interpreting abstract concepts. However, it’s worth noting that we already have AI generators like Midjourney, Dall-E 2, and Stable Diffusion, which are popular among both artists and non-artists to produce art and designs by simply entering text prompts.
Artwork generated through Midjourney AI
This raises the question, who do you think has an edge when it comes to creating the best art? A person who is only proficient in illustration, or a person who is an architect but also has knowledge and experience in fields such as fine art, creative writing, medieval history, and visual design? Clearly, the latter person would have an advantage and be able to create better art and adapt more easily.
In every profession, the only limits are the user’s imagination and the models used in the process. We are seeing a shift where traditional roles such as writing, coding, and art and design are becoming more about editing and generative art.
This is a paradigm shift and we can expect to see more legacy jobs in the tech industry being phased out in the future.
Whats next?
It is impossible to predict the future with certainty, but I believe that even though generalists have an advantage over specialists, we need both in order to progress in this Information Age.
Similar to OpenAI, many more AI engines may be developed in the future. Who knows which billion-dollar company is secretly working on an AI engine or what advancements Apple or Google have in store for us in the field of AI? As more AI products are created by utilising APIs of AI engines, companies and even nations may compete for access to data.
The more one thinks about it, the more questions arise — will we ever achieve artificial consciousness and technological singularity in the distant future? If we continue to rely on AI to perform tasks and make decisions, what will be left for humans to create? Mmm.. Perhaps this is a topic for another blog.
It is possible that new job opportunities will arise and the lines between professions will become blurred.
We have already begun to unconsciously or consciously outsource our thinking to the internet, much like how Google has become a fundamental part of our daily lives. It is likely that something similar will occur with AI in the future.
The best course of action is to be prepared for it.
Thank you for reading this :)
| 2023-01-21T00:00:00 |
2023/01/21
|
https://medium.com/@jai.designer/the-future-of-work-in-an-ai-driven-world-how-will-generalists-and-specialists-fare-320ab95c4d74
|
[
{
"date": "2023/01/01",
"position": 9,
"query": "future of work AI"
}
] |
5 Ways Generative AI will Transform the Future of Work ...
|
5 Ways Generative AI will Transform the Future of Work (And How Your Business Can Prepare)
|
https://www.linkedin.com
|
[
"Sanjoy Kumar Malik",
"Sean Preusse",
"Ann-Kathrin H.",
"Senior Manager At Ey",
"Seyi Ogunbona",
"Digital Business Consultant",
"Product Owner",
"Business Analyst",
"Ex-Deloitte",
"Driving Digital Transformation"
] |
Generative AI has the ability to write articles, blogs, compose emails, draft advice and technical documents, create marketing materials, and even design ...
|
As artificial intelligence (AI) technology continues to advance, a new type of AI called generative AI is rapidly emerging. Unlike traditional AI, which is designed to perform specific tasks, generative AI has the ability to create and innovate independently. This includes the ability to generate new ideas, design new products, write code, and even create entire pieces of content.
The potential applications of generative AI are vast, and it has the potential to revolutionize industries and business models by changing the way organizations get work done. This technology could potentially automate tasks that were previously thought to be the exclusive domain of humans.
Why now?
Following the release of ChatGPT on November 30th, 2022, the innovative technology quickly gained widespread adoption with over 1 million users in just 5 days. ChatGPT, a Large Language Model (LLM), allows users to generate human-like text through chat prompts, making access to artificial intelligence highly accessible and democratized.
But ChatGPT's capabilities don't stop at text generation - it can also create images, sounds, and video. This versatility has the potential to transform industries across the board and fundamentally change the way humans interact with the internet.
Traditionally, businesses have adopted artificial intelligence to streamline specific tasks, often those that are repetitive or complex in nature. However, ChatGPT and other generative AI technologies have the potential to revolutionize creative roles and tasks, requiring businesses to rethink their operations and workforce expectations.
5 use cases for Generative AI
1. Content creation – Generative AI has the ability to write articles, blogs, compose emails, draft advice and technical documents, create marketing materials, and even design websites. This technology can produce high-quality content quickly and efficiently, saving businesses time and resources.
2. Design – Generative AI can generate ideas and designs for products or buildings (real or virtual) that humans may not have thought of, leading to rapid innovation. This technology has the potential to revolutionize designer roles and tasks, allowing businesses to produce new and creative designs at a faster pace.
3. Code generation - Generative AI can write code for software development or streamline testing, increasing productivity and allowing developers to focus on more complex tasks. This will support the next iteration of low-code-no-code platforms as it will enable them to perform more complex tasks, attracting even more “citizen developers”.
4. Data analysis and insights - Generative AI has the ability to analyze large amounts of data and generate insights and recommendations that would be difficult or time-consuming for humans to discern.
5. Customer service - Generative AI can handle customer inquiries and resolve issues in a more human and authentic way, as well as increasing the breadth and speed of response. This technology can improve the customer experience and help businesses build stronger relationships with their customers.
Business impacts & considerations for Generative AI
Improve efficiency
Implementing generative AI within appropriate use cases has the potential to significantly improve efficiency. For example, knowledge workers can use generative AI to draft technical responses to queries, which can then be reviewed and validated rather than created from scratch. The initial adoption of generative AI in business is likely to focus on human-AI augmentation rather than replacing humans entirely.
Review your business models
If today's business outputs are heavily characterized by labor, they will look different in a future where generative AI contributes a significant portion of value. This will require businesses to assess how they charge for products and services, such as shifting to a subscription-based model rather than charging by the hour. This is especially true in industries such as consulting. A lawyer or consultant could draft technical advice with generative AI, review and make changes before finalizing, potentially saving 80% of the time required.
New services & rapid innovation
Generative AI can significantly speed up the design process for buildings and products. Instead of taking days, weeks, or even months for a designer or architect to come up with a single design, a generative AI system can generate numerous designs and iterate quickly, allowing organizations to innovate faster and bring products to market more quickly.
Hyper-personalisation
Generative AI can be used to create highly personalized and customized plans, products services or designs that consider an individual's habits, health, preferences, location, and environment.
Skilled labour & reskilling employees
Any new technology innovation requires companies to consider the potential impacts in how work will get done and plan for future workforce skills. There is a risk that jobs, such as knowledge workers (historically less impacted by emerging technologies) could for the first time, find themselves being displaced by generative AI. There are 2 important considerations:
First, whilst Generative AI may automate some tasks, the real benefits will come from training employees to use it in a way that augments, enhances and streamlines their role. For example, employees must know how to use and ask the AI the right questions, interpret the outcomes and understand the limitations to effectively use it, harness its power and maximise productivity gains.
Second, inevitably some employees will need to be reskilled entirely into new roles - which could be in support of new products, business models, or methodologies that Generative AI enables.
Accessing Generative AI
In a business world that is AI + human, a workforce is no longer defined by just humans (employees), but also by access to advanced AI systems. Businesses will need to determine their approach to how to access generative AI based on specific needs, resources and goals – be it through developing in-house expertise or licencing technology or using cloud-based services.
Be aware of the limitations
Generative AI has reached a level of text and natural language sophistication where it is almost impossible to know what content is human-made versus AI-generated. It is therefore critical to be aware of its limitations, particularly in terms of reliability and accuracy. Currently, generative AI models do not read sources or cite work, meaning there is no way to verify that sources are trusted and answers are accurate. Deploying generative AI to augment rather than replace humans will allow organizations to realize the benefits while managing accuracy.
A futuristic office building, designed by generative AI for this article
What businesses need to think about now
Generative AI can’t completely replace humans, however it will change how things are done, and will drastically enhance human output. The most successful businesses of the future will be those that most effectively harness the AI as a tool to improve or use it create something entirely new, not possible before.
Organizations need to start thinking and planning for how they can incorporate generative AI into their business operations. Its use is likely to become increasingly widespread in the coming years, and organizations not planning for this now may find themselves at a competitive disadvantage. By proactively planning for the integration of generative AI, businesses can position themselves to take advantage of the benefits it offers.
Here is a business plan created by, naturally, generative AI:
ChatGPT's plan for how businesses should incorporate Generative AI
| 2023-01-01T00:00:00 |
https://www.linkedin.com/pulse/5-ways-generative-ai-transform-future-work-how-your-business-brown
|
[
{
"date": "2023/01/01",
"position": 23,
"query": "future of work AI"
}
] |
|
Will AI make most HR functions irrelevant in the near future?
|
The heart of the internet
|
https://www.reddit.com
|
[] |
An AI bot could easily scan through court rulings, laws and past practices to advise a manager on how to proceed with discipline and termination.
|
We're already seeing Artificial Intelligence being utilized in recruitment. AI is being used to write articles, create art, do all sorts of things.
I don't see it as much of a leap for the technology to replace much of what we do.
Benefits administration? No problem.
Comp analysis? Child's play.
Employee relations? An AI bot could easily scan through court rulings, laws and past practices to advise a manager on how to proceed with discipline and termination.
In fact, I think it's harder to identify aspects of our function that couldn't be assisted or replaced by AI.
What are your thoughts?
| 2023-01-01T00:00:00 |
https://www.reddit.com/r/humanresources/comments/107lxum/will_ai_make_most_hr_functions_irrelevant_in_the/
|
[
{
"date": "2023/01/01",
"position": 28,
"query": "future of work AI"
}
] |
|
The way to survive AI and automation? Stay relevant.
|
The way to survive AI and automation? Stay relevant.
|
https://www.linkedin.com
|
[
"Amaresh Shinganagutti",
"Financial Freedom",
"Sean Chatman",
"Michael Brian Lee",
"We Help Leaders",
"Teams Adapt",
"Navigate Change.",
"Of Us Have Lost Access To Our Creativity - Let'S Reconnect You.",
"Creative Breakthrough Catalyst",
"Keynote Speaker"
] |
The World Economic Forum's 'The Future of Jobs Report 2020' predicts that AI is expected to replace 85 million jobs worldwide by 2025. So, if you have a job ...
|
Are the machines on the verge of taking our jobs? And if so, what can we do about it? Contrary to popular belief, this isn’t a new discussion. People have been having it for hundreds of years. Remember the Luddites, who destroyed machines in textile factories back in the early 1800s?
And here we are again, in 2023, talking about how AI applications like ChatGPT are about to render us all redundant. They aren’t – but the debate is certainly highlighting the need for businesses and workers round the world to stay relevant and gear themselves for a new future.
10 years later, and it seems that the machines are indeed rising. Since 2000, robots and automation systems have replaced around 1.7 million manufacturing jobs. The World Economic Forum's ‘The Future of Jobs Report 2020’ predicts that AI is expected to replace 85 million jobs worldwide by 2025. So, if you have a job that can be done by a computer or a robot, at some point that role could well be automated.
But just look at the opportunities. The WEF predicts that AI will create 97 million new jobs by 2025. Right now, we shouldn’t be trying to protect jobs that computers and robots can do better. We should be finding ways to train our workforce for future work, and how to succeed in this brave new world.
How do we do that? I asked ChatGPT for three ways that humans can stay relevant in the age of AI. Here’s what it said:
1. Develop expertise in areas where AI is less advanced
‘While AI excels in areas such as data analysis and decision-making, it may not be as good at tasks that require creativity, empathy, and critical thinking. By developing expertise in areas such as problem-solving, decision-making, and communication, humans can stay relevant by working alongside AI systems.’
2. Continual learning and upskilling
‘As AI continues to advance, it is important for individuals to stay current with the latest technologies and trends. This can be achieved through ongoing learning and upskilling, such as taking online courses or participating in professional development programs.’
3. Leveraging the strengths of AI and humans
‘AI is best at handling repetitive and mundane tasks, while humans excel at tasks that require creativity, empathy, and critical thinking. By working together, AI and humans can create a powerful synergy that enables organizations to achieve more than they could individually.’
What does this tell us?
Relevance starts with education
Quite simply, we have to be training people of all ages in the skills they need to be relevant here and now. In my home country of South Africa, around 736 000 young people passed their final high school exams in 2022. Question is, have they been taught the skills at school they need to get a job that won’t be automated in the next 20 years? Even if they become part of the 7% who get a university degree, do they have the skills to hit the ground running in the modern workplace?
The answer to both questions is almost certainly a resounding ‘no’. Fact is, the world of education has moved on. People are opting to do courses in Python or abuse counselling rather than do a four-year degree. We’re seeing exponential growth in MOOCs (massive open online classes), which are giving hundreds of millions of high school graduates across the world access to higher education in bite-sized chunks.
Why is this important? For one, it gives young people access to the practical skills they need to get future-facing jobs. Just as importantly, though, they’re helping the current cohort of employees upgrade their skills to meet the demands of a job environment that’s being disrupted every day. Traditional ways of education are being disrupted too – and that’s a good thing.
Relevance is in your own hands
Mostly, though, we must grab our own destinies with both hands. I talk a lot about how the world of work has changed. In the current economic climate, there are limited jobs available. As employers, we’re challenged to help our people evolve to learn the new skills we need from them in this day and age. That’s only valid up to a point.
I’d suggest that in today’s workplace, relevance is everything. And to remain relevant, we have to change our thinking. Being relevant takes hard work. Relevance is a choice – and it’s your choice alone. If you’re going to sit around waiting for your employer to make you relevant, or for job options to be placed at your door, you’re going to be waiting for a while.
Relevance is a massive opportunity
But while relevance starts with the employee, the employer also has a clear role in driving job satisfaction and reducing attrition. As employers, how do we make things like unstructured education, job shadowing and learning on the job possible to allow our people to find their relevance?
At a time when businesses the world over are grappling with issues like flexible working, the great resignation, and the need to demonstrate their employer value proposition, helping our people stay relevant is a key element of attracting and retaining the best talent.
For one, we have a real opportunity to take the mundane, repetitive, and soul-destroying jobs away from people and give them more rewarding, high-impact tasks. This creates more value for the company and makes for happier people.
More than that, though, we have an opportunity to pull millions of young Africans into the global workforce. In 2018, then Gigaom CEO and futurist Byron Reese described AI as ‘the greatest job engine the world has ever seen’, with many fields that will experience job growth through AI. ‘But just as with the internet, the real gains in jobs will come from places where our imaginations cannot yet take us,’ he said.
| 2023-01-01T00:00:00 |
https://www.linkedin.com/pulse/way-survive-ai-automation-stay-relevant-lee-naik
|
[
{
"date": "2023/01/01",
"position": 80,
"query": "future of work AI"
}
] |
|
The Ambiguous Labor Market Impact of Automating Prediction
|
Artificial Intelligence: The Ambiguous Labor Market Impact of Automating Prediction
|
https://www.aeaweb.org
|
[
"Agrawal",
"U Of Toronto",
"Gans",
"Joshua S.",
"Goldfarb",
"Ajay Agrawal",
"Joshua S. Gans",
"Avi Goldfarb"
] |
We describe and provide examples of how artificial intelligence will affect labor, emphasizing differences between when the automation of prediction leads to ...
|
Abstract Recent advances in artificial intelligence are primarily driven by machine learning, a prediction technology. Prediction is useful because it is an input into decision-making. In order to appreciate the impact of artificial intelligence on jobs, it is important to understand the relative roles of prediction and decision tasks. We describe and provide examples of how artificial intelligence will affect labor, emphasizing differences between when the automation of prediction leads to automating decisions versus enhancing decision-making by humans.
Citation Agrawal, Ajay, Joshua S. Gans, and Avi Goldfarb. 2019. "Artificial Intelligence: The Ambiguous Labor Market Impact of Automating Prediction." Journal of Economic Perspectives 33 (2): 31–50 . DOI: 10.1257/jep.33.2.31 Choose Format: BibTeX EndNote Refer/BibIX RIS Tab-Delimited
Additional Materials Author Disclosure Statement(s)
| 2019-05-14T00:00:00 |
2019/05/14
|
https://www.aeaweb.org/articles?id=10.1257/jep.33.2.31
|
[
{
"date": "2023/01/01",
"position": 81,
"query": "AI labor market trends"
},
{
"date": "2023/04/01",
"position": 92,
"query": "AI labor market trends"
},
{
"date": "2023/10/01",
"position": 88,
"query": "AI labor market trends"
},
{
"date": "2023/11/01",
"position": 91,
"query": "AI labor market trends"
},
{
"date": "2024/03/01",
"position": 85,
"query": "AI labor market trends"
},
{
"date": "2024/05/01",
"position": 90,
"query": "AI labor market trends"
},
{
"date": "2024/06/01",
"position": 88,
"query": "AI labor market trends"
},
{
"date": "2024/08/01",
"position": 84,
"query": "AI labor market trends"
},
{
"date": "2024/09/01",
"position": 84,
"query": "AI labor market trends"
},
{
"date": "2025/05/01",
"position": 91,
"query": "AI labor market trends"
}
] |
AI agents, a quiet job market & future jitters — how are you dealing ...
|
The heart of the internet
|
https://www.reddit.com
|
[] |
At the same time the hiring scene feels ice-cold: fewer postings, lower salaries. Companies seem to want people who wire up or guardrail AI, not ...
|
For experienced developers. This community should be specialized subreddit facilitating discussion amongst individuals who have gained some ground in the software engineering world. Any posts or comments that are made by inexperienced individuals (outside of the weekly Ask thread) should be reported. Anything not specifically related to development or career advice that is _specific_ to Experienced Developers belongs elsewhere. Try /r/work, /r/AskHR, /r/careerguidance, or /r/OfficePolitics.
Members Online
| 2023-01-01T00:00:00 |
https://www.reddit.com/r/ExperiencedDevs/comments/1lu3fo2/ai_agents_a_quiet_job_market_future_jitters_how/
|
[
{
"date": "2023/01/01",
"position": 98,
"query": "AI labor market trends"
}
] |
|
Why Everyone is Wrong to Fear AI: Why We Should ...
|
Why Everyone is Wrong to Fear AI: Why We Should Embrace It | Essay.
|
https://medium.com
|
[
"Disrupt Appeal"
] |
One of the main reasons people are against AI is because they fear that it will lead to widespread job displacement and economic disruption.
|
Why Everyone is Wrong to Fear AI: Why We Should Embrace It | Essay. Disrupt Appeal 3 min read · Jan 9, 2023 -- Listen Share
In recent years, there has been a growing sentiment of fear and mistrust surrounding artificial intelligence (AI). From concerns about job displacement and privacy to dystopian visions of a future dominated by machine intelligence, it seems like everyone is against AI. But is this fear warranted? Is AI really the enemy that some make it out to be? In this essay, we will explore why everyone is against AI and why they shouldn’t be.
One of the main reasons people are against AI is because they fear that it will lead to widespread job displacement and economic disruption. It is true that AI has the potential to automate many tasks that are currently performed by humans, and this could lead to some job loss in the short term. However, it is important to remember that new technologies have always disrupted the job market in the past, and yet we have always managed to adapt and create new industries and opportunities.
Another reason people are against AI is because of concerns about privacy. There are valid concerns about the potential for AI to be used to monitor and track individuals, but it is important to remember that AI is simply a tool, and it is up to us as a society to ensure that it is used ethically and responsibly.
Finally, some people are against AI because they fear that it will eventually surpass human intelligence and take over the world. While it is true that AI has the potential to become incredibly powerful, it is important to remember that it is still a machine and will always be bound by the limits of its programming. There is no reason to believe that AI will become a threat to humanity as long as we use it wisely and ethically.
In conclusion, while there are valid concerns about the impact of AI on society, it is important to remember that it is simply a tool and that we have the power to shape how it is used. Instead of fear and mistrust, we should embrace AI as a tool that has the potential to improve our lives and make the world a better place for everyone.
| 2023-01-09T00:00:00 |
2023/01/09
|
https://medium.com/@DisruptAppealMag/why-everyone-is-wrong-to-fear-ai-why-we-should-embrace-it-essay-4ff74e1a96d1
|
[
{
"date": "2023/01/01",
"position": 10,
"query": "AI economic disruption"
}
] |
An Honest admission, I fear the upcoming technological ...
|
The heart of the internet
|
https://www.reddit.com
|
[] |
I fear that AI will, perhaps slightly hyperbolically, lead to the destruction of our civilization. I feel this will largely be brought on by a rapid, and ...
|
Ok so, simply put, I'm lay-person, blue collar worker who enjoy technology. I love that my home is wired up, that we're exploring the depths of space, that we're looking at better and better augmetics, and that fission and other technologies are coming online; lets bring on that Star Trek, Star Wars, or whatever future. I love my apple watch, and self-driving cars. But, AI has me worried for our future. When I say AI, I generally tie it in with the use of robotics or computers; drones, programs, machinery, etc.
I fear that AI will, perhaps slightly hyperbolically, lead to the destruction of our civilization. I feel this will largely be brought on by a rapid, and massive disruption in our workforce that will likely see hundreds of millions unemployed, followed by the over all degradation of society as we know it. I'm not at the point where I think a true, thinking AI will rule us all; but I genuinely don't feel that's an impossibility. Now, this isn't the immediate horizon, but on like a 40-50 year timeline.
I'm hoping that someone can really talk me down (politely please, I'm just a reader trying to understand the world). I want to be excited about the future again. My only solace right now, is this phrase "that's its easy to see what jobs an innovation will replace, but near impossible to anticipate what opportunities they'll create."
So here are a few reasons that AI scares me, in no particular order:
It's in businesses best interest to replace us - Over the long term, in any capitalist society, it is in a company's best interest to reduce it's costs; and it's employees are often it's biggest costs. Over the long term, any company that can, will find a way to replace its workforce to as near totality as it can without impact it's operations; corporations with shareholders especially. Humans aren't good at "moderation" and knowing when to stop - lets be real. Humans are bad at moderating ourselves. I have no faith that well meaning scientists will push it too far, and ill meaning people will create every kind of evil from it. Great, we have an AI that can code, an AI for hacking won't be far behind. Hurrah, we have an AI for search and resume, and the military will create an AI for hunting people. I struggle to fathom why people think creating a truly thinking AI is good idea. WE think humans are shitty, how do we really think an ultra powerful AI that is running our lives will feel about us? Tech disrupting pretty much every industry at once - I understand that technology creates a lot of opportunities, often more than it destroys. Another conversation I was in used the Mechanical Combine as an example, it destroyed hundreds of thousands of jobs on farms; but created many more. I do appreciate these examples, but in every example I can think of, a technology really disrupted either one industry, or a small handful, and people were able to either take advantage of the change or change sectors. I can't think of another technology, save perhaps the internet, that will impact almost literally every industry on earth, at the same time, everywhere, at an incredibly rapid pace. Lose your job as a taxi driver? Don't look at medical diagnosis, art, policy, factory workers, legal aides, mining, military personnel, and more. All of these are likely to be replaced by drones or AI, or vast sums of their workforces will be. What are we going to do, retrained 200million low income workers to build code for AI? Can't do that, AI is writing code. Humans won't be able to "QC" for AI for very long - Many people say, "oh well, if the AI is writing code (or policy, or law, etc.), it'll still need humans to QC it's work." My question is, for how long? the AI is learning at a rapid pace. If it takes over writing code, how long will it be before those who are doing the QC, have never actually written code in their lives? 5 years? 10 years? Why would you have someone who has never professionally written code, only learned in school, QCing for an AI who has millions of hours learning code? It won't be worth the money you pay people, at least not forever. Humans suffer without a purpose in life - This is a bit of a wishy washy one. I've seen a few people say that "good, people will be left with more time to socialize, explore, and do the fun things in life." Now, I don't how many of you have been unemployed (I have), and I know many other who have; and they're not happy. You collect EI (similar to a UBI), and feel depressed. You feel like you have no value. Humans need something to do, something to contribute to, we always have. Back to being cavemen, each individual had a role in the tribe. I feel like saying "Go forth, you're now free to never work again, but only get paid this fixed amount for the rest of your life; Enjoy!" is a recipe for a stagnant, dying society. Governments are slow to react - We all know this. I read a headline that said AI generated digital content (music, art, videos, TikToks, etc.) could make up 80% of what's on the internet by 2025. That's A LOT of people out of work. I don't know about your governments, by the idea of national Universal Basic Income isn't anywhere on the radar, and implementation will take a decade for sure. But technology waits for no government, and the lag time in between is what scares me immensely. The divide between the Rich and Poor will explode - Simply put, when AI replaces jobs, it won't be the rich who suffer, it'll be the poor. Those that can harness AI, specially those who OWN large businesses, will become richer than any of us can imagine today; and the rest of us will suffer on a static UBI. I can't fathom the unrest and suffering that will likely follow. The creative space, which I hoped was going to be the last refuge of humanity, was actually the first to go - I had always hoped that creative pursuits, such as art and music, would be the last things to go. That even if jobs disappear we could each delve into the creative, and find self worth there. But instead, they were the first to go, at least digitally. I can see some physical manifestations going to AI as well.
Again, I honestly hope that I'm wrong about all of these, and I'd love to see how. This isn't even touching on our society losing it's ability to write thing (why write a book when you can get an AI to write papers, blog posts, news posts, reports, summaries, etc.). This might seem outlandish today, but in 10-15 years I can hardly fathom where we are, and where the AI is. I want to be excited about the future, but this scares me.
| 2023-01-01T00:00:00 |
https://www.reddit.com/r/Futurology/comments/10ffivq/an_honest_admission_i_fear_the_upcoming/
|
[
{
"date": "2023/01/01",
"position": 14,
"query": "AI economic disruption"
}
] |
|
The Rise of AI: How Its Impacting Our Lives
|
The Rise of AI: How Its Impacting Our Lives
|
https://www.linkedin.com
|
[
"Bako Faysal",
"Javier Gil"
] |
Additionally, AI can be used to automate jobs, which could lead to job loss and economic disruption. Finally, AI can be used to create weapons and other ...
|
Artificial intelligence (AI) is a rapidly growing field that has the potential to revolutionize the way we live and work. AI is a form of technology that enables machines to learn, think, and act like humans, allowing them to complete tasks that would otherwise require human intelligence. In this article, we'll explore the basics of AI and discuss how it can be used to benefit our lives.
AI is a rapidly advancing field that has the potential to completely transform our lives and the way we work. AI is a type of technology that allows machines to learn, think, and act like humans, allowing them to complete tasks that would be too difficult for humans to do. In this article, we'll look at the fundamentals of AI and examine how it can be used to improve our lives.
What is artificial intelligence?
Artificial intelligence (AI) is the ability of a computer or machine to think and learn. It is a branch of computer science that focuses on creating intelligent machines that can work and react like humans. AI systems are designed to think and act like humans, but they are not necessarily conscious or self-aware. AI systems can be used to analyze large amounts of data, recognize patterns, and make decisions with minimal human intervention. AI is used in a variety of fields, from robotics to healthcare, and is becoming increasingly important in our lives. AI can help us make better decisions, automate mundane tasks, and even create new products and services. AI is an exciting and rapidly growing field, and its potential is only beginning to be realized.
How does AI work?
AI systems are powered by algorithms, which are sets of instructions that tell the computer what to do. Algorithms are designed to analyze data and recognize patterns, and they can be used to make predictions and decisions. AI systems are trained using large amounts of data, and they can learn from their mistakes and become more accurate over time. AI systems can be used to automate tasks, such as driving a car or recognizing faces in a crowd. AI can also be used to analyze large amounts of data and make predictions, such as predicting the stock market or predicting the weather.
What are the benefits of AI?
AI can be used to automate mundane tasks, freeing up time for humans to focus on more creative and meaningful work. AI can also be used to analyze large amounts of data, allowing us to make better decisions and gain insights that would otherwise be impossible. AI can also help us create new products and services, such as self-driving cars and personalized healthcare. AI can also be used to improve our lives in other ways, such as helping us to better understand our environment and the world around us.
AI is a rapidly growing field with the potential to revolutionize the way we live and work. AI can be used to automate mundane tasks, analyze large amounts of data, and make better decisions. AI can also help us create new products and services, and improve our lives in other ways. AI is an exciting and rapidly growing field, and its potential
How is AI being used today?
Artificial Intelligence (AI) is being used in a variety of ways today. AI is being used in many industries, such as healthcare, finance, retail, and transportation. In healthcare, AI is being used to diagnose diseases, detect anomalies in medical images, and provide personalized treatments. In finance, AI is being used to detect fraud, automate trading, and provide personalized financial advice. In retail, AI is being used to personalize customer experiences, optimize inventory management, and automate customer service. In transportation, AI is being used to automate driving, optimize routes, and predict traffic patterns. AI is also being used in other areas such as education, security, and manufacturing. AI is being used to automate grading, detect security threats, and optimize production processes. AI is becoming increasingly important in many areas of our lives, and its use is only expected to grow in the future.
What are the potential benefits and risks of AI?
The potential benefits of artificial intelligence (AI) are vast, from improved decision-making to increased efficiency and cost savings. AI can help automate mundane tasks, allowing humans to focus on more important tasks. AI can also help to improve accuracy and reduce errors, as well as improve customer service and satisfaction. AI can also help to predict customer needs and provide personalized experiences.
However, there are also potential risks associated with AI. As AI becomes more sophisticated, it can be used to manipulate data and make decisions that are not in the best interests of the user. AI can also be used to create bias in decision-making, as well as create privacy and security risks. Additionally, AI can be used to automate jobs, which could lead to job loss and economic disruption. Finally, AI can be used to create weapons and other dangerous technologies, which could be used for malicious purposes.
What are the ethical considerations of AI?
The ethical considerations of artificial intelligence (AI) are becoming increasingly important as AI technology advances. AI has the potential to revolutionize many aspects of our lives, from healthcare to transportation, but it also raises a number of ethical concerns. Some of the most pressing ethical considerations of AI include privacy, safety, and fairness.
Privacy is a major concern when it comes to AI. AI systems are often used to collect and analyze large amounts of data, which can be used to identify individuals and track their activities. This raises questions about who has access to this data, how it is used, and how it is protected.
Safety is another ethical consideration of AI. AI systems are becoming increasingly complex and powerful, and there is a risk that they could be used for malicious purposes. This could include manipulating data, making decisions without human oversight, or even causing physical harm.
Finally, fairness is an important ethical consideration of AI. AI systems are often used to make decisions about people’s lives, such as who gets hired for a job or who gets approved for a loan. If these decisions are based on biased data or algorithms, it could lead to unfair outcomes.
These are just a few of the ethical considerations of AI. As AI technology continues to develop, it is important to consider the ethical implications of its use and ensure that it is used responsibly.
How can AI be used to improve decision-making?
Artificial intelligence (AI) can be used to improve decision-making in a variety of ways. AI algorithms can be used to analyze large amounts of data quickly and accurately, allowing decision-makers to make more informed decisions. AI can also be used to automate certain decision-making processes, such as identifying patterns in data or predicting future outcomes. AI can also be used to identify potential risks and opportunities, allowing decision-makers to make more informed decisions. Finally, AI can be used to provide recommendations and advice to decision-makers, helping them to make better decisions. By leveraging the power of AI, decision-makers can make more informed, accurate, and timely decisions.
What are the most promising AI applications?
The most promising applications of artificial intelligence (AI) are in the areas of healthcare, finance, and transportation. In healthcare, AI can be used to diagnose diseases, analyze medical images, and provide personalized treatments. In finance, AI can be used to automate financial processes, detect fraud, and provide personalized financial advice. In transportation, AI can be used to automate the driving process, optimize routes, and reduce traffic congestion. AI is also being used in the fields of education, retail, and manufacturing, among others. As AI technology continues to develop, the potential applications are becoming more and more exciting.
How can AI be used to create more efficient processes?
Artificial Intelligence (AI) can be used to create more efficient processes by automating tasks and reducing the need for manual labor. AI can be used to analyze data, identify patterns, and make predictions that can help streamline processes. AI can also be used to automate mundane tasks, such as data entry, which can help free up resources for more important tasks. Additionally, AI can be used to optimize processes by providing insights into how they can be improved. For example, AI can be used to identify bottlenecks in a process and suggest ways to reduce them. By using AI to create more efficient processes, businesses can save time and money, and increase their productivity.
AI is quickly becoming an integral part of our lives, from healthcare to finance to transportation. Artificial intelligence (AI) is a form of technology that enables machines to learn from data and make decisions. AI can be used to automate processes, identify patterns, and provide recommendations. AI can also be used to create more efficient processes, freeing up resources and increasing productivity. As AI technology continues to develop, the potential applications are becoming more and more exciting. With AI, businesses can make more informed decisions, automate mundane tasks, and optimize processes. By leveraging the power of AI, businesses can save time and money, and increase their productivity.
What are the implications of AI on society?
The implications of artificial intelligence (AI) on society are far-reaching and complex. AI has the potential to revolutionize the way we live and work, from automating mundane tasks to providing personalized services. AI can also help us make better decisions, from healthcare to finance, by providing us with more accurate and timely information.
At the same time, AI can also create new ethical dilemmas. For example, AI-driven automation could lead to job losses, and the use of AI in decision-making could lead to bias and discrimination. Additionally, AI-driven systems could be vulnerable to cyberattacks, which could have serious implications for our security and privacy.
Overall, AI has the potential to bring great benefits to society, but it is important to consider the potential implications of its use. We must ensure that AI is used responsibly and ethically, and that its use is regulated to protect the rights and interests of all individuals.
How can AI be used to address global problems?
| 2023-01-01T00:00:00 |
https://www.linkedin.com/pulse/rise-ai-how-its-impacting-our-lives-jefferson-entrampas
|
[
{
"date": "2023/01/01",
"position": 19,
"query": "AI economic disruption"
}
] |
|
Modeling the artificial intelligence-based imperatives of ...
|
Modeling the artificial intelligence-based imperatives of industry 5.0 towards resilient supply chains: A post-COVID-19 pandemic perspective
|
https://pmc.ncbi.nlm.nih.gov
|
[
"Tazim Ahmed",
"Department Of Industrial",
"Production Engineering",
"Jashore University Of Science",
"Technology",
"Jashore",
"Chitra Lekha Karmaker",
"Sumaiya Benta Nasir",
"Bangladesh University Of Engineering",
"Dhaka"
] |
by T Ahmed · 2023 · Cited by 117 — The recent COVID-19 pandemic has significantly affected emerging economies' global supply chains (SCs) by disrupting their manufacturing activities.
|
Abstract The recent COVID-19 pandemic has significantly affected emerging economies’ global supply chains (SCs) by disrupting their manufacturing activities. To ensure business survivability during the current and post-COVID-19 era, it is crucial to adopt artificial intelligence (AI) technologies to renovate traditional manufacturing activities. The fifth industrial revolution, Industry 5.0 (I5.0), and artificial intelligence (AI) offer the overwhelming potential to build an inclusive digital future by ensuring supply chain (SC) resiliency and sustainability. Accordingly, this research aims to identify, assess, and prioritize the AI-based imperatives of I5.0 to improve SC resiliency. An integrated and intelligent approach consisting of Pareto analysis, the Bayesian approach, and the Best-Worst Method (BWM) was developed to fulfill the objectives. Based on the literature review and expert opinions, nine AI-based imperatives were identified and analyzed using Bayesian-BWM to evaluate their potential applicability. The findings reveal that real-time tracking of SC activities using the Internet of Things (IoT) is the most crucial AI-based imperative to improving a manufacturing SC’s survivability. The research insights can assist industry leaders, practitioners, and relevant stakeholders in dealing with the impacts of large-scale SC disruptions in the post-COVID-19 era. Keywords: Post-COVID-19 pandemic, Supply chain resilience, Artificial intelligence, Industry 5.0, Bayesian Best-Worst Method
3. Research methodology This research develops an innovative integrated model for exploring and evaluating the AI-based imperatives of I5.0 that will help organizations make strategic decisions to establish a resilient SC for the post-COVID-19 world. Considering all possible AI-based imperatives of I5.0, the integrated approach was developed with Pareto analysis, Bayesian, and BWM approaches to determine the relationship between pairs of AI-based imperatives of I5.0 and evaluate their priorities. Fig. 1 presents the essential steps for the proposed research framework. Fig. 1. Open in a new tab Proposed research framework. 3.1. Data and context of study A structured framework for assessing the AI-based imperatives of I5.0 was implemented for Bangladesh’s apparel and footwear industries as a case study of an emerging economy. Due to the surge of the COVID-19 pandemic, these two industries’ SCs are facing a lot of challenges (Acioli et al., 2021). Many manufacturing firms have adopted advanced AI technologies to develop a more sustainable production method and establish a resilient SC. Unfortunately, they have failed to implement them properly due to a lack of understanding of such technologies. In response, we have picked up this topic and proposed a framework that will provide policy-makers valuable insights into measuring which AI-based imperatives they should focus on during the adoption process. In this research, data were gathered in two phases. In the first phase, a survey was conducted to finalize the AI-based imperatives with the help of Pareto analysis. For this purpose, this study selected a total of 40 experts using a subjective sampling method (Guarte & Barrios, 2006). The inclusion criteria of experts are having at least ten years of relevant experience and adequate knowledge of I5.0 initiatives. A brief description of expert profiles is shown in Table 2 . Table 2. The detailed information of the experts. Features Number of experts Percentage Evaluators
(m = 40) Designation Managing Director 10 25 General Manager 10 25 Manager (Production) 5 12.5 Supply Chain Manager 10 25 Academic 5 12.5 Domain of expertise Sustainable supply chain 8 20 Supply chain management 11 27.5 Environment, health, and safety 7 17.5 Logistics management 7 17.5 Production/Operations 7 17.5 Experience Less than 12 years 8 20 12 to 18 years 18 45 More than 18 years 14 35 Open in a new tab Pareto analysis, or the 80/20 rule, introduced by Vilfredo Pareto, is an effective and simple tool for identifying the “vital few” variables from “trivial many”. For collecting expert’s opinions, a questionnaire with the identified AI-based imperatives was prepared and circulated among experts through email communication (See Table A1 in Appendix-A for the questionnaire). Experts were given the freedom to express their valuable thoughts on the importance (priority weight) of all advanced technologies with the help of a 9-point Likert scale, where a scale of 1 indicates very weakly important, and a scale of 9 indicates very extremely important. After that, the cumulative percentage score of all technologies was calculated, and the most significant ones (comprising 80% score) were finalized, as depicted in Fig. 2 . In the second phase, fifteen experts were interviewed to collect the data to investigate the relationships among the AI-based imperatives and determine their final priorities. Here, an integrated approach combining the Bayesian approach and BWM was anticipated to examine the relationships between pairs of imperatives and prioritize them toward SC resiliency. In the following sections, first, the steps of the BWM are explained, then, the details of the B-BWM are described. Fig. 2. Open in a new tab Pareto diagram of the AI-based imperatives of I5.0 towards resiliency of SCs. 3.2. Best-Worst method (BWM) The BWM, proposed by Professor Jafar Razaei, is a novel and recent tool (Rezaei, 2015). This research selected this method to assess the advanced AI-based imperatives of I5.0 due to its several benefits. First, the best and worst are identified before developing pair-wise comparison vectors. Thus, the decision-makers have a clear view of the priority of evaluation (Fartaj et al., 2020). This action, in turn, increases the consistency of the pair-wise comparisons. Second, the development of pair-wise comparison vectors against two opposite measures helps reduce the biases of expert opinions. Third, it is the most data and time-efficient method compared to other Multi-Criteria Decision Making (MCDM) methods. This method requires a few data which could mitigate the possible biases and, at the same time, provides more reliable and consistent pair-wise comparisons. 3.3. Bayesian-BWM The original BWM establishes overall weights from a probabilistic perspective and serves as the foundation for the B-BWM (Mohammadi & Rezaei, 2020). The input of the B-BWM, such as two pair-wise comparison vectors, is identical to BWM. In contrast, the output of B-BWM provides a probability distribution as opposed to the BWM’s specific value, which is the sole distinction. The definitions of each notation used in this method have been presented in Table A2 (Appendix-A). The followings are the major stages for B-BWM deployed in the current study. Stage 1: Fixing a set of AI-based imperatives. C = { c 1 , c 2 , . . . , c n } , where n denotes the total number of AI-based imperatives. Stage 2: Choosing the best ( C B ) and the worst ( C w ) imperative from a set of C attributes. Each evaluator now chooses the most crucial and worst imperatives from a set of C attributes. Stage 3: Conduct a pair-wise comparison vector between the best over the other (BO) AI-imperatives. Each expert uses a rating scale of “1 to 9” to construct the pair-wise comparison vector between the best and the other imperatives. The imperatives have a stronger impact when there are more of them. The resultant vector of BO is written as A B = a B 1 , a B 2 , . . . , a Bn . Here, a Bj shows how much more important the best imperative is than the others c j ∈ C c j ∈ C . Stage 4: Conduct a pair-wise comparison between the other over the worst imperative (OW). In the same way, each evaluator rates the impact of the other imperatives on the worst one on a scale from “1 to 9.” The following OW vector is shown as A w = a w 1 , a w 2 , . . . , a wn . Here, a wj expresses how much more important the other imperatives c j ∈ C are than the worst one . Stage 5: Finding the optimal and the aggregated weight. This stage determines each optimal weight z 1 : K as well as the total optimal weight z agg given A B 1 : K are identified, which accounts for all the evaluators. Following are the joint probability distribution and the probabilities for each variable. P z agg , z 1 : K A B 1 : K , A w 1 : K (1) P x = ∑ y P x , y (2) where x, y are two arbitrary random variables. 3.4. Bayesian hierarchical model A probabilistic hierarchical model is initially plotted to analyze the relationship between the variables before the Bayesian model is created. Fig. 3 displays a detailed overview of the B-BWM model. In this case, circular and rectangular nodes, respectively, present variables and observed variables. The directed arrows show which nodes are dependent on each other. Therefore, it is evident that the magnitude of z agg depends on z K and that again depends on A B K and A W K . The corresponding variables ( z K , A B K , A W K ) in the plate are iterated by each assessor. Fig. 3. Open in a new tab The probabilistic graphical model of the B-BWM. Fig. 3 illuminates the conditional independence between the two variables. For example, A W K is independent of z agg , given z K , so, P A W K z agg , z K = P A W K z K (3) The resultant equation, combining the Bayes rule with Equation (1), can be rewritten as follows. P z agg , z 1 : K A B 1 : K , A W 1 : K α P A B 1 : K , A W 1 : K z agg , z 1 : K P z agg , z 1 : K = P z agg ∏ K = 1 K P A B L z K P A W K z K P z K z agg (4) The probability chain rule, the conditional independence of the several variables, and the evaluators’ independent assessments of each variable are used to establish the final equality in this case. It is essential to identify all variables in order to compute the posterior distribution. Since every variable in this situation is an integer, a multinomial distribution may be used to represent it. As the two vectors ( A B K and A W K ) are just opposite, the opposite weight results from this. The distribution will be as: A B K z K multinomial 1 z K (5) A W K z K multinomial 1 z K (6) The MCDM requires a weight vector to satisfy the non-negativity and sum to one property. The Dirichlet distribution is used to determine the weight as a consequence. One way to explain the distribution is as: D i r a = 1 B a ∏ j = 1 n z j a i - 1 (7) Here, z is this MCDM’s ideal weight and α is the Dirichlet distribution’s parameter. The Dirichlet distribution’s mean and concentration factor have once again been parameterized for this study’s purposes. Here, λ and z agg denote the concentration factor and the distribution consequently. z K z agg D i r λ × z agg (8) Equation (8) shows that each evaluator’s weight vector, z K , must be close to the distribution’s mean value, z agg , and that the concentration factor γ gauges this proximity. It is necessary to simulate the concentration parameter, and gamma distribution will be accurate in simulating such a non-negative value. γ gamma a,b (9) where a and b represent the model parameters of the gamma distribution. Finally, z agg as the prior distribution is calculated employing an uninformative Dirichlet distribution with the factor value of α = 1 as: z agg D i r 1 (10) No closed-form solution exists for the probabilistic model defined by the equations (5–10). A Markov-chain Monte Carlo (MCMC) sampling is necessary to compute the solution. The B-BWM was performed in the free and open-source Just Another Gibbs Sampler (JAGS), one of the most effective available probabilistic languages. 3.5. Credal ranking In this work, the I5.0 AI-based imperatives were ranked in terms of relevance using the credal ranking approach. Unlike earlier ranking techniques, which determined the significant variable based on two numbers or intervals, this technique employs the Dirichlet distribution to determine the degree of confidence in the criterion’s superiority. These credal ranking and order concepts are utilized to create the probabilistic hierarchical model and determine the confidence level. Definition 1 The formulation of a credal sorting O for a pair of attribute c i and c j , can be explained as follows (Mohammadi & Rezaei, 2020): O = c i , c j , R , d (11) Where, R is the relationship among the performance measures c i and c j .
d ∈ [ 0 , 1 ] represents the relation’s degree of confidence. Definition 2 The credal ranking is a list of credal orderings that contains all pairs ( c i , c j ) for all c i , c j ∈ C , upon a given set of criteria C = { c 1 , c 2 , . . . , c n } . Now, for every set of criteria c i and c j , we just require calculating the credal ordering degree. To achieve this, the S samples from JAGS were utilized and the degree was calculated in the manner specified below: (Mohammadi & Rezaei, 2020). P c i > c j = 1 S ∑ s = 1 S I z i ag g s > z j ag g s (12)
4. Implementation of Bayesian-BWM This section presents the findings from implementing the proposed framework to analyze the AI-based imperatives of I5.0 to establish resilient SCs for Bangladeshi RMG and footwear industries in the post-COVID-19 era. The AI-based imperatives were considered the alternatives for assessing the SC resiliency issues in the first phase of the proposed Pareto and B-BWM integrated framework. In the second phase, BO and OW vectors were formed following responses from the purposively selected evaluators. Table A3, Table A4 in Appendix-A show the BO and OW vectors, respectively. Then, with the help of multinomial distribution, these two inputs were modeled in Eqs. (5), (6), and the Dirichlet distribution was used to get the aggregated final weight vector of the imperatives of I5.0 using Eqs. (7), (8). Table 3 represents the weight vector of the AI-based imperatives of I5.0. This weight vector represents the relative importance of each imperative over the others, along with the ranking. Table 3. Aggregated final weights of the AI-based imperatives of I5.0. AI-based imperatives of I5.0 Final Weight Rank Production flexibility through automation integration (I1) 0.1329 4 Use of cyber-physical production system (CPPS) (I4) 0.1699 2 Cyber immunity for data management (I6) 0.1052 5 Boosting employee safety and operational continuity through AI (I7) 0.0607 7 Application of big data and predictive analytics (I8) 0.0598 8 Inventory control using RFID (I11) 0.0924 6 Real-time tracking of SC activities using IoT (I12) 0.1727 1 Advancing SC transparency by implementing the blockchain technologies (I14) 0.0515 9 Creation of digital SC twin (I16) 0.1550 3 Open in a new tab The credal ranking, which is a weight-driven graph to comprehend the relationship between a pair of imperatives, is one of the main results of the B-BWM. Fig. 4 shows the confidence in choosing one imperative above the others in this investigation, which was achieved using credal ranking. Fig. 4. Open in a new tab Hierarchical credal ranking of the AI-based imperatives of I5.0 for establishing resilient SCs.
5. Result and discussions The proposed framework integrated with Pareto and B-BWM has resulted in the relative importance of AI-based imperatives to achieve SC resiliency for the RMG and footwear industries. As shown in Table 3, “Real-time tracking of SC activities using IoT (I12)” is the most important AI-based imperative for achieving resilient SC with an aggregated weight of 0.1727. Most of the RMG and footwear industries in an emerging economy like Bangladesh lack real-time tracking of SC activities. Hence, optimizing these activities becomes very difficult during the COVID-19 pandemic. IoT can make the SC activities visible to all the stakeholders, and the strategy formulation process regarding selecting optimum routes, energy consumption, inventory policy, and waste elimination becomes very effective. Thus, adopting this AI-based imperative will increase the financial, environmental, and social performance of the SCs of the RMG and footwear industries. Yadav, Luthra, and Garg (2021) also found that integrating IoT can increase resiliency in the case of agri-food SCs in the turbulent business environment resulting from COVID-19. Therefore, “Real-time tracking of SC activities using IoT (I12)” can be a novel implication for Bangladeshi RMG and footwear industries to establish resilient SC. By adopting this strategy, other sectors of emerging economies with similar business characteristics can also make their SCs resilient. The second most important imperative suggested by the current research is the “Use of cyber-physical production system (I4)” with a weight of 0.1699. Recently, several studies have identified that cyber-physical production systems can tackle the operational disruptions of SCs due to the COVID-19 pandemic and enhance environmental performance (Andronie, Lăzăroiu, Iatagan, Hurloiu, & Dijmărescu, 2021). In an emerging economy like Bangladesh, disruptions in operational and environmental performances of SCs resulting from the COVID-19 pandemic have become a matter of concern for export-oriented industries like the RMG and footwear industries and many local manufacturing industries. Adopting the cyber-physical production system can make the SCs of these industries smooth and efficient by providing a self-monitoring facility that will eventually help to build a resilient SC. In this research, “Real-time tracking of SC activities using IoT (I12)” and “Use of cyber-physical production system (I4)” are found to have almost equal importance in improving SC resiliency. However, IoT needs to be well integrated before establishing the cyber-physical production system. “Creation of digital SC twin (I16)” will help the RMG and footwear industries simulate the actual SC and collect the real-time data of SC operations. Thus, the uncertainties and risks throughout the SC can be reduced while minimizing human participation in various SC operations during the COVID-19 pandemic. Burgos and Ivanov (2021) stressed the creation of a digital twin to increase SC resiliency during the COVID-19 crisis. The current research has also found the “Creation of digital SC twin (I16)” as the third most important AI-based imperative of I5.0 to increase the resiliency of SCs in RMG and footwear industries. In recent times, the COVID-19 pandemic has made the companies of emerging economies aware of the flexibility in production and SC operations. In Bangladesh, the RMG and footwear industries have also become concerned about SC operations’ flexibility that can be achieved through automation integration. Moreover, the automotive industries of emerging economies with similar production characteristics to RMG have also realized the importance of automation integration during COVID-19. “Production flexibility through automation integration (I1)” is the fourth most significant AI-based imperative suggested by the current research. According to the study by Delic and Eyers (2020), one of the prerequisites for improving SC performance and resiliency is the flexibility of the manufacturing system, which can be achieved through automation. Again, adopting I5.0 initiatives in SC will generate a vast amount of data. Therefore, establishing the “Cyber immunity for data management (I6)” will be imperative for the companies under the COVID-19 crisis. Sobb, Turnbull, and Moustafa (2020) also suggested addressing cybersecurity issues while embedding AI technologies with SCs. Another AI-based imperative for resilient SC found in the current research is “Inventory control using RFID (I11)”. Due to the COVID-19 crisis, end-to-end tracking of items and inventory control have become challenging tasks, although they are required for improving SC performances and customer satisfaction. Deploying the RFID to track and control the inventory can solve this problem for most of the SCs of emerging economies. Varriale et al. (2021) found that RFID adoption accelerates achieving SC resiliency. The recent COVID-19 pandemic has challenged the employee safety of all types of industries. Hence, operational continuity is being hampered because of this safety issue. This eventually has a drastic impact on SC resiliency. “Boosting employee safety and operational continuity through AI (I7)” can be a solution to this problem. AI can automate and manage various SC activities, optimizing human-to-human physical communication (Di Vaio, Boccia, Landriani, & Palladino, 2020). Uncertainty in customer demands and energy consumption has increased dramatically due to the COVID-19 crisis. Forecasting customer demands and energy consumption with greater accuracy during this crisis is imperative to make SC operations smooth and effective. “Application of big data and predictive analytics (I8)” helps companies to make a more accurate prediction on customer demands and energy consumption, even during adverse situations (Tsai et al., 2021). Companies in the emerging economy like Bangladesh are far behind in this regard. Therefore, this AI-based imperative of I5.0 suggested by the current research can be a practical implication for RMG, footwear, and other industries. However, all the imperatives above must be adopted to benefit from the “Application of big data and predictive analytics (I8)”. For this reason, this imperative has been ranked 8th amongst the nine AI-based imperatives. Finally, “Advancing SC transparency by implementing the blockchain technologies (I14)” has been ranked last in the current research. However, Nandi, Sarkis, Hervani, and Helms (2021) found that blockchain can enhance the resilience and sustainability of SC during COVID-19. However, significant investment is necessary to build a blockchain-enabled SC. The current research was conducted in Bangladesh, an emerging economy where investment and legislation are major issues for firms looking to use blockchain technology. Therefore, the current research has found this imperative of I5.0 less important than the others. The credal ranking in Fig. 4 shows that “Real-time tracking of SC activities using IoT (I12)” is considered the most important AI-based imperative, with a confidence of 0.77 against “Creation of digital SC twin (I16)”, with a confidence of 0.96 against “Production flexibility through automation integration (I1)” and with a confidence of 1 against “Cyber immunity for data management (I6)”, “Inventory control using RFID (I11)”, “Boosting employee safety and operational continuity through AI (I7)”, “Application of big data and predictive analytics (I8)” and “Advancing SC transparency by implementing the blockchain technologies (I14)”. Again, the confidence of selecting the “Real-time tracking of SC activities using IoT (I12)” against “Use of cyber-physical production system (I4)” is 0.55, indicating that these two AI-based imperatives are equally important to be adopted. Table 3 also shows no discernible difference in the weights of these two imperatives. However, “Real-time tracking of SC activities using IoT (I12)” is preferable to the “Use of cyber-physical production system (I4)” to achieve SC resiliency. Fig. 4 also shows that the other pairs of AI-based imperatives have reasonably high confidence except for the confidence between “Boosting employee safety and operational continuity through AI (I7)” and “Application of big data and predictive analytics (I8)”. The confidence level of choosing I7 over I8 is 0.53, which is close to the threshold value (0.50). It indicates that these two AI-based imperatives have almost equal significance for building resilient SC. For the sustainability of the business, many organizations might consider digitizing their SC with I5.0 technology as a costly undertaking, as introducing such technology in developing countries requires a lot of investment. Most of the costs are associated with the investment in technology purchasing, training, human resources, and maintenance. However, in the long run, it can reduce costs and strengthen the SC against any future disruptions. Therefore, embracing revolution is quite realistic and rational for the emerging economies’ companies from the cost and benefit trade-off perspective, with tangible benefits to reduce costs and increase productivity. Although adopting I5.0 technologies by emerging economy companies is still in the embryonic stage, many RMG and footwear have started using I4.0 technologies that might be helpful for the technological transition. For example, many RMG and footwear companies have introduced virtual reality, additive manufacturing, and robotics to make their operations and SC more sustainable.
6. Implications From a theoretical standpoint, the results of this study provide a wide range of ramifications for the researchers. In order to construct resilient SC in the post-COVID-19 future, the current work has first addressed a set of AI-based imperatives of I5.0 that must be accepted. The majority of the work currently in circulation focuses on detecting and evaluating the effects of COVID-19 on SC resilience (Golan, Jernegan, & Linkov, 2020). This research is a preliminary attempt to pinpoint the answers in light of I5.0 for developing a robust SC in an emerging economy. This study has highlighted the connection between the AI-based technologies of I5.0 and SC resilience that may help the researchers frame more robust solutions in the future. Again, the solutions of I5.0 proposed by this study may be applicable for all the other country contexts where the companies are facing problems establishing resilient SC during the COVID-19 pandemic. Secondly, this study has offered a new and intelligent framework to model the AI-based imperatives of I5.0 to establish resilient SC. This framework integrates Pareto theory with the B-BWM, which may provide future scientists with a different view to utilize such integration with other methods to identify the relevant interest factors. The findings from applying the proposed framework also have several managerial implications. Due to the uncertain business environment caused by the recent COVID-19 pandemic, companies must rethink what initiatives or strategies they need to take to achieve SC resilience (Ali et al., 2021). This research has shed light on the significance of AI-based imperatives of I5.0 to establish resilient SC. This may help SC professionals and researchers rethink the solution strategies for I5.0 to increase SC resiliency. Operations managers and policymakers may find the suggested solutions, such as real-time SC activity tracking using IoT, setting up cyber-physical production systems, and creating a SC digital twin, helpful in coming up with the best plans to build a resilient SC. The current research has integrated Pareto analysis into the assessment framework that helps identify the relevant AI-based imperatives of I5.0. The proposed framework has integrated the B-BWM for effective group decision that also helps the companies to select the right AI technologies to build resilient SC during the COVID-19 crisis.
7. Conclusions and future research directions The COVID-19 pandemic affected the global market of many emerging economies by disrupting manufacturing activities. Many manufacturing industries have already shut down their operations, and others face many challenges in continuing their business operations during this pandemic. To enhance the survivability of modern SCs and adopt sustainable ways of production, SCs and manufacturing firms from emerging economies need to build a resilient SC by adopting AI-based imperatives. Many emerging economies’ industries have already sought and adopted various technologies. Still, they have failed to get their most advantages due to a lack of in-depth knowledge about these imperatives. A structured framework has been proposed in this study that assists decision-makers and relevant stakeholders of emerging economies in identifying, evaluating, and prioritizing the AI-based imperatives for establishing a resilient SC. This research presented a Pareto-based B-BWM model for assessing AI-based imperatives in an emerging economy context. Based on extant literature, sixteen AI-based imperatives were identified; later, by the Pareto chart, nine were finalized. After applying B-BWM, real-time tracking of SC activities using IoT was found to be the most crucial AI-based imperative, followed by using cyber-physical production systems and creating a digital SC twin. This research contributes to the literature from multiple directions. First, it connects AI-based imperatives of I5.0, SC resiliency, and the daunting effects of the COVID-19 pandemic. This type of integration in the SC resiliency domain has not been suggested or explored. The second contribution is the integrated method, Pareto-based B-BWM, to sort out, evaluate, and analyze the AI-based imperatives of I5.0 for reducing the difficulties caused by COVID-19 through establishing a resilient SC. The research findings have the potential to guide decision-makers in shaping strategic decisions for increasing resiliency in SCs amid the COVID-19 pandemic. Third, this research has revealed how badly various SC issues, such as production, sourcing, distributions, etc., have been disrupted due to the COVID-19 pandemic. Fourth, the evaluation of AI-based imperatives of I5.0 responds to what technologies-based imperatives should be adopted for which dimension to deal with the ‘effects of a large-scale SC disruption such as the COVID-19 pandemic. Although the research has contributed significantly to SC resiliency and disruption management, it possesses some limitations. Here, the proposed model was developed by collecting data from Bangladeshi RMG and footwear industries; therefore, the findings from the proposed framework may not reveal a clear view of other related industries. Another limitation is that while the results are expected to apply to other industries, they are mostly aligned with the business and operational characteristics of Bangladeshi RMG and footwear industries. This research provides several avenues for future research. This research has brought the AI-based imperatives of I5.0, the impacts of the COVID-19 pandemic, SC resiliency, and B-BWM into a single platform. The idea of I.50 is still in an embryonic phase. The applications of AI technologies in the SC management context are almost unexplored. The proposed model was developed as an emerging economy based on Bangladeshi RMG and footwear industries. In the future, this work can be performed in other developing and developed economies contexts to generalize the findings.
CRediT authorship contribution statement Tazim Ahmed: Conceptualization, Methodology, Software, Formal analysis, Investigation, Data curation, Writing – original draft. Chitra Lekha Karmaker: Conceptualization, Methodology, Software, Formal analysis, Investigation, Data curation, Writing – original draft. Sumaiya Benta Nasir: Conceptualization, Methodology, Software, Formal analysis, Investigation, Data curation, Writing – original draft. Md. Abdul Moktadir: Conceptualization, Resources, Writing – review & editing, Supervision. Sanjoy Kumar Paul: Resources, Visualization, Writing – review & editing, Supervision.
Declaration of Competing Interest The authors declare that they have no known competing financial interests or personal relationships that could have appeared to influence the work reported in this paper.
Appendix. Primary questionnaires 1. Details of the expert: (a) Position:
(b) Company Name:
(c) The number of years of service:
(d) Major role: Q1: Selection of the most relevant AI-based imperatives of I5.0 towards resiliency of the emerging economies’ SCs in a post-COVID-19 world. Express your valuable opinions (importance weight) using the 9-point Likert scale (see Table A1, Table A2, Table A3, Table A4 ). Table A1. Identified the most relevant AI-based imperatives of I5.0. No. List of AI-based imperatives Code 1: Very weakly important and 9: Highly important 1 2 - - 9 1 Production flexibility through automation integration I1 2 Optimization of SC activities using cloud technologies I2 3 Decentralization of production system using additive manufacturing I3 4 Use of cyber-physical production system (CPPS) I4 5 Optimization of warehouse activities using augmented reality I5 6 Cyber immunity for data management I6 7 Boosting employee safety and operational continuity through AI I7 8 Application of big data and predictive analytics I8 9 Application of robotics in
logistics service I9 10 Vertical networking and horizontal integration of smart production systems I10 11 Inventory control using RFID I11 12 Real-time tracking of SC activities using IoT I12 13 Application of machine learning in production planning and control I13 14 Advancing SC transparency by implementing the blockchain technologies I14 15 Rapid prototyping using 3D printing I15 16 Creation of digital SC twin I16 Open in a new tab Table A2. Definition of notations. Notation Definition C Alternative to evaluate C B Best alternative C w Worst alternative A B Best -to-Others vector A w Others-to-Worst vector z Weight of an alternative by each evaluator z agg Aggregated weight of an alternative K Number of evaluators z K Weight of an alternative by kth evaluator O Credal ordering R Relation between the alternatives d Confidence in the superiority of the alternatives M Sample size Open in a new tab Table A3. Best-to-Others vector. Expert Best Imperative I1 I4 I6 I7 I8 I11 I12 I14 I16 E 1 I4 6 1 4 9 7 6 3 8 2 E2 I12 3 2 5 7 6 5 1 9 4 E 3 I4 5 1 3 5 9 7 2 6 3 E 4 I16 4 3 6 6 8 6 4 9 1 E5 I1 1 5 4 9 6 4 3 7 2 E6 I12 3 2 4 9 7 5 1 8 6 E7 I16 4 5 3 8 7 6 2 9 1 E 8 I4 5 1 6 7 8 7 3 9 3 E 9 I1 1 2 4 6 9 3 1 8 2 E10 I4 3 1 5 7 7 6 2 9 4 E11 I12 4 3 6 8 7 5 1 9 2 E12 I1 1 2 3 6 9 4 2 6 2 E13 I4 5 1 4 6 9 3 5 7 5 E14 I12 4 2 5 8 7 9 1 8 3 E15 I16 4 3 4 9 7 6 5 6 1 Open in a new tab Table A4. Others-to-Worst vector. Imperative Expert E 1 E 2 E 3 E 4 E 5 E 6 E 7 E 8 E 9 E 10 E 11 E 12 E 13 E 14 E 15 Worst Imperative I7 I14 I8 I14 I7 I7 I14 I14 I8 I14 I14 I8 I8 I11 I7 I1 4 7 5 5 9 7 6 5 9 7 6 9 5 6 7 I4 9 8 9 7 5 8 5 9 8 9 7 8 9 8 6 I6 6 5 7 3 6 4 7 4 6 3 4 7 6 5 6 I7 1 4 5 3 1 1 2 3 4 3 2 4 4 2 1 I8 3 4 1 2 4 3 3 2 1 4 3 1 1 3 3 I11 4 5 3 4 6 5 4 4 7 8 5 6 7 1 4 I12 7 9 8 6 7 9 8 7 8 8 9 8 5 9 5 I14 2 1 4 1 3 2 1 1 2 1 1 4 3 2 8 I16 8 6 7 9 8 5 9 6 8 6 8 8 5 7 9 Open in a new tab
Data availability The data has been provided within the manuscript.
| 2023-01-31T00:00:00 |
2023/01/31
|
https://pmc.ncbi.nlm.nih.gov/articles/PMC9886400/
|
[
{
"date": "2023/01/01",
"position": 20,
"query": "AI economic disruption"
}
] |
Report Says AI Could Potentially Replace 85 Million Jobs ...
|
The heart of the internet
|
https://www.reddit.com
|
[] |
“the World Economic Forum estimated that AI will replace some 85 million jobs by 2025. The same report, however, concluded that some 97 million new jobs ...
|
A subreddit devoted to the field of Future(s) Studies and evidence-based speculation about the development of humanity, technology, and civilization. -------- You can also find us in the fediverse at - https://futurology.today
Members Online
| 2023-01-01T00:00:00 |
https://www.reddit.com/r/Futurology/comments/10o9jby/report_says_ai_could_potentially_replace_85/
|
[
{
"date": "2023/01/01",
"position": 22,
"query": "AI economic disruption"
}
] |
|
Is AI a blessing or a curse for humanity?
|
Is AI a blessing or a curse for humanity?
|
https://www.linkedin.com
|
[
"Montgomery Singman",
"Prof. Ahmed Banafa",
"Mazen Zbib",
"Eric Anderson",
"Helping Ambitious Engineers",
"Tech Pros To Elevate Their Career",
"Upgrade Your Linkedin Profile",
"Cv Resume",
"Job Search Skills",
"Interview Performance"
] |
Why is the use of AI problematic? Displacement of workers: AI has the potential to automate many jobs, which may cause economic disruption and the loss of jobs.
|
There has been a recent uptick in the use of artificial intelligence applications including ChatGPT-4, Chatsonic, Dall-E 2, and Midjourney. It appears that the praise for these tools is never-ending.
Are we prepared for how these products will alter our culture and the way we conduct business, and to what extent are we aware of the implications?
TL;DR: AI tools can be both incredibly awesome and terrible.
What is AI?
AI is an abbreviation for "Artificial Intelligence."
Understanding natural language, identifying images, generating predictions, and learning from data are all examples of tasks that were formerly thought to require human intellect but are now routinely accomplished by computers and machines thanks to advances in artificial intelligence.
This field focuses on programming computers with the ability to learn and reason like humans.
Self-driving cars, speech recognition, and image recognition are just some of the many areas where AI has found usage.
Why is the use of AI problematic?
Displacement of workers: AI has the potential to automate many jobs, which may cause economic disruption and the loss of jobs.
Artificial intelligence systems can reinforce and even amplify biases that are present in the data they use for training. This may cause unjust or biased results.
AI tools have the potential to propagate false information and manipulate data, further undermining public confidence in the digital world. Targeting algorithms on social media have already demonstrated this, but the harmful potential of AI is much greater.
This is especially true of deep learning neural networks and other AI systems that lack transparency. The public may have trouble putting their faith in AI decisions if they cannot understand how they were reached.
Privacy concerns can arise from the use of AI, especially if private information is needed for the system's training or operation.
The use of AI systems in life-or-death scenarios, like autonomous vehicles or medical diagnosis, does not come without its own set of safety concerns.
The use of AI has the potential to centralize power, with a select few organizations having exclusive access to and responsibility for AI applications.
One could argue that using AI gives one an unfair advantage. The cost of creating and maintaining algorithms might make them unaffordable for many businesses.
Some worry about the rightness of building machines with human-level cognition and decision-making abilities, among other ethical questions raised by AI.
AI technologies make it simple to copy output without acknowledgment, and many content producers and artists may not receive credit for their efforts.
Problem mitigation
Best practices in AI development, such as using diverse data sets, developing explainable AI, and implementing regulations and policies, can help to reduce the severity of the issues related to the use of AI.
As AI tools become more common, it is critical to ensure that users are aware of the potential for abuse and understand the consequences of their actions.
Users should be educated on the various types of AI tools, their capabilities, the potential for misuse, and the effects of such misuse.
It's not all bad
The potential for AI to transform the way we live and work should not be underestimated.
Artificial intelligence has the ability to automate repetitive jobs and make data-driven judgments more quickly and correctly than humans.
AI may be applied to create new goods and services that boost production and efficiency, giving businesses a competitive edge in the market.
By offering individualized services and recommendations, AI may also assist individuals, making their lives simpler and more enjoyable.
Last but not least, AI can be used to improve our comprehension of the world around us, from weather forecasting to comprehending the behavior of complex systems.
Summary
As a rapidly developing field of technology, artificial intelligence (AI) holds promise but also presents challenges.
We must keep track of technological advancements and how they are utilized.
| 2023-01-01T00:00:00 |
https://www.linkedin.com/pulse/ai-blessing-curse-humanity-joon-nebell
|
[
{
"date": "2023/01/01",
"position": 31,
"query": "AI economic disruption"
}
] |
|
AI as a System Technology
|
AI as a System Technology
|
https://link.springer.com
|
[
"Sheikh",
"Wetenschappelijke Raad Voor Het Regeringsbeleid",
"Prins",
"Schrijvers",
"Den Haag",
"The Netherlands",
"Haroon Sheikh",
"Corien Prins",
"Erik Schrijvers",
"Search Author On"
] |
by H Sheikh · 2023 · Cited by 17 — We believe that three aspects of the techno-economic paradigm of AI are already distinguishable. ... disruption. Describing how the record industry was ...
|
Academics have long been interested in how different types of technology exert a general influence over the economy and society. An early example is the Kondratiev wave theory, in particular as elaborated by Joseph Schumpeter. He observed that periods of high economic growth alternate with periods of lower growth, a pattern he attributed to the effect of new technologies; sets of new technologies periodically boosted growth, after which the effect gradually waned over time. According to Schumpeter, such dynamism was inherent to a capitalist market economy: “it is essential to understand that capitalism is an evolutionary process … ‘industrial mutation’ … is constantly bringing about revolutionary change to the structure of the economy from the inside, constantly destroying the old structure and creating a new one.”Footnote 5 Such reasoning forms the basis of the familiar concept of creative destruction.
In his acceptance speech when presented with the Nobel Prize for Economics in 1971, Simon Kuznets introduced the idea of ‘epochal innovations’ driving periods of great economic development. Innovation scientists Carlota Perez and Chris Freeman have written about a similar phenomenon, which they refer to as ‘new technology systems’ and ‘technological revolutions’.Footnote 6 A new technology system is a powerful and conspicuous cluster of new and dynamic technologies, products and industries that lead to major change throughout the economy and ultimately to economic growth. Perez has identified five such clusters since the Industrial Revolution, including the eras of steam power and railways, of steel and electricity, of oil, cars and mass production and of information and telecommunications. She argues that each of these brought its own ‘techno-economic paradigm’: a way of thinking and acting, leading to the relevant technologies becoming integral to the fabric of society.Footnote 7 Alessandro Nuvolari has made a significant addition to Perez’s theories by emphasizing that the observed effects are attributable not so much to individual technologies as to blocks of radical innovations that together bring about revolution.Footnote 8 Some researchers accordingly take the view that innovation consists not of the development of major new things but of the combination of things that already exist.Footnote 9
4.1.1 General-Purpose Technologies
AI can be classified based on its general, transformative impact on society. It is useful to view the technology in relation to the concept of the general-purpose technology (GPT). GPTs are technologies whose potential applications are not specific, like those of a lawnmower, toaster or microscope, but generic insofar as they lend themselves to countless, highly diverse purposes. GPTs can therefore have a major influence on the economy and society. Timothy F. Bresnahan and Manuel Trajtenberg introduced the concept in an article published in 1992,Footnote 10 which cited three criteria for the classification of a technology as a GPT. First, a GPT is highly pervasive, being utilized in numerous sectors, production processes and products. Second, there is great scope for its technical improvement, meaning that the cost of the technology keeps falling and its efficiency increasing. Third, a GPT spawns numerous ‘innovational complementarities’, leading to generalized economic productivity improvements.
A large body of literature on the concept of the GPT is now available. However, that has not led to the adoption of a uniform definitionFootnote 11 or consistent use of the term. Some authors recognize only a small number of historical GPTs, while others argue that there have been many throughout human history, going back as far as the domestication of livestock and the forging of bronze. One author suggests that the literature identifies twenty-eight technologies as GPTs.Footnote 12
Another topic of debate amongst academics is the existence of technologies that have great societal impact but are not particularly generic. Examples include the printing press and the steamship: technologies whose applications are limited but have radically changed society. The technologies most widely recognized and cited as GPTs are the steam engine, electricity, the internal combustion engine and IT.Footnote 13
Notwithstanding the qualifications made above, a number of interesting studies in recent years have related AI explicitly to the concept of the GPT. Following a conference organized by the US National Bureau of Economic Research (NBER) in 2017, for instance, a collection of papers entitled The Economics of Artificial Intelligence was published in 2019. The first part, entitled ‘AI as a GPT’, includes contributions by renowned technology researchers and economists and contains various interesting analyses that we draw on in this report, although – in keeping with the nature of the original conference, but in contrast to our own focus – they are concerned primarily with the macroeconomic effects of AI.
Also of interest in this context is the thesis by Jade Leung of Oxford University, entitled Who will govern artificial intelligence? Learning from the history of strategic politics in emerging technologies. In this she places AI alongside aerospace technology, biotechnology and cryptography as an example of what she calls ‘strategic GPTs’, and in that context emphasizes the relationship between governments and new technologies, particularly in the defence sector. Leung identifies three key actors here, the government, business and the research community, and demonstrates that each has different aims, instruments and limitations, which may converge in certain phases but are at odds in others.
Various researchers have recently sought to place AI in a broad historical perspective without making explicit use of the term ‘GPT’. In a polemic on Andrew MacAfee and Erik Brynjolfsson’s famous book The Second Machine Age, Carlota Perez wrote a nine-part series of articles entitled Second Machine Age or Fifth Technological Revolution? In these she explores how today’s digital technologies – including AI – compare with previous technologies.Footnote 14
All of these studies, and particularly the perspective developed in them, are relevant to the theoretical framework we use to view AI in this report. We additionally draw on a number of more empirical studies of the effects of specific technologies. Sarah A. Seo has written about the best-known application of the internal combustion engine, namely the motor car. She also demonstrates how this symbol of freedom has simultaneously led to an enormous increase in the power that the state – particularly the police – have over citizens’ private lives.Footnote 15 In a general survey of a series of technologies ranging from tractors and margarine to electricity and GMOs, Calestous Juma investigates the dynamics of social resistance to new technologies.Footnote 16 This report thus draws not only on research into GPTs but also analogies with recent technologies such as genetically modified organisms (GMOs) and nanotechnology, which have interesting parallels with AI.Footnote 17
4.1.2 AI as a GPT
The question we need to ask at this point is whether AI can actually be regarded as a GPT. But the answer seems quite clear: although its global impact is currently in its early stages, it already appears that AI is indeed a GPT. If we consider Bresnahan and Trajtenberg’s three criteria for classification as a GPT, a strong case can be made for saying that all apply to AI.
The first of these criteria is pervasiveness. Although AI’s perfusion of the economy and wider society has gathered pace only in recent years, the technology is already used in a variety of sectors and products. Earlier in this part of the report (2.2), we presented a range of examples illustrating how AI is being used in manufacturing, agriculture, the public sector, entertainment, financial services and medical practice. Given that versatility, it is already apparent that AI is well on the way to pervading society and the economy.
The second criterion is inherent potential for technical improvement, leading to lower cost and increased efficiency. Again, it is evident that AI passes this test. In Chap. 1 we highlighted how Moore’s Law states that computing power doubles every 2 years, opening the way for the further improvement of AI technologies. We also saw how scientific research has fuelled the development of new and improved technologies. As a result, the application of AI has passed numerous milestones in recent years. Furthermore, as highlighted in our discussion of the future of the lab, promising new technologies are being developed, which are expected to further boost the performance and efficiency of AI.
Finally, classification as a GPT depends on the presence of complementary innovations that lift general productivity. Numerous signs of a positive influence on general productivity can already be discerned, but AI is simply too young for us to demonstrate conclusively the existence of complementary innovations. Nevertheless, various authoritative research bodies and consultancies, including Accenture, PwC, McKinsey and Deloitte, have forecast major productivity increases over the decade ahead. We set out the three defining characteristics of system technologies in Fig. 4.1.Footnote 18
Fig. 4.1 The three defining characteristics of system technologies Full size image
4.1.3 AI as a System Technology
We can conclude, then, that AI satisfies the three criteria for classification as a general-purpose technology. The GPT concept and the wealth of literature considering AI as such a technology provide useful starting points to understand what kind of technology we are dealing with. Nevertheless, we have chosen not to apply the term ‘GPT’ here. Rather, we have elected to define AI as a ‘system technology’. That choice reflects significant focal differences between our analysis and the literature on GPTs.
Firstly, the GPT literature from the earliest Kondratiev wave sources to the recent NBER study has a strong focus on the macroeconomic effects of the technologies in question. Many researchers seek to quantify the effects of the technologies they study. That gives rise to debate as to whether and how a GPT can be shown to support a prolonged increase in economic growth. Given the huge number of variables to be accounted for, a model capable of demonstrating such an effect has to be extremely complex. By contrast, we have chosen to concentrate not on the quantitative effects of system technologies but primarily on the qualitative changes they bring about.
Secondly, the literature on GPTs pays particular attention to historical classifications. As indicated earlier, there is considerable debate as to how many historical technologies may be considered GPTs. One researcher recognizes dozens, Perez distinguishes five clusters, authors such as Chandler refer to three Industrial Revolutions,Footnote 19 Schwab identifies four and Brynjolfsson and McAfee speak of two ‘machine ages’. Furthermore, many authors make use of highly schematic timelines with precise start and end dates for individual technologies. This report differs from those approaches in that we refrain from introducing such demarcations. Because we are concerned mainly with qualitative impact rather than quantitative effects, we do not need to commit ourselves to a strict classification system or definite start and end dates for technologies. What we are seeking to do is highlight general patterns. To that end we concern ourselves primarily with a small number of previous system technologies – the steam engine, electricity, the internal combustion engine and the computer – and draw pragmatically on historical sources to identify relevant parallels.
Another reason for not adopting the term ‘GPT’ is that it emphasizes a technology’s versatility. We prefer ‘system technology’ because we wish to emphasize the systemic nature of certain technologies and to broaden the focus to their systemic effects on society. In the context of ‘system technology’, therefore, the word ‘system’ has two implications. First, it implies that the technology consists of a system with multiple components. Electricity, for example, works in conjunction with generators, cables, batteries and so on. Similarly, AI is part of a wider technical system of data and hardware. The second implication of ‘system technology’ is that the technology influences a variety of systems and processes within society. Exercising such influence involves a complex process of adaptation, trial and negotiation. In other words, our chosen term reflects the process of societal integration and the associated qualitative effects.
4.1.4 Similarities and Differences Between AI and Earlier System Technologies
AI is a system technology and therefore comparable with earlier technologies of that type such as the steam engine, electricity and the internal combustion engine (Fig. 4.2). Furthermore, we can define AI even more precisely given that particular characteristics make it more similar to one technology than another in certain respects. For example, the internal combustion engine and the steam engine are tangible, whereas AI is like electricity in being intangible to some extent. It does not exist in isolation but only as part of a product or service. In that sense, devices such as toasters, lamps and radios that work by means of electricity are comparable with thermostats, watches and machines that work by means of AI.
Fig. 4.2 AI as a new system technology Full size image
Another respect in which AI is more like electricity than the internal combustion engine is that it is ‘technology-radical’, rather than ‘use-radical’. The descriptor ‘technology-radical’ is applied to technologies driven primarily by technical and scientific progress; their development is propelled by the curiosity of researchers, without any clear notion of how or for what purpose the technology will ultimately be used. By contrast, ‘use-radical’ implies a clear understanding of the applications from the outset, with commercial factors playing a role early on. The development of use-radical technologies is goal-oriented. That was the case with the internal combustion engine. Like with electricity, researchers were working on AI long before people recognized the lucrative applications we are now aware of.
A distinction can also be drawn between system technologies in which governments play an obvious role from the start and those whose development has no such involvement. The first group includes technologies developed specifically for defence purposes and dependent on the defence sector for their further application and development. This differentiates them from ‘civilian-first’ technologies, whose development is attributable mainly to their economic potential. Governments have more control over the development of the first group of technologies than the second. Space technology is an example of a technology developed with direct government involvement, while biotechnology is an example of one whose development fits the second model. However, both are examples of what Jade Leung calls strategic GPTs.Footnote 20
With AI, the US military institute DARPA was a key financier in the early stages. Nevertheless, early government-funded AI research was of a fundamental nature and military applications represent only a small portion of its full range of uses. In that respect AI is more akin to biotechnology than aerospace technology. However, it differs from biotechnology insofar as the latter’s developers are largely attached to major (academic) laboratories, whereas innovation in the field of AI is more decentralized. That has implications for researchers’ ability to define universal standards.
It is important to consider not only such technical similarities and differences between AI and other system technologies, but also how AI compares in terms of its societal and temporal context. Take the role of the government, for example. The steam engine was developed in a laissez-faire climate in the UK, with the government playing only a very limited role. On the other hand, the combustion engine and the motor car were developed in an era when government economic policy was led by Keynesian thinking. Although governments now exercise considerable influence over the economy by means of standardization and legislation, AI emerged at a time when there was significant resistance to strong guidance of the economy. It is important to bear those circumstances in mind when seeking to identify historical patterns that are instructive in relation to AI.
The societal context of AI also differs from that of earlier technologies in terms of the mobilization of social actors. Increasing prosperity and the progress of democratization have empowered more people to express themselves in the public arena. Whereas enterprises and governments could once shape society with relative ease, nowadays civil society, the academic community, individuals and the media have much more influence than in the past. The mobilization of these actors therefore plays a more significant role in relation to AI and its integration into society than it did in relation to earlier system technologies.
This phenomenon ties in with what Trajtenberg calls the ‘democratization of expectations’: factory workers during the Industrial Revolution had little power because most struggled to make ends meet. We return to this point in Sect. 4.5, in relation to the Luddites. Today far more people participate in public life and workers have much better representation. Moreover, people are less inclined to bear the cost of technological change while also having greater expectations in terms of sharing in the benefits of such change.Footnote 21
The world today is not only more democratized than in the past but also more globalized. Consequently, the issues associated with AI have always been more global. The extensive nature of modern markets and the consequently wide geographical impact of AI’s applications are relevant in this context, as is the existence of all manner of international constraints such as trade agreements, human rights and technical standards. Interestingly enough, the rise of earlier system technologies has often been an impulse for the formation of new international organizations for standardization,Footnote 22 and these are now playing a role in relation to AI. Examples include entities active in the fields of telecommunications and the internet, standardization bodies such as the ISO and international engineering associations such as the IEEE. Although the development and embedding of earlier technologies had an international dimension, the significance of that dimension has increased over time under the influence of globalization.
One final difference between the development context of AI and that of earlier system technologies is the increased level of organization and communication amongst scientists. The scientific community was not well integrated at the time of the steam engine’s development, whereas academic organizations, codes of conduct and standards now exert significant influence.
4.1.5 The Techno-Economic Paradigm of AI
Finally, Carlota Perez’s notion of the techno-economic paradigm warrants attention.Footnote 23 She argues that major technological change leads not only to new products and services but also to new ways of thinking and working and new principles of organization. For example, the Industrial Revolution led to the rise of factories while electricity enabled ‘networked’ production. Similarly, the invention of the internal combustion engine gave us not only cars but also the conveyor belt. Fordism, Taylorism and just-in-time production are all derived from organizational principles. Although it is too early to characterize the techno-economic paradigm of AI in definitive terms, we can already discern certain outlines that follow earlier forms of digitalization but also exhibit new features.
We believe that three aspects of the techno-economic paradigm of AI are already distinguishable. The first relates to changes in the nature of objects and products. As discussed at the end of the previous chapter, in the digital domain we are dealing not so much with end products as with semi-finished ones. A digital product is never finished. Unlike traditional products and services, which ultimately leave the factory and are sold, digital products are constantly being revised and adapted. By means of updates, digitally-enabled objects such as computers, cars, cameras and medical devices are always changing. In the words of Kevin Kelly, everything is in a continuous ‘state of becoming’.Footnote 24 Or, as Luciano Floridi puts it, ‘things’ are being replaced by ‘-ings’, such as interact-ing, process-ing, network-ing, do-ing and be-ing.Footnote 25
Related to this is the phenomenon that physical objects that acquire a digital aspect cease to be discrete entities. In this regard Adam Greenfield highlights porosity as a common characteristic of modern-day technologies. The boundaries between objects and between user and platform, and even the walls of our homes, have become porous due to bilateral interconnection and intermingling. Numerous actors are therefore involved with and present in all those products. The changes to the nature of physical objects raise a variety of security, privacy and responsibility questions.
A second feature of the technical paradigm of AI is, paradoxically, that while objects associated with individuals are becoming more transparent, much of the technology is becoming invisible. At a meeting in Davos in 2015, Eric Schmidt predicted that the internet would disappear. He did not mean that it would fall into decline but was referring to an idea derived from an influential 1991 article by Mark Weiser entitled The Computer for the twenty-first Century.Footnote 26 That introduced the concept of ‘ubiquitous computing’, an omnipresent architecture of digital technology. According to Weiser, “The most prominent technologies are those that disappear. They become integral to the fabric of daily life, with the result that we cease to be aware of them.” Hence, “computers can disappear into the background”.Footnote 27
Luciano Floridi has made the same point using a metaphor. He suggests that we are now living on the ‘piano nobile’, the central upper storey of a Renaissance home visible from the outside. However, below us are numerous servants – in our case digital servants – at work in the service rooms.Footnote 28 An interesting feature of this spatial metaphor is that it emphasizes the existence of a vertical structure. The building has multiple superimposed levels, not all of which are visible. Benjamin Bratton sees in such verticality the core of digital technology.Footnote 29 He argues that we used to live in a horizontal world, with people, objects and countries adjacent to each other on the map. Digitalization has introduced a vertical structure, however, the layers of which are formed by internet addresses, cloud services and data centres running through everything largely unnoticed. In the world of technology, the ‘stack’ is a familiar concept: an entity made up of superimposed layers of hardware, software, network and applications. The existence of that largely invisible layering raises questions regarding power relationships and dependencies.Footnote 30 Jose van Dijck uses another metaphor to describe the vertical structure of digital technology. She refers to the treelike structure of platformization, focusing attention on the power concentration associated with, for example, vertical integration.Footnote 31
One final aspect of the technical paradigm of AI that warrants attention relates to Floridi’s concept of technology. He argues that the idea of technology as an instrument is problematic because it suggests that a person uses an instrument, and by doing so exercises influence over the outside world. That obscures the fact that much of our technology today acts not act on an external physical world but on other technologies. Our attention should therefore be directed towards that ‘inter-technological’ dynamism. Floridi calls technologies that act on other technologies ‘second-order technologies’. One example is a brake, which acts on the wheel of a car. In that case the process is activated by a person pressing the brake pedal.
However, the world of AI is complicated by the existence of ‘third-order technologies’: technologies that cause other technologies to act on yet other technologies, without human intervention. In an autonomous vehicle, for example, the decision to activate the brake is taken by the vehicle’s control system. Wherever an AI system can make decisions autonomously, a third-order structure may be formed. Many road-traffic penalty systems are already characterized by such structures. A vehicle is photographed infringing a traffic regulation – breaking a speed limit, for example – triggering the issue of a penalty notice, which is sent to the address of the vehicle’s registered keeper. The autonomy that technology acquires with the integration of algorithms and that is ultimately integral to the definition of AI used in this report gives rise to questions about matters such as human control, responsibility and legal liability.Footnote 32
| 2023-07-14T00:00:00 |
2023/07/14
|
https://link.springer.com/chapter/10.1007/978-3-031-21448-6_4
|
[
{
"date": "2023/01/01",
"position": 42,
"query": "AI economic disruption"
}
] |
Policy for AI as a System Technology
|
Policy for AI as a System Technology
|
https://link.springer.com
|
[
"Sheikh",
"Wetenschappelijke Raad Voor Het Regeringsbeleid",
"Prins",
"Schrijvers",
"Den Haag",
"The Netherlands",
"Haroon Sheikh",
"Corien Prins",
"Erik Schrijvers",
"Search Author On"
] |
by H Sheikh · 2023 · Cited by 6 — Artificial intelligence is not just another technology – it is a 'system technology' that will fundamentally change our society. That is the key message of ...
|
From an analysis of the history of previous system technologies, we have distinguished five overarching tasks for the integration of AI into government and society: demystification of what it is and can do, contextualization of its development and application, engagement by various parties, regulation of the technology, its use and the social implications and, finally, its national positioning in relation to other countries and international organizations (Fig. 10.1). We have discussed these tasks in detail in Part 2 of this report and recap them briefly here, also indicating what civic values are at stake and what risks are involved if we do not face up to these tasks.
Fig. 10.1 Five tasks for the social integration of AI Full size image
AI as a System Technology There is a rich body of academic literature discussing technological revolutions, epochal innovations and technical eras. A recurring central concept in this corpus is that of ‘general purpose technologies’, those not used for a specific purpose but applicable broadly throughout society. Examples include the steam engine, electricity, the combustion engine and the computer. In Chap. 4 we revealed how AI has the three characteristics of a general purpose technology: it is (1) ubiquitous, (2) subject to continuous technical improvement and (3) enables complementary innovations in other fields. In this report we have labelled AI a system technology. On the one hand this points to the fact that – like electricity and combustion engines – it is part of a wider system of other technologies, while on the other we use this term to emphasize the systemic effect such technologies have on society. What Do We Mean by AI? In this report we have adopted the definition formulated by the High-Level Expert Group on AI (AI HLEG) of the European Commission: “systems that display intelligent behaviour by analysing their environment and taking actions – with some degree of autonomy – to achieve specific goals.” The broadest definition of AI equates it with the use of algorithms, while the strictest views it as the imitation of all human skills (‘artificial general intelligence’). The former stretches the concept of AI enormously while the latter defines it out of existence. The AI HLEG version is sufficiently specific, while at the same time – by admitting non-concrete phenomena such as deep learning –leaving room for new techniques and developments. AI and Digital Technology AI is strongly intertwined with other digital technologies such as computing and data but does not coincide with them. One of the fathers of computing, Alan Turing, was also the inventor of the so-called Turing test, which is used to assess AI systems. AI is dependent on huge amounts of data, and internet data. Current deep learning methods require large amounts of digital information to work effectively. At the same time AI cannot be synonymized with these other technologies. We have outlined its development and the many ways it is linked to computers, data and the internet in Chaps. 2 and 3. But AI also has a separate scientific and historical background, with its own ‘springs and ‘winters’. While computers have been widely used since the Second World War, and the internet has been ubiquitous since the 1990s, the emergence of AI as a social phenomenon is a far more recent development. This is why it deserves individual attention.
10.1.1 Task 1: Demystification
The first overarching task – demystification – concerns preconceptions about AI as a technology. In fact, it is really about the question: What is AI? System technologies always go hand in hand with extreme preconceptions. Excessively high expectations lead to disillusionment and ill-considered applications, while exaggerated fears lead to rejection of a technology and unexploited opportunities. Clinging to such preconceptions will have a negative effect, particularly in the longer term. We argue that more realism is needed to be able to ask the right questions about societal integration and civic values. In the past we saw all manner of unrealistic expectations arise concerning the future of electricity and automobiles, driven by public demonstrations and races. Commentators thought that trains, the telegraph and later the internet would bring global peace by connecting the world. Conversely, the imagery surrounding earlier system technologies in the form of Frankenstein’s monster and words like ‘electrocution’ – which linked electricity to mortality – stirred up fears of these breakthroughs.
There are also numerous myths surrounding artificial intelligence. AI systems are said to be rational and objective, but also to work like an unfathomable ‘black box’. It is thought that the technology could eventually match and even exceed all human capabilities, and even turn against humanity. In addition, there are all sorts of myths associated with digitalization in a broader sense, such as the idea – popular until quite recently – that the development of the internet should be ungoverned and, more importantly, unregulated. Another mistaken preconception is that there is no alternative to the current form of digital technology and that digitalization offers a solution to every problem.
If we do not address such ideas, society may come to rely too heavily on AI systems – with all manner of unwelcome consequences. They could also lead to AI being rejected and its benefits being reaped insufficiently, if at all. Finally, exaggerated preconceptions can prevent an open discussion on crucial questions surrounding the societal integration of a technology. Demystification primarily involves issues such as legal protection, the public’s confidence in the technology, adequate provision of information and the quality of the public debate.
10.1.2 Task 2: Contextualization
The second task we have distinguished is contextualization. This concerns the application of AI and the question: How will the technology work? In other words, contextualization relates primarily to the technical ecosystem. System technologies do not function independently; they are dependent on other supporting technologies or their underlying facilities. An example is the car’s dependence on the oil industry, petrol stations and a road network. Moreover, system technologies become connected over time to other emerging technologies, as the car is connected to electronics. In addition to the technical ecosystem, contextualization is also about the role of the social ecosystem. At a macro level, a lasting effort will be needed to adapt work processes, value chains and knowledge development. Only after this has been done will organizations be in a position to use the technology effectively and become more productive. At the micro level this will require behavioural change and effective interaction between the users and the new technology.
AI also requires various supporting technologies or facilities, such as data, telecommunication networks, chips and supercomputers. Furthermore, we are already seeing increasing connectivity between AI and other new technologies such as 5G networks, the ‘Internet of Things’ and quantum computing. As far as macro level developments are concerned, the expectation that AI will make human work redundant on a massive scale appears unfounded. Rather, a process of intensive training and practice will be required to make it an effective tool in the workplace. At the micro level the task is to achieve effective human-machine interaction. Here the relative autonomy of AI systems forms the main challenge.
Insufficient attention to supporting technologies and facilities (such as good quality, secure and readily available data and networks) will lead to poorly functioning AI systems, underutilization of opportunities or stagnation of development. Just as the road network was essential for the use of the car, so AI requires technical adaptations to the ecosystem. Attention to that aspect is particularly important in those areas where a country can benefit most from AI. For the Netherlands this means areas in which the country has traditionally had a strong international position (such as agriculture and services) and areas where AI can help address existing challenges (such as those in healthcare). Other countries will obviously make other choices, such as manufacturing in the case of Germany or defence in the case of France. Insufficient attention to the social ecosystem will also lead to poor implementation and to all manner of issues, or even rejection of the technology if the users of AI systems are not adequately equipped to deal with these issues. So not only are the quality and safety of AI applications at stake, but also the public benefits that can be gained in areas ranging from wider access to better quality healthcare and education to better government services.
10.1.3 Task 3: Engagement
The third overarching task, engagement, concerns the societal environment of AI and the question: Who should be involved? When new system technologies arise, large companies and governments have the means and interests to be early adopters. Civil society parties usually do not become involved until later. As such these new technologies initially only reinforce the existing balance of power in society. Consider how the deployment of the steam engine in factory production processes marginalized workers or how adapting the infrastructure for the automobile forced non-drivers (at that time mainly poorer people) off the roads.
Stakeholders’ engagement in society can take a wide range of forms. At one extreme is violent resistance, while non-violent protests and calls for bans are also ways of restricting a new technology. At the other end of the spectrum, civil society can play its part in improving a technology – for example, by contributing its own expertise or by applying it in its own practices.
AI in its current manifestations also reinforces existing imbalances. Less affluent citizens, ethnic minorities and women are among the groups discriminated against by algorithms. Civil society is now mobilizing to protest against a number of controversial applications, such as autonomous weapons, facial recognition and the use of AI by the police. Much of this opposition takes the form of protests and calls for bans, but strikes are on the table too. But when it comes to more co-operative forms of engagement aimed at the useful social integration of AI – such as contributing expertise or using the technology to tackle challenges related to climate change, poverty, or human rights –much still remains to be gained.
What will happen if engagement lags behind? It is likely that existing imbalances will be reinforced and the balance of power between governments and large companies on the one hand and citizens on the other further distorted. In particular, the rights of various weaker social parties will be threatened. So, if there is not enough engagement in AI, fundamental rights such as equality, privacy, non-discrimination and autonomy as well as democratic principles like participation, inclusion and pluralism will all be at stake. A regulatory framework is an important prerequisite for shaping this engagement, which brings us to the fourth task for government.
10.1.4 Task 4: Regulation
The task of regulation is relevant at the societal level, focusing on the question: What frameworks are required? When a new technology leaves the lab, it is initially difficult to oversee, adapt or develop the necessary frameworks. Much is still unclear about its nature and effects, and so as long as AI is not yet embedded across the full breadth and numerous contexts of society it is difficult to know what specific civic values it might compromise.
In the early phase, technology companies often promote self-regulation by the sector or argue that users themselves can be relied upon to safeguard certain values. Gradually, however, structural issues come to light that require a more active government role. Other system technologies were initially concentrated in the hands of a few companies, such as (in the US) GE and Westinghouse in the case of electricity or the ‘big three’ in Detroit when it came to automobiles. But other factors also contribute to the need for a more active government role. As technology becomes more deeply embedded in society, it increasingly touches upon civic values that fall under the responsibility of government. With time the broader social effects of a new technology become clearer, and so policy and legislation become less and less tentative. From this point government needs to develop a broader and more unified legislative agenda; separate dossiers no longer suffice.
With AI we saw an initial focus on self-regulation. Today the momentum has shifted towards more active government intervention (the European draft AI Act is a good example of this). At the same time structural issues are coming to light, which government will also have to address if it wants to manage the effects of the technology. These include the concentration of power in the hands of large companies, the growth of surveillance in society and increasing public-sector dependence on commercial businesses.
Of course, there are no panaceas or ‘silver bullets’ for the regulation of system technologies. Properly embedding a technology in society requires a broad set of measures developed over a long period of time. An example is the internal combustion engine that made the motor car possible: seat belts, insurance, number plates, airbags, driving tests, traffic rules and road signs were all steps that contributed towards its social integration – a process that continues to this day because the car and its environment are being developed continuously. It was impossible to foresee that all these measures would be necessary when the car was first introduced. However, this does not mean that the legislator can endlessly vacillate about what the best approach might be. The task of regulation requires both a greater role for government and a broader legislative agenda. If government waits too long to develop its agenda, lawmaking will be left behind by the dynamism of the process. Meanwhile, other stakeholders will have taken control of the way AI is embedded to the extent that it will be almost impossible to reverse this development. Existing frameworks then lose their legitimacy and our social system based on shared civic values will come under threat.
10.1.5 Task 5: Positioning
The final overarching task we have identified is positioning. This relates to the international arena and is about the question ‘what is our international position?’ Firstly, this concerns the role that a new system technology can play in boosting national competitiveness. In the past technologies like the steam engine, electricity and the internal combustion engine helped many countries strengthen their competitive position in the international arena. They even influenced the nature and outcomes of international conflicts; railways were essential to Prussia’s victory over France in 1870–1871 and the first computer code-breakers contributed towards vanquishing the Germans in the Second World War. These two dynamics feed the idea of a global race to dominate a new technology and some countries even try to develop and maintain such innovations completely within their own borders. However, history teaches us that system technologies always have a global character, and that international co-operation is in fact the best way to improve individual countries’ competitiveness and security.
The same dynamic is involved in AI. There is much talk of an ‘AI race’, with the US and China setting the pace. Many countries have therefore developed AI strategies in recent years in order to join this race and to deploy AI to strengthen their competitiveness. But there is also a growing awareness of its impact in the areas of conflict and security. The most prominent application is so-called autonomous weapons. Several international initiatives have now been launched to control the development and extent of this new arsenal. But there are many other military and civilian applications of AI that can threaten national security.
If countries fail to develop their position in AI and pay too little attention to broader co-operation at the international level, they will miss out on opportunities to strengthen their competitiveness. Moreover, not enough consideration of their international position in AI will leave countries insufficiently aware of and prepared for the security risks the technology brings.
10.1.6 Five Tasks, Five Transitions
These five overarching tasks are thus critical to AI’s successful integration into society. But it is also important to emphasize their interrelations. Demystification, for example, strengthens society’s ability to engage with AI technology. So, although these tasks can be separated analytically, in practice a combined approach is needed. The stakes involved in integrating AI successfully are high (utilizing innovation potential, societal acceptance, etc.), and the process puts various civic values at risk – although it is impossible to predict in advance which will be affected, or how. We have argued elsewhere in this report that it is impractical to draw up an exhaustive list of civic values and analyse them all in the light of AI. The unpredictable nature of system technologies necessitates a more dynamic perspective. We therefore suggest that the debate on AI and its consequences for society be conducted on the basis of the five identified tasks. Many contemporary and future issues can be addressed within this broad framework.
With this cluster of five overarching tasks, we thus offer a long-term framework for AI’s societal integration. This, however, does not answer the question of what needs to be done in the short term in the light of these tasks, particularly from the government point of view. In other words, what transitions are involved? Below we describe the transition associated with each task (Fig. 10.2) and then, in the next section, explain each transition with the help of concrete recommendations. The transitions are:
1. From fiction to facts; 2. From abstraction to application; 3. From monologue to dialogue; 4. From reaction to action; and, 5. From nation to network.
Fig. 10.2 Every task requires a transition Full size image
10.1.7 A Broad Agenda for AI
The five transitions represent an AI agenda for the years ahead. Our first observation in this respect is that the breadth of this agenda implies that national governments cannot be solely responsible for its implementation. Across all five tasks a variety of actors in society have a role to play and responsibility to take. For example, academics will be needed in the transition from fiction to a more facts-based approach of AI. Ordinary citizens can help shape this transition too, by informing themselves about AI or by following the ‘national AI course’. The media also have an important role to play in informing people who are unmotivated or unable to find out more for themselves. Meanwhile, much of the transition from abstraction to its application will fall to industry. Government bodies may later become major users of AI, but initially all manner of private-sector players will need to answer the question of how it can be used in practice. In short, all the tasks and the associated transitions will require a collective effort by various actors.
A second observation is that not all steps towards achieving the tasks will require the same effort. In fact, some things will happen automatically. As society collectively gains more experience with AI, for example, we can expect a degree of demystification and thus a more realistic awareness of its implications. Moreover, initiatives are already emerging in some areas. These include autonomous weapons and their effect on countries’ international positions, which are receiving attention around the world. When it comes to regulation, not every new application of AI will require brand new legislation. Existing rules already provide the necessary framework for a variety of applications, and in some cases self-regulation by companies or other societal parties will suffice – for the time being, in any case.
In this report that was originally written for the Dutch government, we are therefore selective in the tasks we highlight: our recommendations concern only those areas in which the WRR believes the Dutch government should take more initiative. However, these recommendations may also apply to other governments. For each recommendation we suggest a number of concrete actions. We end by describing how these recommendations can be supported both institutionally and politically.
| 2023-07-14T00:00:00 |
2023/07/14
|
https://link.springer.com/chapter/10.1007/978-3-031-21448-6_10
|
[
{
"date": "2023/01/01",
"position": 49,
"query": "AI economic disruption"
},
{
"date": "2023/01/01",
"position": 25,
"query": "government AI workforce policy"
}
] |
ChatGPT Strikes at the Heart of the Scientific World View
|
ChatGPT Strikes at the Heart of the Scientific World View
|
https://www.cigionline.org
|
[
"Blayne Haggart"
] |
by B Haggart · Cited by 5 — ... disruption, of creating a true artificial intelligence designed to shape and ... Developing Countries' Business Participation in the AI Economy · Douglas ...
|
As a result, if you can’t evaluate the process for accuracy, your only choice is to evaluate the output. But to do that, you need a theory of the world: knowledge beyond correlations. The danger of a dataist mindset is that a theory of the world will be imposed, unthinkingly, on the algorithm, as if it were natural rather than someone’s choice. And wherever they come from, whatever they are, these theories will shape what the program considers to be legitimate knowledge, making choices to prioritize some information over others.
Consider what is likely ChatGPT’s most lauded accomplishment: that its responses, unlike those of other chatbots, don’t go “full nazi” within 10 minutes. This has been a serious problem with previous chatbots. The most infamous of these is probably Tay, an ill-fated Twitter bot from Microsoft — itself an OpenAI investor. Within 24 hours of its 2016 release, Tay’s users tweeted multiple references to Naziism and other hateful ideologies, which Tay neatly, by design, started to repeat, while also serving up unprompted weirdness such as “ricky gervais learned totalitarianism from adolf hitler, the inventor of atheism,” in response to the question “is Ricky Gervais an atheist?”
Ensuring that ChatGPT didn’t just reflect the often incredibly vile nastiness that passes for online discourse was almost certainly an express design goal of the OpenAI team. They couldn’t trust their correlations, and not just because it would make them look completely ridiculous. OpenAI is an organization with major money behind it, and ChatGPT is almost certainly not cheap to run. OpenAI was started with an initial investment of $1 billion, from investors such as Elon Musk and noted Trump supporter Peter Thiel, among others. In 2019, Microsoft invested $1 billion in OpenAI and is currently in talks to invest another $10 billion in OpenAI on the strength of the ChatGPT hype. OpenAI knew that if their tool had gone “full nazi” after launch, their multi-billion-dollar investments would have been dead in the water.
The point isn’t that OpenAI got the ideological balance wrong or right in its (not fully successful) efforts to tamp down racist and hateful ideologies. It’s that the designers had an idea about what the output should be — one informed by their own preconceived notions, business interests and ideologies. Clearly, they tweaked their system until it produced the output they wanted to see. Its output depends entirely on the choices of its “trainers” — those who decide what data and data sets are important, and design algorithms to follow the rules of correlation that they themselves decide on. Whoever controls the chatbot’s design will shape what it produces.
The Hierarchy of Knowledge
Science doesn’t disappear in a dataist world. What matters is the hierarchy: which groups are driving the discussion and, most importantly, seen as possessing the most important knowledge. In a theocracy or a totalitarian state, science is subordinated to religious or political knowledge.
The same goes for science and technique. Digital technology made possible the global financial system in the 1980s, but it was the financial sector that ran the show. The information technology technicians were consigned to the back of the shop, as it were. The scientist, or the subject matter expert, proposed, and the engineer disposed.
Now these roles have been reversed. We have Apple-branded payments systems. We have PayPal and Venmo, which are seen as tech companies first, financial companies second. And of course, we have cryptocurrencies, the ultimate expression of tech-driven hubris. In the world of the technician, which is where we increasingly live, it makes perfect sense that a tech company would presume to know enough about finance to replace the global financial system.
The Importance of Belief
Dataism’s definition of knowledge is fundamentally unscientific. But just as it doesn’t matter to me whether or not heaven is real, the important thing about machine learning isn’t whether or not the data speaks for itself, but whether we act as if it can. Our assumptions and beliefs about the world dictate how we act in the world.
Much of the data governance debate has focused on how companies with access to troves of our personal data could use this data — as Shoshana Zuboff argues in her influential polemic, The Age of Surveillance Capitalism — to brainwash us and modify our behaviour. In actuality, the real issue isn’t that companies such as Google and Facebook now have the tools needed to cause, as Zuboff describes it, a “seventh extinction,” the death of the human spirit itself. Rather, it’s that governments, companies and individuals will buy into the ideology of dataism and treat the results of pattern-recognition programs as infallible, and regulate accordingly.
It bears repeating: The issue is not what these machines can do, in other words, but what we believe they can do, and how this changes how we act. The problem is primarily ideological, not technological. Driven by a dataist faith in big data, governments, and society generally, are automating and outsourcing countless important activities to the individuals and organizations with the power to command and manipulate the data we’ve decided is necessary to run our lives. We do this not because machine learning is capable on its own of generating unique insights, but because we believe it can.
Automation without Understanding
Different forms of knowledge put different groups in places of power when it comes to determining what knowledge gets created and used, and for what ends. Different types of knowledge workers — be they priests, scientists or tech billionaires — will define and use knowledge differently.
In a big data world, power over knowledge lies with those individuals and organizations that can marshall the resources to collect and deploy the data and computing power, and create the algorithms, needed to make machine learning work.
Their authority comes from the dataist belief that data, and the process of its collection, is neutral, and that the machines they create will produce authoritative and useful knowledge.
The OpenAI approach to creating knowledge reflects a dataist view of knowledge. It betrays a technician’s mindset: automation without understanding. Automation always involves breaking down a process into its component parts and routinizing the parts that can be, and ditching the parts that can’t be, turned into data.
Sometimes, automation produces an acceptable result. Other times, it can transform the nature of the activity entirely.
During the early stages of the COVID-19 pandemic, for example, tech companies were quick to insert themselves into the public health system by promising digital contact tracing, using location tracking of peoples’ smartphones as a substitute for reporting personal contact with infected individuals. However, as political philosopher Tamar Sharon recognized, this automation stripped long-established manual contact-tracing processes of the aspects that actually make contact tracing useful, such as whether there was a wall between individuals in close proximity. It’s no surprise that, from a public health perspective, digital contact tracing amounted to very little.
Automation without understanding is also on display with ChatGPT and the student essay. As every teacher will tell you, student essays are, almost without exception, boring and repetitive. Countless op-eds have highlighted how ChatGPT can replicate a rote high-school essay. From one angle, it seems to have automated the student essay.
In practice, however, it’s only automated the least important part of it. The essay is a centuries-old, proven technology for teaching people not only facts but also how to think. Ignore for a moment that ChatGPT is a giant auto-complete machine that produces bullshit: text without understanding. ChatGPT automates only the output aspect of the essay. As a technology, it — and OpenAI by extension — ignores that the student essay’s main purpose is not to present information but to teach a student how to think by following the steps to produce essays. We write bad essays today so that we can write good essays tomorrow.
By potentially destroying the essay as a pedagogical tool, OpenAI has taken direct aim at the very foundations of our science-based educational system, all in the name of disruption, of creating a true artificial intelligence designed to shape and create a new form of knowledge.
At Stake: The Power to Control Knowledge Itself
A chatbot or search engine’s clean interface can make it seem like its output appears out of thin air, delivered by a neutral machine. But algorithms, computer programs and machine-learning processes are explicitly designed by people to do some things, and not others. The power to design knowledge-creating machines is a form of ultimate power, to control what counts as knowledge itself.
This power is even more awesome when you consider that we, the great unwashed, can only evaluate the output, not the steps that led to it. Unlike a book, which provides information about the publisher, the author and the author’s sources that you can review to determine its trustworthiness, ChatGPT is an oracle — moreover, one that can be manipulated to produce what its creators consider to be the “correct” outcomes.
As academics Mary L. Gray and Siddharth Suri remind us, so-called artificial intelligence systems always involve behind-the-scenes workers who make decisions within systems designed to make choices when it comes to content or data evaluation. These choices, by definition, favour some groups and outcomes over others. There will always be a thumb on the scale.
That’s from the inside. On the outside, absent scientific verification, dependence on the oracle reduces the rest of us to hapless recipients of automated wisdom who simply must trust that the oracle is correct — which it is, in a post-science world, because it’s the oracle. It’s a form of knowledge that demands awe and acceptance, not understanding. In effect, it degrades knowledge into a form of magic. It removes from individuals the power to understand, question and challenge. It’s infantilizing.
Dataism, Not Machine Learning, Is the Real Threat
But machine learning itself isn’t the problem. I’m writing this using Microsoft Word. While its spell- and grammar-checkers aren’t perfect, they’re still useful. The same is true for technology in general. Tesla’s supposed full self-driving mode, according to safety research organization the Dawn Patrol, may have an unfortunate tendency to lead to collisions, but driver-assistance technology seems like it can be helpful.
By contrast, OpenAI’s technology, and machine-learning tech generally, is only made possible by appropriating the work of billions of people — artists, authors, regular people — turning it into data, and using that data without the creators’ express informed consent to construct the model. This tool, if used as intended, could deprive artists and educators of the ability to earn a livelihood or do their job.
ChatGPT’s designers could have aimed to create a tool with a regard for verified truth, or at least judged their progress by whether that is possible. But such a goal, which would have required privileging scientific, subject expert judgment, goes against the hard core of dataism, where truth is determined by mere correlation.
While the scientific method empowers, oracular tools like ChatGPT create two problems. First, they make it that much more difficult for non-experts to evaluate and reason for themselves. (Some people have suggested that teachers could assign students to evaluate ChatGPT output for accuracy. That might work for a time, at the cost of turning students into fact-checkers instead of training them to produce knowledge.) More importantly, it presumes a world in which the scientific method still dominates. But when a society is in thrall to dataism, that can no longer be presumed. To whom does one turn if there’s no way to differentiate scientific texts from nonsense?
Second, trusting in correlations merely subsumes background ideologies, preferences and beliefs into the data and algorithmic designs. There’s a reason why system after system based on machine learning has been revealed to produce racist and sexist outputs: when you depend on correlations to produce knowledge, you end up with conventional wisdoms and popular (and sometimes unsavoury) opinions, not accuracy. But if we place our trust above all in the correlations, on what grounds can we say that the machine is being “improperly” racist?
Doing Better Than Good Enough
The bottom line: Like so many Silicon Valley pitches, ChatGPT promises more than it can deliver. It’s the proverbial stopped clock that’s right twice a day. It promises understanding; it delivers authoritative-sounding nonsense that must still be evaluated by actual experts before it can be trusted. It eliminates the rote steps (reading actual research, writing bad essays) that we know create scientific knowledge and teach people how to think. It pretends that a technology designed to further the business interests of its backers has been created in the public interest. It unleashes an untested technology on an unwitting public as a form of market research. Imagine the reaction if a drug company did the same thing with an untested drug.
ChatGPT isn’t automating the writing or research process. It’s creating a completely new form of knowledge, one in which correlations confer legitimacy, and in which the evaluation of the truthfulness of these correlations occurs behind the scenes, embedded in programming decisions and hidden labour. It is an approach that places scientific understanding in a secondary, and at best, an evaluative, role. The issues raised by ChatGPT are about more than a single technology. Meta’s and Tesla’s share values may be cratering, but the race to master machine learning and deploy related technologies in government and industry highlights how ingrained dataism has become. As José van Dijck remarks in her 2014 article, businesses, governments and scholars are all deeply invested in the idea that digital data sources provide us with an objective and neutral, even “revolutionary,” means by which to better understand society, make profits and conduct the business of the state.
| 2023-01-23T00:00:00 |
2023/01/23
|
https://www.cigionline.org/articles/chatgpt-strikes-at-the-heart-of-the-scientific-world-view/
|
[
{
"date": "2023/01/01",
"position": 58,
"query": "AI economic disruption"
}
] |
Disruptive business value models in the digital era
|
Disruptive business value models in the digital era - Journal of Innovation and Entrepreneurship
|
https://innovation-entrepreneurship.springeropen.com
|
[
"Sewpersadh",
"Navitha Singh",
"College Of Accounting",
"University Of Cape Town",
"Uct",
"Cape Town",
"South Africa",
"Floor",
"Leslie Commerce",
"Rondebosch"
] |
by NS Sewpersadh · 2023 · Cited by 105 — The coronavirus pandemic illustrated how rapidly the global environment could be disrupted on many levels but also drive an acceleration in others.
|
Several constructs emerged from the thematic analysis of the integrative review for developing a digital business model, reflected in Table 3.
Table 3 Digital business model key constructs Full size table
Using the people, process and technology (PPT) framework (Leavitt, 1964), these ten constructs from Table 3 and innovation capabilities are presented in Fig. 2. This study has added governance to the PPT framework to form the PPTG framework. Governance is imperative for oversight over the value-creating activities (Sewpersadh, 2019a) to balance the trade-offs from the synergistic benefits of lower costs, increased coordination, greater productivity and value delivery with the ethical and risk concerns over customer data.
In Fig. 2, people have been expanded to include service bots. Collaboration between service bots, employees and customers are integral for value co-creation. Service bots cost-effectively record customer information from the various stages of their service interactions, allowing for data warehousing. Data warehousing is important for allowing data mining tools and the analysis of critical customer parameters.An ethics and risk officer will play a key governance role in overseeing the principles of fairness and ethics over emerging technologies, such as service bots. Increasingly companies integrate their AI technologies with social media platforms which necessitates the ethics and risk officer to detect, correct and prevent any biases that the service bots learn through the data they collect. For example, service bots may discriminate against customers based on their demographics (Puntoni et al., 2021). In 2016, Microsoft launched a service bot called Tay to research conversational understanding. This project failed, because the developers did not anticipate that some Twitter users would teach the bot to make racist, inflammatory and offensive tweets through its Twitter account (Berditchevskaia & Baeck, 2020). For this reason, recent studies proposed digital corporate responsibility to guide ethical dilemmas related to AI technology (Lobschat et al., 2021). There are also ethical and security risks when service bots impersonate humans (van der Aalst et al., 2018), since they may make improper judgements due to contextual changes that may remain undetected, leading to unintended consequences. For instance, service bots may make poor-quality recommendations that do not align with customer interests or may expose customers to vulnerable and risky situations (Mullainathan & Obermeyer, 2017). Service bots require service audits to prevent poor service quality outcomes. Service bots also have excessive access and privileges that place them at risk of cyber-attacks. The ethics and risk officer may assist in safeguarding data using surveillance methods to detect intelligent malware.Footnote 16 Research has found that customers are more likely to act unethically and misbehave (LaMothe & Bobek, 2020) when interacting with service bots. Therefore, service bots need to be monitored to detect and prevent these infringements.
In Fig. 2, PPTG is improved with technologies for process value configuration. Technology with people allows for smart analytics on service value capture and optimisation. For example, service staff, key accounts managers and digital developers in Solutioncorp evaluate customer service data to identify priority areas for AI innovation (Sjödin et al., 2021). This dispersion of emerging technology gives rise to a disruptive landscape in the knowledge economy, necessitating more R&D and continual business model innovation. The three overarching themes from the constructs presented in Table 3 are innovation, sustainable business models and value creation, which will be discussed further below.
Innovation continuum
The rapid pace of the evolution in technology innovation accelerates the diffusion of innovations (Rogers, 1995). The increased R&D in innovation creates a continuum (Fig. 3), where companies are not statically classified according to their degree of innovation but rather placed on a continuum. Those businesses that recognise innovations’ relative advantages, compatibility and trialability (Rogers, 1995) will move to the higher end of the continuum. Although, a high-innovation company may not remain a disruptor in the market if it becomes complacent or myopic with its innovation strategy and neglects to continuously improve its business processes. This complacency can be explained by the icarus paradox, where success may lead to a path of convergence with an emphasis on the same strategies, which may simplify and desensitise divergent evolving demands (Elsass, 1993; Miller, 1990). Past successes promote a defensive mindset and overconfidence, resulting in the persistence of the same strategic formulas when executing innovative strategies is the most appropriate response (Sewpersadh, 2019b) to the market’s changing needs. Thus, this paradox may lead to myopia, complacency and inertia. This complacency leads to a condition of ‘unconscious incompetence’, where the lack of knowledge of the availability of advanced technologies leads to suboptimal decision-making or decision paralysis on deploying such technologies. For this reason, the degree of innovation is bidirectional on the innovation continuum, which allows for the acceleration and deceleration of innovation investment. As business models transition from traditional to transformative ones, eventually evolving into disruptive ones, those with myopic capabilities soon find their business models antiquated. When companies intensify their investment in innovation, they adopt a futurist strategy allowing them to transition up the innovation continuum and challenge complacent companies.
Rogers (1995) cautioned that insufficient knowledge, inability to predict consequences or overzealous innovation investments might lead to over-adoption. Also, the complexity or incompatibility of innovations may not be suitable for some businesses, which may jeopardise their positioning on the continuum. For this reason, governance structures, such as a digitalisation committee, are important for moderating the firm’s adoption strategy. This committee will assess the suitability, acceptability, feasibility and sustainability of developing or acquiring innovations. Integrating stakeholder networks in collaborative activities creates trust-based relationships, legitimacy and good governance that allows for the acceptability of innovations. In Fig. 3, governance optimisation is vital for ensuring value-maximising decision-making concerning value-creating activities for all stakeholders (Sewpersadh, 2019a).
There could also be a reluctancy to allocate resources for R&D due to a digital paradox (revenue growth is not as expected despite the proven growth potential) (Gebauer, et al., 2020). For these reasons, value creation and governance optimisation are unidirectional factors in Fig. 3 and are placed on the high end of the continuum, where disruptive business models operate. Governance is essential to moderate the negative effects of an over-adoption, complex or incompatible innovations and the digital paradox. Good governance is also critical for balancing trade-offs when making strategic decisions. For instance, harmonising the need for legally protected intellectual assets for profit maximisation and sustainability with knowledge sharing to build collaborative networks.
Central to the innovation process is the need for firms to create and acquire “new combinations” of knowledge. Based on the resource-based theory, complementary assets and capabilities are scarce but valuable strategic resources, since they have strong path dependencies that are difficult to imitate (Barney, 1991), thus shaping the firm’s competitive advantage in the cooperative network. Since companies compete in a capital-intensive space, with barriers to entry and economies of scale, profits may be achieved with the legal protection of competitive advantages, such as closed innovation. Closed innovation is the internal research within a particular company that is generally protected by patents, so that access to that innovation is controlled by the rightsholder (Chesbrough, 2003). Progressively, open innovation has become a way in which key resources are obtained for the development and execution of innovation (Chesbrough, 2003, 2011). Open innovation is a means of sharing costs, ideas, synergies and skills (Chesbrough & Crowther, 2006) from value networks to co-create innovation rather than an individual company outlaying capital to conduct R&D from scratch. For this reason, in Fig. 3, the networking capabilities of a company also follow the direction of its innovation policy due to the collaborative work with extended networks that allow for the acquisition of external knowledge. As innovation diffuses, collaborators within forged networks stimulate newer co-created innovations with superior outcomes.
A significant limitation to knowledge sharing is the disclosure of internal knowledge to external collaborators (Cassiman & Veugelers, 2002), commonly referred to as the risk of knowledge leakage (Gans & Stern, 2003) or the “paradox of openness” (Laursen & Salter, 2014). This paradox describes the fundamental tension between knowledge sharing (value creation) and knowledge protection (value appropriation) in open innovation. Open innovation may increase the imitation tendency of mimetic companies, who benefit from incurring fewer costs and inefficiencies with access to extended networks. Therefore, a company’s position on the continuum and its competitive stance in the industry depends upon its ability to remain at the technological forefront. Consequently, open innovation also poses significant governance challenges to monitoring, controlling, and managing intellectual property rights in enterprise innovation (Graham & Mowery, 2006). Hence, risk-averse companies usually have linear business models with a unilateral dependency on internal resources. This tendency to be an information hoarder lends itself to a closed innovation competitive stance. For this reason, the company’s risk strategy must also be considered, since innovation pioneers may be more risk-tolerant than those with more traditional business models. As newer, more revolutionary technologies become available, static business models with poor networks risk being on the low end of the innovation continuum. Companies that have failed to keep at the forefront of technology do not have sustainable business models and may lose their extended networks.
Sustainable business models
The diminishing competitiveness of traditional business models (McGrath, 2010) has led to a fundamental rethinking of the firm’s value proposition for new prospects (Bock et al., 2012) on refining how an existing product or service is provided to the customer (Velu & Stiles, 2013). Reconceptualising structural elements for technology and resource capitalisation to create new activity frameworks and networks aimed at clear value propositions is known as business model innovation (Battistella et al., 2017; Hamel, 2000; Helfat et al., 2007). Therefore, business model responsiveness becomes a critical success factor in addressing challenges in the knowledge economy. A business model’s alignment and coherence should be mutually reinforcing and incorporate a response to the concomitant influence of contextual factors (Dehning & Richardson, 2002; Melville et al., 2004; Schryen, 2013) and lag effects on firm performance (Schryen, 2013). The responsive business innovation model, in Fig. 4 is a hybridisation of prior value models with interlinkages to current service technologies employed in the market, including digital platforms, crowdsourcing, blockchain, crowdworking, big data and service bots.
Fig. 4 Source: Author Responsive Business Innovation Model. Full size image
Figure 4 ascribes to Santos et al. (2015), where the model is more about “how is it being done?” than “what is being done? It incorporates an iterative strategy that maps cross-functional relationships between innovations and the underlying activities to be responsive to the evolving economic environment. Large corporates often use share centre services to support their network of firms under a GBS structure. However, with the evolution of AI, the GBS structure can evolve into a digital platform business model. A responsive business innovation model focuses on facilitating interactions across many shared centres by providing a governance structure and a set of standards, so that they operate as one cohesive ecosystem. It is an activity system with interconnected and interdependent activities to satisfy the market’s perceived needs (Foss & Saebi, 2018).
The responsive business innovation model enables the acquiring, developing, and integrating of key resources to overcome inertia. Introducing a new business model into an existing organisation is challenging and may require a separate organisational unit to redefine and reconfigure the model. For example, General Electric (GE) experienced business model transformation conflicts when they tried to adopt digital servitisation. There were conflicts between digital and physical service offerings, new ecosystem partnerships and traditional supply chain relationships, digital revenue and product sale models (Moazed, 2018). For this reason, positioning a Centre of Excellence (COE) is important, since it can provide the organisational structure, methodology, skills, tools and governance framework for handling the future innovation needs of a large global corporate (SSON, 2018). A GBS structure includes a COE for higher level business support and specialist work and thus is incorporated in Fig. 4. COE comprise of a centralised specialist team to promote collaboration and provide higher value services, resulting in economies of scale. COEs focus on agility,Footnote 17 CRM and talent development while standardising and automating cross-function end-to-end process ownership), resulting in reducing costs and harnessing process efficiency (SSON, 2018). Examples of these are procure-to-pay (supply chain and accounting) and hire-to-retire (HR and accounting. The positioning of the GBS is better placed by groups of talent (area of expertise) rather than location, function or lowest costs.
The CRM literature provides a framework to delve into human motivations concerning their buying incentives, biases and emotional connections. For this reason, CRM is at the heart of the business model with AI differentiators (McAfee et al., 2012; Payne & Frow, 2005; Stringfellow et al., 2004) that responds to evolving consumer behaviour and expectations. The deep knowledge of consumers’ emotional and functional needs allows businesses to optimise capital to address those needs. This strategic response to customer needs and experience requires standardisation (lower costs, benchmark service quality) and differentiation (premium service). For instance, businesses could standardise business processes through RPA for efficiency gains but personalise services via service bots for market differentiation.
Service bots are key components of a digital strategy for entities searching for innovative and cost-effective means to build closer customer relationships (Artificial Solutions, 2020). With a GBS structure, the service bots may need to be multilingual due to the diversified client base. Furthermore, by integrating with social media (shown in Fig. 4), service bots can access clients’ online data and learn their preferences, sentiments, outlooks and proclivities. The data from clients’ online presence are often undervalued, but access to this enables businesses to transcend beyond basic business intelligence. Therefore, the service bot’s initial customer interaction will offer a superior service through seamless verification of personal information (similar to the Facebook sign-up process) and quick information transfer through hyperlinks. A seamless trail of conversations can be achieved whenever users swap from device to device (cross-platformFootnote 18), since this practice improves engagement and customer fulfilment (Artificial Solutions, 2020). The increased customer engagement means more actionable and enriched data to train service bots to personalise the customer’s experience. In so doing, service bots can service customers more competently and cost-effectively without human error (Artificial Solutions, 2020; Kiat, 2017).
A limitation of service bots is that humans can notice tone and subtext in a way that a service bot could never master. This disparity calls for cross-functional collaboration between service bots and higher skilled humans, transitioning toward blended workforces. Data-centric CRM harness the potential of big data to focus on not only the functional but also the deeper psychological aspects of buying behaviour (Stringfellow et al., 2004). Access to client data is essential for value creation (Paiola & Gebauer, 2020) to improve existing services and create novel innovations (Opresnik & Taisch, 2015) within the confines of privacy laws. Automating customer interaction with service bots (see Fig. 4) allows for a higher degree of message personalisation without increasing personnel costs. In-depth analysis of unstructured conversational data conveys perceptions on what is done well or what can be improved by the business to develop market differentiators for a strategic competitive advantage. Smart analytics, such as sentiment analysis, support businesses in gauging their customers’ mindsetsFootnote 19 and analysing the customer’s journey more effectively while remaining within the confines of data safety legislation.
Strategy guides and shapes by including the company’s brand reputation, Fig. 4. The iterative CRM engagement strategy and value outlook (short, medium and long term) is built from big data collected from the AI-led CRM and crowdsourcing from their networks. This process allows companies to leverage their large network of end-users to inform the co-created products, services and experiences. A large network also provides microwork opportunities through crowd-working platforms for comprehensive support and supplement human labour. However, managing the trade-offs between stakeholders, technology, and societal benefits is important. Stakeholder engagement is essential in identifying key stakeholder requirements for these benefits to occur. Accordingly, business models should recognise and incorporate environmental, social and governance (ESG) goals, whereby trade-offs must be managed. For instance, automation disrupts the human capital leverage model, in which a trade-off exists between harmonising the prospective savings from automation and the human impact of job losses. Due to the escalation of global warming, business models must also incorporate innovative sustainable environmental solutions (Carayannis et al., 2020). Therefore, innovations must be expanded beyond service innovations to ESG innovations.
In Fig. 4, the benefits of using blockchain technology in a business model are also presented. Blockchain represents an endlessly accumulating list of records stored in “blocks” protected using cryptography principles (Arnaut & Bećirović, 2020). The peer-to-peer protocol ensures unambiguous and common ordering of all transactions in blocks, a process that guarantees consistency, decentralisation, integrity and auditability (Arnaut & Bećirović, 2020; Yuan & Wang, 2018). These features make the blockchain’s permanent ledger resistant to data manipulation, which is a value contribution to the company.
Value creation
A business model’s lifecycle involves “periods of specification, refinement, adaptation, revision and reformulation” (Morris et al., 2005 pg.732). The business model’s initial period in the lifecycle has a process of trial and error, where core decision-making delimits the firm’s evolution. For this reason, a value creation cycle is essential to harness a sustainable competitive advantage by continuously refining, adapting, revising and reformulating a business model to counteract the limitation of becoming static. In Fig. 5, the importance of the continual assessment of the contextual factors, and the suitability thereof, feed into the value creation cycle necessitating the need for change. However, the suitability of this change must be assessed in terms of the company’s contingencies. Research is necessary for informed decision-making on whether the change is incremental versus transformative to reap all the benefits and value that innovations offer. For value creation, the decision-making process should be free from bias and consider the business’s ESG values, goals, and trade-offs. It is also important to be cognisant that there is a time lag before benefits can be realised. A value architecture may also assist in alleviating some of the trade-offs, particularly structuring a digitalisation committee.
Fig. 5 Source: Author Value creation cycle. Full size image
The value architecture (Osterwalder & Pigneur, 2010), presented in Fig. 6, allows a responsive business innovation model to capture and create market activation to build the deep, compelling experiences customers desire with service-related products. However, there is a need to balance the trade-offs between conflicting value drivers. For instance, costly R&D may have environmental consequences that conflict with the desire to provide a good return on capital. For this reason, a clear value preposition is the first step in the value architecture. A value preposition is the underlying economic logic explaining how value is delivered to customers at the appropriate cost (Magretta, 2002). The building blocks of value proposition, configuration, delivery and capture (Osterwalder & Pigneur, 2010; Osterwalder et al., 2005) must be considered to develop a sustainable competitive advantage for the organisation (Teece, 2010). While the value preposition remains customer centred, the value configuration and capture are focused on relational selling using technological innovations. While the value delivery is focused on efficiency and service optimisation using service innovations.
| 2023-12-14T00:00:00 |
2023/12/14
|
https://innovation-entrepreneurship.springeropen.com/articles/10.1186/s13731-022-00252-1
|
[
{
"date": "2023/01/01",
"position": 69,
"query": "AI economic disruption"
}
] |
Bridging the accountability gap of artificial intelligence
|
Bridging the accountability gap of artificial intelligence – what can be learned from Roman law?
|
https://www.cambridge.org
|
[
"Klaus Heine",
"Alberto Quintavalla"
] |
by K Heine · 2024 · Cited by 9 — Footnote On the other hand, it is contended that the disruption of AI ... economic potential of AI. From the Roman law experience, one would expect a ...
|
Introduction In recent years there is hardly a topic in legal scholarship that has attracted as much attention as artificial intelligence (AI). That has to do with a whole array of doctrinal legal issues, ethical challenges, socio-technical expectations as well as politically-charged industrial politics. The discussions about regulating AI are most of the time an amalgam of legal doctrines, legal methods and author-specific aspirations of what AI may mean for humans and the future applicability of law. The level of sophistication in some of these discussions has been quite high. At the same time, the debates are sometimes quite controversial. On the one hand, it is argued that AI is only another new technology that may create some challenges but, eventually, it will be integrated and handled by the canon of incumbent law.Footnote 1 On the other hand, it is contended that the disruption of AI refers not only to technology, but also to established legal routines and hence new legal designs are needed for a successful integration of AI into law.Footnote 2 That the latter set of questions is on the doorstep has only recently started to become apparent. Although autonomous decisions by AI might not yet be the norm as engineers say, legal and ethical questions can rapidly materialise due to the constant advancement and improvement of AI. It is in this context that opening up a debate on how law can possibly address the challenges posed by AI turns out to be a beneficial process. Putting all specificities and branching of the legal discourse aside, there are two pillars on which the current debate on AI is grounded. A first complex of questions can be traced back to what has been called the ‘responsibility gap’ or ‘accountability gap’.Footnote 3 The accountability gap refers to the problem of allocating responsibility to AI. If an AI entity undertakes autonomous decisions, then the AI may also be responsible for its own decisions. But how can an AI become responsible in a system of legal obligations that are tailor-made for humans and corporate actors which assume human decision-makers? Can AI be liable for its own decisions? If so, what would such an allocation of liability look like? An even stronger case can be made for AIs that communicate with each other and which coordinate their decisions, as is the case, for example, with algorithmic collusion. Would those networks create a separate legal entity that can be held accountable and which creates legal consequences for its owners? Those questions, which seem to be looming, would not be easy to address since they challenge the incumbent legal system. Admittedly, most AI systems currently have a human in the loop – the technology not yet being mature enough for autonomous decision making. The number of AI systems that may qualify for fully autonomous decision making is, however, likely to increase. One needs only to think of the rising number of autonomous care robots in assistance and care.Footnote 4 Thus, legal scholars have begun to investigate how to address that accountability gap. The second pillar of the legal debate is concerned with the consequences that different legal designs for AI may have. The two dimensions of consequences are either ethical or economical, or a mix of both. This is clearly apparent in the EU Commission White Paper on Artificial Intelligence and the Proposal for a Regulation laying down harmonised rules on artificial intelligence, both endorsing an AI approach that is human-centric (ie fulfilling certain societal values) and acts as a catalyst for economic growth (ie aiming to raise per capita income in the EU).Footnote 5 This approach is also mirrored in the recent EU Commission proposal for an update of the Product Liability Directive, aiming at the coverage of AI-related harms.Footnote 6 In that sense, the rules governing AI are not discussed from the doctrinal angle of consistency within a system of norms, but as socio-technological tools to achieve certain ends.Footnote 7 In the case of the EU, the aim is to catch up with the US and China by providing a legal framework for AI that facilitates EU-based business models. This contribution will deal with the accountability gap and its associated legal challenges arising from the deployment of AI by drawing inspiration from a particular instance in Roman law. In fact, an analogy has occasionally been made in the literature between how ancient Romans regulated slaves and how AI might be regulated.Footnote 8 Slaves were allowed and expected to take autonomous decisions up to a certain degree, thereby implying that those decisions might entail failure and damage. This made it necessary that the law would balance the risks between the master, on the one hand, and third contracting parties, on the other hand. An effective governance of the contractual relations of slaves was necessary to raise the economic potential of slaves for their masters and to ensure relational trust for third parties. In this paper, we are not arguing that Roman law provides the blueprint for dealing with today's AI problems, or that it assists in the definition of legal personhood for robots. This would be too far-fetched for a couple of reasons. First, slaves were actual persons endowed with the thinking (and sentient) capacities of any human being – something that AI entities lack. Secondly, and relatedly, the range of activities that slaves could carry out was infinitely broader than the ones that an AI system can currently operate autonomously. However, Roman law provides a stock of knowledge that can be helpful to sort out certain challenges that the deployment of AI systems has started to pose and will continue to pose. In other words, our contribution aims to give guidance on the direction in which solutions for the agency problem of AI can be found, bearing in mind that technological progress is a gradual process, and the accountability gap is only nascent given a series of attempts by today's law-making to address it. The paper is organised as follows. In Section 2, we explain how the autonomy, association, and network risk of autonomous decision making sometimes leads to the accountability gap in contemporary law. Section 3 delves into Roman law and explores how it dealt with autonomous decision making of slaves. It will become apparent that there are striking parallels between the legal problems that had to be solved then and those needing to be solved now. It will also become clear that the accumulated knowledge implied in Roman law provides interesting suggestions on how to possibly shape legal designs aimed at closing the accountability gap of AI. Section 4 puts the autonomous decision making of machines in a wider context by stressing that the law's function of solving conflicts and facilitating cooperation is intrinsically linked with how to balance the allocation of risks among different stakeholders. The paper ends with a brief conclusion.
1. The triple-helix of the accountability gap Damages, losses, and wrong expectations cannot be avoided in a world of uncertainty and fallible knowledge. Law or any other institution cannot simply rule out losses and misfortune. A trivial example is traffic: terrible accidents can happen at sea, in streets or in the air, but one would hardly decide from that to stop traffic and transportation. The typical answer to risk is rather to spot the decision-making entity and to constrain its sphere of activity to a degree that is in accordance with societal standards; this may also include an obligation to compensate victims. Hence, in property, contract, and tort law it is about spotting responsibility and agency, thereby facilitating human action and trade to the benefit of the involved parties. Where necessary, the public regulation of specific activities complements the private law. Private and public law aim at the same target from different angles: the resolution of conflict by identifying the accountable agent(s).Footnote 9 Thereby, conflict resolution should be efficient in the sense that the purposes of all agents which are affected by a conflict are considered. That means the conflict resolution mechanisms which are provided by law should be informed, purposeful and prevent strategic action to the disadvantage of third parties. There should be no accountability gap. Over the exact meaning of ‘informed’, ‘purposeful’ and ‘strategic’ there might be dissent, but the root problem of the accountability gap is straightforward. The accountability gap refers to a missing link between a law or regulation, on the one hand, and a responsible decision or action, on the other. The accountability gap is not a severe problem when there are appropriate tools to repair it.Footnote 10 Judges often repair smaller accountability gaps by employing an existing law through interpretation. But there are also larger accountability gaps that cannot be easily bridged by expanding an established law, because the result would not only be a doctrinal ‘overstretch’, but the deficient legal design would also lead to dysfunctional decisions and actions.Footnote 11 In these latter cases new doctrinal solutions and tools are necessary that lead to socially meaningful results. These kinds of paradigmatic shifts in law have happened in the past and are in principle not a new phenomenon. Examples include the invention of the modern limited liability company as a reaction to the new capital-intensive production possibilities of the industrial revolution,Footnote 12 the legal definitions and ways of how to deal with electricity as a sort of intangible good,Footnote 13 or the emergence of enterprise liability.Footnote 14 A similar turning point is being reached with the advent of AIs and robots, too. Autonomous decision making seems destined to bring doctrinal routine to its limit, whether that is in automated contracts, the liability of surgery robots in hospitals or in the case of algorithmic collusion creating hardcore cartels. To better understand what principal legal problems would be involved if machines were to take decisions autonomously, it is worthwhile distinguishing between three different types of risk: (1) the autonomy risk; (2) the association risk; and (3) the network risk. These three risks constitute the triple-helix of the accountability gap and may require a recalibration of responsibility between human and artificial decision makers.Footnote 15 The autonomy risk. This sort of risk may emerge when AI entities have leeway to take their own decisions based on what they have learned from (big) data. It is this type of machine autonomy that we often have in mind when we think about robots doing the job of humans. For example, it is not unrealistic to imagine that an AI could formulate independently the terms of a contract and sign it in the future.Footnote 16 By doing so, AI would create a valid obligation against the contractual partner. This would not mean that this scenario is currently happening nor that the AI would automatically become a self-standing legal person. However, this situation would make the AI identifiable as a distinctive entity (legal representative) in the process of contracting, in which the owner (employer) of the AI might be the ultimate principal vouching for the fulfilment of the contractual obligations as well as for any possible damages. An even more common example is extra-contractual liability arising from autonomous healthcare robots, when one would reasonably ask for responsibility on the part of the AI and compensation of victims. In this regard, one should note that the liability of contemporary operators denies compensation if the operator has maintained the AI according to the state of the art of possible safety standards.Footnote 17 Moreover, it is yet not clear whether software codes that establish algorithms fall under the European Product Liability Directive.Footnote 18 While it can be assumed that at the moment consumers are still sufficiently protected by legal interpretations of liability laws, sector specific regulations and insurances (eg car liability insurance), the progress of AI technology is likely to lead to more legal inconsistencies. In addition, this growing inconsistency in legal design would have the side effect that the incentive for controlling the developmental risk of the AI is thwarted, with detrimental effects on the usage of those advanced systems. A concrete example can be autonomous vehicles since technical experts provide the prospect of full driving autonomation with no need for a human to drive – so-called levels 4 and 5.Footnote 19 To counteract this scenario, one may argue for a clearer attribution of responsibility. Similarly, and as discussed below, the introduction of the corporate form in the seventeenth century made it easier to find the locus of responsibility allowing for a more rapid advancement of the industrial revolution. That does not mean that AIs and robots should be legally treated like humans, simply because they create and sign contracts. The machines come into the world as distinctive legal entities because humans would attribute to them, for pragmatic reasons, decision-making power. Accordingly, the deliberate attribution of decision-making power may create a distinct locus of responsibility that is not fully covered by human oversight, although a human owner might be in the background as the principal.Footnote 20 This mismatch of responsibility and decision making comes strikingly forward in academic and policy discussions, when one asks for ‘explainability’ of algorithmic decision making.Footnote 21 But, at the same time, it is a core feature of machine learning that the exact reasons leading to a decision remain in a black box. That makes it a deliberate and consequentialist decision of humans to attribute responsibility to AIs for the risks that they may cause, because this legal design yields advantages for society over legal designs that would simply expand the incumbent legal designs. That does not mean that AIs’ autonomy would be unrestrained or that responsibility becomes a shallow category. On the contrary, it means that a socially advantageous legal design becomes integrated into the conflict resolution mechanisms of doctrinal law. To underscore the last point, it is worthwhile remembering the introduction of the limited liability company some 200 years ago. It was also not a human but a corporate actor with its own legal personality that was invented against the background of colonial trade and the need to raise financial capital for the new production possibilities of the industrial revolution. Hence, the introduction of legal personhood for companies was a deliberate act to reap the benefits of technological progress and the exploration of new parts of the world.Footnote 22 The process of introducing new corporate forms was thus not ad hoc, but was a process of legal experimentation until the adequate risk allocations between a company's stakeholders had been found. Moreover, the vast literature about the regulatory competition between company laws indicates that legal experimentation to find out the best legal designs never comes to an end.Footnote 23 In addition, the history of company law teaches us that there is not one, but a need for very different corporate forms with very different levels of sophistication – a point to which this paper will return in the final section. In summary, the autonomy risk may emerge when decision-making power is delegated to AIs. This delegation is for good reasons, because otherwise the benefits of AI cannot be reaped. But that may bring with it a need for a recalibration of the accountability between a human principal and the AI as agent. This recalibration must close the accountability gap in order to resolve conflicts in the case of failure of AIs as well as to re-establish doctrinal consistency. Moreover, the accountability gap must be closed in a smart way, meaning the legal design must fulfil its purpose in an effective way and should facilitate the application of algorithmic decision making. The association risk. This type of risk may materialise in man-machine associations. That is when humans and AIs collaborate and form an entity which interacts with other entities. An illustration is a surgeon who collaborates with a surgery robot to get the best result for a patient. This can be the case of an outside medical specialist who supervises the operation of Smart Tissue Autonomous Robot – an AI that can autonomously perform laparoscopic surgery – that is owned and operated by the hospital.Footnote 24 This scenario makes it difficult to allocate responsibilities for compensation purposes – eg whether the doctor should be considered as operator or user.Footnote 25 Another example can be the decision over a mortgage for a family house made by a bank employee in conjunction with a predictive analytics software that is scoring a high default risk of the couple asking for the mortgage due to a bias in the model used.Footnote 26 In this scenario, it is a tall order to prove voluntary or involuntary discrimination by the bank which had partly relied on (an opaque) AI technology.Footnote 27 In man-machine associations, man and machine bring in their comparative advantages which meld into one service. In the case of misfortune or damage, it is barely possible to sequentially trace back all decisions which were made either by the machine or the human and to allocate responsibility accordingly.Footnote 28 Therefore, those associations of man and machines may be regarded as a symbiosis that creates its own legal entity, at least as a locus for responsibility in the case of contractual and non-contractual liability.Footnote 29 This would still preserve the ethical obligation with the human but recognise that the decisions have been made in a conjunction with a machine. Any regulations or legal obligations are then targeted against the hybrid and not only the human(s) involved.Footnote 30 This yields the advantage that potential victims of the hybrid know exactly who to approach in case of damages or malperformance. The network risk. This risk type points to a scenario in which the decision making is located in a network of AIs. AIs in a network learn from each other and can coordinate their decisions. Those networked AIs can do a whole range of things. Surgeon robots may learn from each other around the world and boost their capabilities.Footnote 31 That is especially relevant when it concerns complex surgery that does not happen very often at a single hospital, or where the gene sequencing for vaccines is largely done by AIs.Footnote 32 In a pandemic, networked AIs learn from each other worldwide. But networked AIs also analyse stock markets and may increase correlation of risk and decrease diversification, thereby contributing to the worsening of a systemic event and financial crises.Footnote 33 Networked AIs are also able to collude with each other and to perform cartel strategies that have not been seen yet; one only has to think about sophisticated price discrimination strategies of flight or hotel booking systems. Networked AIs open the door to a new world of possibilities in all aspects of life, as health, business, education, sustainability, or policing for better or for worse. The most important feature of AI networks is that they take decisions without human interference. This implies that there is basically no human who could be made accountable and to whom a decision could be traced back. A poignant example for the doctrinal problems which emerge is algorithmic collusion.Footnote 34 Think, for example, of flight booking systems which learn from each other how to coordinate price discriminatory tactics. Those systems can coordinate with each other, using collusive tactics better than any human could do, because the documentation of quantities, qualities and prices is automatically in the big data. Also, keeping cartel stability is less of a problem for AIs, because relational trust is not a valid category for a machine. The networked AIs simply keep their collusive tactics as learned by their algorithms. As such, consumers and the public may suffer considerable damages from networked AIs. Hence, public authorities will certainly stop those activities when they detect them, possibly by simply pulling the plug. That means the public attaches a consequence to a behaviour that is not in the public interest and regarded as illegitimate. For economic and ethical reasons, society does not allow algorithmic collusion. The problem with networked AI is, however, that traditional legal doctrine has major difficulties in solving the rising challenges within a consistent system of legal reasoning. This not only has to do with the lack of human responsibility in AI networks, but also with the lack of human moral judgement that could be addressed by legal norms. In other words, legal doctrine gets into problems, because there is no human to which its routines could be addressed. This becomes clear when one looks specifically at the case of algorithmic collusion. Collusion through networked AIs has the evident effect of an anticompetitive agreement. But an agreement needs at least the quality of a meeting of minds, the will of someone to make an offer to collude or to follow an offer. This implies that there is a sort of communication and intent about any sort of agreement. This carries even more weight if a legal order attaches criminal sanctions to collusive tactics and charges it with moral sentiment. Therefore, it is implicitly assumed that there is a human who is responsible and morally in charge of the collusion. Typically, this is the company and its management involved in collusion. But with networked AI there is no human which could be morally targeted, or which would be deterred by the threat of a criminal sanction. Also, the responsibility of a human for the actions of the AI cannot be easily demonstrated when there is no evidence for collusive intent and if there is no documentation and communication about it.Footnote 35 The AI remains a black box, although the call for ‘explainability’ is becoming louder. In the end, it is the lack of legal personhood that makes it impossible to integrate the case of networked AIs into the incumbent doctrinal conflict-resolution system. Incumbent legal doctrine foresees that there is at least some anchoring of decision making with humans. But networked AIs fail in this respect. There is no human in the loop that could be made accountable without overstretching the incumbent law and running into doctrinal inconsistencies. Therefore, it is reasonable to conceive networked AIs and their actions as separate legal entities that create specific risks, for which they are accountable. Those risk pools are identifiable and can be regulated as well as be obliged to pay compensation. The incumbent legal system is not fully equipped to close the accountability gap that can emerge by the three identified risks of AI. While some attempts have been successful, a general framework that would cover all possible instances is yet to be found. It is in this context that many scholars start discussing possible alternatives. However, this is not an entirely novel problem in legal history. There have been other instances where law had to address lacunae in accountability. One such historical occurence is the emergence of slave-run business models in ancient Rome. The expansion of social and economic activities through slaves let the praetors, the Roman magistrates with responsibility for litigation, introduce new legal remedies – the actiones adiecticiae qualitatis. This ‘legal invention’ allowed the establishment of a sort of indirect agency for entities which did not have legal personality and were thus subject to others’ legal authority (alieni iuris). The paper will turn now to this legal invention of the praetors and relate it to today's legal problems of conceiving AIs as legal entities.
2. Mind the gap: how Romans closed the accountability gap (a) The slaves-AI analogy The literature on AI has occasionally looked at how ancient Romans dealt with the accountability gap problem created by assigning business activities to slaves.Footnote 36 In both AI and slave-run businesses, the underlying problem can become that of (indirect) agency. Just as the user or operator of AI cannot fully predict or control how the AI will behave and decide, so the master did not know how his slave would behave. Of course, the slave was a human, unlike AI. This implies that slaves had potentially full freedom and autonomy in carrying out any (business) activity – something that is presently beyond the abilities of AI entities. However, what is remarkably interesting for the present contribution is how Roman law dealt with a scenario where the slave, who was not granted legal personality, could take autonomous decisions which have an effect on the master. In other words, slave-run business in Roman times concerned a situation in which there was a sort of agency under structural uncertainty given that a micro-management of the slave by the master was either impossible or not reasonable. Hence, that the slave is a human may play a role in the detailing of the incentives of the governance system, but it is less relevant for solving the structural problem of agency under uncertainty. It is in fact on this latter aspect that the present contribution, adopting a future-oriented outlook, focuses its attention. The agency problem between master and slave emerged after the second century BC, when ancient Rome was in the early days of becoming a hegemonial power in the Mediterranean Sea. The military success led to a sharp increase in the number of slaves. The traditional familia expanded, containing a relatively high number of slaves. Relatedly, the pater familias tended to delegate business activities to his slaves (and/or other persons-in-power such as filii).Footnote 37 Hence, the number of slaves who acted as the managers of the family business and were supposed to carry out transactions and negotiate binding contracts on behalf of their masters, increased considerably.Footnote 38 This shift in the ancient management practice created a new problem for the Roman regulatory framework: how to deal with the accountability gap problem? According to the ius civile in force at that time, masters did not have to answer for their slaves’ business activities vis-à-vis third parties, ie suppliers and customers. The guiding principle was ‘alteri stipulari nemo potest’: all obligations would only bind the parties which entered directly into an agreement, and not third parties – the so-called privity of contract.Footnote 39 This regulatory approach granted considerable protection to the pater familias, who could benefit from the slaves’ business activities without being accountable for their actions – the only exception being that the slaves would commit delicts rendering their master noxally liable.Footnote 40 On the other hand, third contracting parties were in a weak position since slaves, who did not have legal personality, could not be brought to courts and thus the contractors of slaves would end up with insufficient compensation even though slaves would be contractually liable. The situation as just described from the early days of Roman slavery seems to mirror today's situation in which employing AIs under the EU Product Liability Directive creates legal inconsistencies and produces economically wrong incentives to employ AI.Footnote 41 Therefore, it is no wonder that the EU, being confronted with this problem, has initiated a debate about an adaptation to the Product Liability Directive and a more coherent integration of AI into private law. In ancient Rome, the accountability gap led to the risk allocation between the parties directly and indirectly involved being so asymmetric, and the incentives for getting efficient contractual outcomes so low, that the incumbent regulatory framework could hardly be a long-term sustainable solution. Contracting third parties were simply reluctant to do business with other masters’ slaves, given that there was no legal certainty that a master would honour the terms of the contract.Footnote 42 Hence, a legal change in the regulatory framework was necessary. The so-called actiones adiecticiae qualitatis were progressively introduced.Footnote 43 These were a set of remedies granted by the praetor to contracting third parties to seek legal protection against the master of a slave with whom they carried out business transactions. One may understand this as a sort of ‘piercing the corporate veil’ from the slave to the legal entity of the master. The aim of these legal remedies was to ensure some additional responsibility for the master and, indirectly, to give some sort of incentive to oversee what the slaves were doing.Footnote 44 When looking at the Roman regulatory framework, however, the part that attracts most attention from scholars is the creation of a sort of corporate limited liability through the peculium and its associated actio de peculio.Footnote 45 The peculium was a fictitiously separate asset from the property owned by the master (res domini). Within the financial parameters of the peculium, the slave independently administered his business transactions. In other words, the slaves got a maximum capital that vouched for their transactions. Based on this historical experience, Pagallo considered the creation of a digital peculium for AI applications.Footnote 46 Whether this already includes the necessity of creating legal personhood for AI in a strict sense is a doctrinal question that need not be answered here. Making a tangent between the peculium and the liability of AI is a fascinating proposal. But one must acknowledge that the establishment of a peculium and its associated actio de peculio represents only a part of the more composite regulatory landscape offered by Roman law. Other legal solutions came into play and complemented the actio de peculio. There were in fact six legal remedies (ie actiones adiecticiae qualitatis) available to Romans offered by the praetors. It is possible to distinguish these remedies based on whether they set an unlimited or limited liability for the master regarding the slave's business transactions vis-à-vis contracting third parties. As is further discussed below, one can conceive this as a direct consequence of the more differentiated legal needs of consumers and businesses in a growing society. The actio exercitoria, actio institoria, and actio quod iussu belong to the remedies granting an unlimited liability. The actio de peculio, actio de in rem verso, and actio tributoria are, conversely, those legal remedies that ensure the master's limited liability. The paper now turns to review these six legal remedies and uses the resulting accumulated knowledge to reflect on the contemporary discussions on AI. While some more specific points for today's legal issues are raised in the following subsection, the next main section adopts a more encompassing view. (b) The specific legal remedies in Roman law The actio exercitoria and the actio institoria were two similar remedies aimed at giving protection to contracting third parties which had business transactions with a slave who was either a maritime or commercial entrepreneur. The actio exercitoria was used whenever an exercitor (both the owner of the ship or the one who rented it)Footnote 47 entrusted the management of a ship to his slave so that the latter became shipmaster (magister navis) and could purchase equipment or goods.Footnote 48 Evidently, the actio exercitoria was a kind of insurance for the remote contractors of slaves to trust in the cooperation of – even though the ship was hundreds of miles distant from – the master. On the other hand, the actio institoria referred to the institor,Footnote 49 who was the administrator of any commercial activity.Footnote 50 As Paulus defines it, ‘A manager is a person who is appointed to buy or sell in a shop or in some other place or even without any place being specified’.Footnote 51 Thus, the actio exercitoria and the actio institoria allowed contracting third parties to sue the master, who is called upon to fulfil the obligations undertaken by the slave.Footnote 52 In both legal remedies, the master's responsibility was only limited by the praepositio, which was an explicit authorisation by the master to his slave to perform (only) certain activities.Footnote 53 Hence, the master would incur unlimited liability only for the transactions falling under the scope of the activities mentioned in the praepositio. Transferring this idea to the employment of AI would mean making the owner of the AI accountable only for the tasks that the AI is supposed to perform within the activities that characterise the business of its owner. In other cases, the owner would not be held accountable and, at the most, the liability could be shifted to the producer or programmer of the AI. How the actual allocation of responsibilities across the value chain (eg producers, operator, owner) would look like in practice would depend on different factors such as the level of automation or the specific sector involved. However, Roman law shows that the potential of private law does not yet seem exhausted in the contemporary proposals for regulating AI. Moreover, it hints at the fact that legal solutions more tailored to the challenges arising from an accountability gap can be possible as prescribed by current scholarship.Footnote 54 The third (and last) legal remedy to set the master's unlimited liability was the actio quod iussu.Footnote 55 This legal remedy aimed to provide contracting third parties with legal protection for the business transaction(s) concluded with a slaveFootnote 56 who was delegated by the master (quod iussu) to fulfil that specific transaction(s).Footnote 57 In addition, this legal remedy could also be brought against the master who ratified what his slave did without authorising him beforehand.Footnote 58 The appointment by command (iussum) had more formal requirements compared to the praepositio: the former could only occur before witnesses, by letter, on oath, or through a messenger.Footnote 59 In this way, the extent of the activities encompassed by these two types of authorisation differed: while the iussum could be limited to a specific act, the praepositio embraced several activities. This distinction led literature to argue that the recourse to legal remedies varied depending on the specific context.Footnote 60 The actio exercitoria and the actio institoria were usually applicable in a context where the slave acted as a ‘manager’, whereas the actio quod iussu was usually used for slaves who performed a single order by the master.Footnote 61 The distinction between the praepositio and the iussum might appear at first glance only as a procedural clarification between a general and a specific rule. Instead, the main difference is the fact that each legal remedy confined the owner's liability to a specific function of the slave's autonomy.. Looking at it this way, it is possible to find again a parallel to recent debates. For example, in the EU there is an ongoing debate about whether to regulate AI according to a general standard, applicable to all industries indifferently, or according to sector and technological specificities of AIs which create certain risk levels.Footnote 62 Roman law makes us aware that the latter solution is possible. In other words, a regulatory framework can accommodate a series of remedies, each one confining liability to specific functions of AI's autonomous nature. That way, it would be possible to develop a sort of regulatory experimentation, whereby different AI entities may be subject to different liability schemes so that rules for AI would better align the needs of business with society.Footnote 63 In its proposed regulatory framework for AI, the EU foresees, at least, the so-called regulatory sandboxes that will allow regulatory opt-outs for certain AI applications for a certain time. As previously mentioned, Roman law not only foresaw cases in which the master would become unlimitedly liable. Other remedies allowed for a limited liability of the master. Here, the peculium played a decisive role, because it was the only source from which contracting parties could satisfy their credit vis-à-vis the slave. The most prominent legal remedy was the actio de peculio, which allowed a party to receive legal protection for the business transactions contracted with the slave (or any another person in power).Footnote 64 The master would guarantee the contract within the limits of the peculium originally granted to the slave.Footnote 65 According to Roman law, the grant of free administration of the peculium (concessio liberae administrationis)Footnote 66 was equal to a general authorisation for the slave to do business within the parameters of the peculium. This legal design strongly supported the entrepreneurial activities of the slave and reduced the need for those activities to be monitored by the master. Because advanced AIs will become more entrepreneurial in the future and may conclude contracts that have not been foreseen, the legal design of the peculium may become an interesting starting point for a better integration of AI into private law.Footnote 67 Regulations which only suppress entrepreneurial activities of AI clearly lead to economic disadvantages by foreclosing many welfare-increasing opportunities. Therefore, identifying AIs as legal entities with a specified autonomy up to a certain amount of liability specified beforehand is a sensible proposal. This would not exclude the possibility of accompanying liability insurances coming into play to compensate extra-contractual damages. Another remedy offered by Roman law to protect contracting parties was the actio de in rem verso.Footnote 68 This remedy was applicable whenever the benefits arising from a contract concluded by the slave were to be incorporated in the master's assets.Footnote 69 In other words, a master who enjoys the benefits of the slave's transaction implicitly has the obligation vis-à-vis the third party.Footnote 70 Because of this reciprocity, some scholars posit that the actio de in rem verso was usually applicable in those contexts where slaves were not business managers ‘by profession’.Footnote 71 In those cases, contracting third parties would be more likely refer to the actio de peculio. In addition, it is also noteworthy that the main distinction of the actio de in rem verso from the actio quod iussu is that the former was applicable whenever the slave performed a business transaction that was useful to the master, but without his actual knowledge.Footnote 72 The actio de in rem verso can trigger complex liability cascades and therefore plays only a niche role in today's civil laws. However, it gives an interesting perspective for the regulation of the association risk, when a human co-works with an AI. Then, the AI typically works for the financial interest of its master. At the same time the collaboration might be so close and intertwined that it is not possible to decipher whether the AI or the human is accountable for a certain action. In those cases, the actio de in rem verso gives a clear hint to make the master of the AI contractually liable if she enjoyed the benefits of the commercial collaboration. In turn, the master may seek financial relief herself from the producer or programmer of the AI. But in any case, an injured third party could demand compensation from the owner of the AI, if the latter enjoyed benefits from the human-AI association, even in cases in which it is not possible to identify who caused the breach of obligations. A similar approach could be advanced in the case of network risks: if the owners of an AI enjoy the benefits from a network of AIs, they will be obliged to compensate victims. This way, the owners of an AI get a strong incentive to oversee the behaviour of AIs in forming algorithmic collusions. Finally, the last remedy offered by the praetor was the actio tributoria.Footnote 73 With this legal remedy, it was possible to ensure a par condicio creditorum between contracting third parties and the slave's master over the assets belonging to the peculium.Footnote 74 In fact, the contracting third parties’ receivables were traditionally paid only after deducting those of the master.Footnote 75 That way it was possible that the master could allow the slave (or another person in power)Footnote 76 to continue several business transactions in parallel without worrying about repaying all the receivables even within the peculium. As a result, there was the chance that the master would be over-indebted and would default when liquidity was lacking. Therefore, the introduction of the actio tributoria aimed to prevent this behaviour by the master. The master, being aware of the various debts incurred from his slave, would become liable and be treated on the same footing as contractual third parties in the distribution of the stock of the peculium (merx peculiaris).Footnote 77 As Albanese points out, Roman law could have considered the knowledge and the approval of the master to make a transaction with the merx peculiaris in the same mould as a praepositio.Footnote 78 However, one must note that there is a strand of scholarship which is dismissive of whether this remedy actually belongs to the actiones adiecticiae qualitatis.Footnote 79 From the actio tributoria we can learn something for today's AI regulation, too. The owner of an AI may be negligent in the sense that she lets an AI perform too many and/or too risky business transactions (eg financial risks), whereby her gains would be secured while the whole pool of third parties would not be. An example is civil law liability in the case of algorithmic collusion between two or more AIs when single AIs may not only perform the primary task, but also interact with each other to gain further benefits by coordinating their actions. Today, it is not self-evident that a doctrinal link can be made between the collusion of AIs and the owners of the AI.Footnote 80 Within the logic of the actio tributoria, the masters of all colluding AIs would be identified, because of the benefits from collusion. A financial pool is created from which the creditors are compensated according to the quotas decided by court. In this way Roman law may give a fresh idea of how to deal with the network risk of AI.
3. Back to the future – legal differentiation and the timing of legal innovation In Section 2 a link was made between how Roman law regulated the relation between a master, a slave and a third party in contract law, and what we can learn from that for today's challenges of AI regulation. Central for Roman law is the master's consent in the transactions of the slave. Hence, legal protection for third contracting parties is based on either a master's explicit authorisation (praepositio and iussum) or the establishment of a peculium. The peculium can be considered as an implicit authorisation for the slave to perform autonomous business transactions for the master. Moreover, the master's type of authorisation played a prominent role for the kind of liability masters had to incur. For example, Miceli claims that the unlimited liability was based on the existence of an explicit authorisation due to the stable and continued cooperation between master and slave.Footnote 81 The lack of an explicit authorisation, instead, could have been the reason why the master should only have limited liability for the slaves’ transaction activities.Footnote 82 Roman law foresaw context-specific ways of closing the accountability gap between masters and slaves, depending on the kind of business, the frequency of business and the experience of the slave. And this is exactly what can be learned for closing the accountability gap that can emerge between the owner of an AI, the AI and contractual third parties: the context specificity in which AIs do contracting and how this puts obligations on the master and third parties. Or, to put it differently, it is doubtful whether simple extensions of incumbent private law will be sufficient to fully lift the economic potential of AI. From the Roman law experience, one would expect a much more differentiated menu of legal options. However, legal differentiation is not the only lesson to be learned from Roman law. By delving into the academic controversy on the chronological order in which the legal remedies were introduced, it is in fact possible to infer other related observations that may also become relevant for today's AI problems. It has already been argued that the possibility of establishing a peculium and its associated actio de peculio can be interpreted as a proto-limited liability scheme. The peculium has therefore been applauded as the zenith of Roman law making. But this overlooks that the actiones adiecticiae qualitatis were in fact not granted altogether by the praetor, but were introduced consecutively over time as adaptions to the legal needs of Roman businessmen in a prospering society.Footnote 83 The legal development of the actiones adiecticiae qualitatis was a gradual process. According to the Institutiones of Gaius, the order of the actiones adiecticiae qualitatis was the following: actio quod iussu, actio exercitoria, actio institoria, actio de peculio and actio de in rem verso. The same order can also be found in the Digest reporting the praetorian edict, except that the actio quod iussu comes last (and not first). Hence, most Romanists believe that the legal remedies establishing the master's limited liability were the last to be introduced.Footnote 84 This conventional view can be further divided into two camps. In fact, some authors argue that the correct order was the one reported in the Institutiones.Footnote 85 A second strand of scholarship believes that it was the Digest which reported the accurate chronological order by which legal remedies emerged over time.Footnote 86 However, de Ligt suggests that the master's limited liability was only an intermediary stage, before Roman law provided some legal remedies that established an unlimited liability to the master.Footnote 87 This is quite an interesting observation, because it takes into account that when Romans started having recourse to slaves for commercial transactions the masters’ activities were strictly separated legally from those of the slaves, and it seems unreasonable to assume that Roman law immediately established a system of unlimited liability for masters.Footnote 88 Accordingly, the praetors would devote more attention to the needs of the pater familias (ie master), while it was only later that attention was shifted to contracting third parties, making it necessary to get to a more elaborated liability regime.Footnote 89 This alternative interpretation is particularly relevant because it showcases that the accountability gap problem is not a mere technical problem but depends on what factor the legislator deems to be more relevant. If the praetor thinks in terms of pater familias, a limited liability scheme is the logical starting point. It would be unreasonable to believe that Roman law would immediately establish an unlimited liability for the pater familias. But if the praetor thinks instead in terms of the problems created through a lack of legal personality of slaves and the pursuant reluctance of third parties to contract, then an unlimited liability scheme would be the logical starting point for law making. The gist of this debate is the question of how the risks among the various parties involved in slaves’ business activities should be allocated and which incentives this allocation of risks sets for doing business. Adopting the conventional view means that a limited liability system was introduced only relatively late in Roman history, when the praetor had realised that business activities were inhibited by quasi-unlimited liability.Footnote 90 Adopting de Ligt's alternative view means, on the other hand, that the limited liability scheme granted by the actiones adiecticiae qualitatis was introduced relatively early in Roman law as an attempt to balance the master's interests with the opposing interests of third parties.Footnote 91 And it was only later that unlimited liability was permitted when the master gave explicit authorisations to slaves with professional business experiences (ie iussum and praescriptio). The lack of sufficient evidence to corroborate one interpretation rather than another makes this interpretative exercise, to a certain extent, speculative. However, regardless of which interpretation is historically correct, the controversy shows two important aspects which seem valuable for today's legal assessment of AI. First, ancient Romans did not have resort to only one legal solution to address the accountability gap problem. Rather, they offered a series of different regulatory solutions depending on the contextual needs that emerged at a specific point in time. The legal remedies adopted at a later stage did not change the incumbent legal system but complemented it. Secondly, the accountability gap problem, together with the pursuit of different societal goals, is essentially a matter of allocating risks among different stakeholders and choosing a starting point for legal development. If the regulator prefers the master's view, then a limited liability system will be preferred as a starting point. The master can ‘experiment’ with new business models and technologies and learn how to deal with completely new and uncertain situations, without fearing immediate bankruptcy. Instead, if the regulator adopts the third parties’ view, then the legal evolution would start out from unlimited towards limited liability. In this scenario, society would appreciate the legitimate interests of third parties over the business interests of the master. Only when the need to innovate and to boost business activities becomes stronger over time, will there be a shift to a limited liability system. These two observations have concrete policy implications if contextualised to AI. For example, they suggest that fitting AIs with limited liability and thereby facilitating entrepreneurial ventures, while inhibiting more balanced and complex transactions, is not as fantastic as one may think at first glance. The more sophisticated liability regimes might be saved for the future when AIs have many more faculties and have become more established in society. Moreover, it suggests that initially opting for a certain regulatory scheme would not necessarily foreclose other possible legal solutions, especially when certain needs materialise at a later stage and create a demand for change. Hence, a more heterogenous legal framework, in which stakeholders can have recourse to multiple legal solutions and choose the one that comes closest to their interests, seems a more sensible solution due to the inherently dynamic nature of AI technology. This more open approach makes it possible that the most effective legal solution will emerge over time and that not just one specific route of legal development will become enshrined in stone.Footnote 92
| 2024-03-14T00:00:00 |
2024/03/14
|
https://www.cambridge.org/core/journals/legal-studies/article/bridging-the-accountability-gap-of-artificial-intelligence-what-can-be-learned-from-roman-law/8B2B88D50E0A795F358C2F53958BDB43
|
[
{
"date": "2023/01/01",
"position": 83,
"query": "AI economic disruption"
}
] |
Designing Trustworthy AI in Higher Education
|
Designing Trustworthy AI in Higher Education
|
https://www.intechopen.com
|
[
"Sandra Rebholz",
"Paul Libbrecht",
"Wolfgang Müller",
"Written By"
] |
The assessment covers the five key dimensions: People and planet, economic context, data and input, AI model, task and output. ... Would the disruption of the ...
|
Applying Artificial Intelligence-(AI)-based systems and tools in the context of higher education imposes many challenges with respect to data privacy and ethics. For example, the EU AI Act that was adopted in March 2024 classifies many AI systems used in education as high-risk AI systems. High-risk AI systems must follow a strict set of requirements in order to be used in practice. Beyond the legal obligations, the trustworthy use of AI systems is not yet widespread. There are already approaches for assessing the trustworthiness of AI systems that shall ensure that such systems comply with existing guidelines for ethical AI. In this chapter, we review available design approaches for building trustworthy AI systems and evaluate their applicability in the context of higher education. In the real-life use case of developing an AI-based analysis system for e-portfolios from students in introductory computing courses at university, the existing design approaches are further detailed and adapted to the specific context of higher education. Furthermore, we assess the trustworthiness of the developed AI-based analysis system using the OECD Framework for the Classification of AI systems. Based on the findings, we conclude and recommend a scenario-based design process that helps build trustworthy AI-based systems in higher education.
1. Introduction Publicly available AI tools are rapidly emerging and finding immediate application in the educational field. This is especially true for Generative AI (GenAI) and corresponding technologies, but there is also an increasing number of initiatives in which independent AI developments are being developed for dedicated use in teaching as well as to support learners and teachers in learning processes. An example of such targeted development, which also motivates and underpins the analysis presented here, is the design and development of AI-based methodologies and tools to support teachers in the assessment of and the formulation of feedback on e-portfolios created by students as academic achievement [1]. Such an application has the potential to ease the assessment and the comparative evaluation of e-portfolios, which is typically time-consuming and elaborate due to the individual character of students’ e-portfolios. However, AI-based assessment of coverage of required topics, depth of treatment of individual topics, and reflective linking of different subject areas also require trust in summarized assessments generated by AI and justifications for corresponding evaluations and reasoning. This concrete example illustrates that AI-based systems may offer much potential in the field of education but also raises questions and poses challenges related to the risks of AI and specifically to the aspect of trust that needs to be addressed. The objective of developing AI-based systems needs to be to develop systems that realize the potential benefits but at the same time make sure that the systems can also be trusted. According to the EU strategy of following a human-centric approach to developing AI systems, trust is the prerequisite for this approach. Based on the use case of supporting the assessment of e-portfolios by AI-based methods and tools as illustrated above, our work presents an in-depth analysis of how to design trustworthy AI-based systems in higher education. Specifically, the following research questions will be addressed: What are the requirements and best practices for building trust with relevant stakeholders involved in the AI-supported analysis of complex learning artifacts such as e-portfolios? How can trust be deliberately integrated into the design and development process of such an AI-based analysis system? In order to answer these questions, we proceed as follows. After an outline of the theoretical foundations of trust in general and trustworthiness in the context of AI-based systems, we present a detailed analysis of the specific challenges of applying AI in education. Subsequently, we review existing approaches for building trustworthy AI systems that implement the Trustworthiness-by-Design paradigm. Based on the real-life use case of developing an AI-based system for analyzing e-portfolios from students at university, we adapt and refine these approaches for the context of higher education. The derived scenario-based design and development process is described in detail, as well as the evaluation of the developed e-portfolio analysis system using the OECD assessment framework for trustworthy AI. Finally, the resulting findings are critically discussed, and the identified benefits and potential challenges of the proposed scenario-based approach are highlighted.
2. Trustworthiness of AI-based systems In a general sense, trust is the belief “that a person (the trustee) will act in the best interests of another (the truster) in a given situation, even when controls are unavailable and it may not be in the trustee’s best interests to do so.” ([2], p. 19). According to a study conducted by Slade et al. [3], the most important element of trust is reliability and consistency of the trustee, followed by beneficence and transparency. Trust with respect to the use of a product or system can be defined as the “degree to which a user or other stakeholder has confidence that a product or system will behave as intended” ([4], section 3.41). Drawing on this definition, trustworthiness is the “ability to meet stakeholders’ expectations in a verifiable way” ([4], section 3.42). Consequently, it depends on the context and type of system in order to determine the characteristics that are expected from a system and how to verify them. In the context of AI-based systems, a variety of principles and requirements underlying trustworthy systems have been identified (e.g., see Refs. [5, 6]). Trustworthy AI-based systems comprise three components: they are lawful, ethical, and robust [5]. Based on these components, the higher-level expert group on AI (AI HLEG) of the European Commission defined a set of requirements that need to be fulfilled by a system in order to be considered trustworthy. These requirements include human agency and oversight, technical robustness and safety, privacy and data governance, transparency, diversity, non-discrimination and fairness, societal and environmental well-being, and accountability [5]. Similar principles can be found in the Recommendation on the Ethics of Artificial Intelligence adopted by the UNESCO in November 2021 [6]. Here, the need for creating awareness and literacy among the public is explicitly stated, and also the aspect of multi-stakeholders in AI governance is included in the principles. In order to evaluate whether a given AI-based system adheres to the requirements of trustworthy AI, a standard set of criteria needs to be established and assessed for a given system. The assessment list by the AI HLEG, for instance, formulates questions for all aspects relevant to trustworthy AI [7]. The list is intended to be used as a self-assessment list for evaluating the trustworthiness of an AI system’s design, development, and usage. It is important to note that not only the final system is assessed, but also the design and development process to build the AI system. Applying the assessment list in a certain domain also requires to adapt or add elements to the list to make it fit the specific requirements of the application context. As an early pioneer in the field, the OECD AI group embraced the task of qualifying artificial intelligence systems so as to make them scrutinizable by policymakers. The working group defined in 2019 the AI principles that define the first policy directions needed to create a trustworthy AI (e.g., shaping and enabling interoperable governance and policy environment for AI (Principle 2.3): Governments should create a policy environment that will open the way to the deployment of trustworthy AI systems) . The OECD framework for the classification of AI systems [8] presents a series of assessment questions, each of which contributes to the principles in a documented manner. This set of mostly qualitative questions gives hints of how the principles are approached. Going beyond the OECD framework, the NIST AI risk management framework [9] describes a process with more concrete steps to manage the risks so as to adhere to the principles and thus “guarantee” trustworthiness. The approach is even more operational with concrete indications of metrics, risks, playbooks, and processes. The need for trusting artificial intelligence has grown explosively, with multiple other initiatives offering approaches to evaluate (e.g., the z-inspection1) or to certify (e.g., the 1EdTech’s TrustEd apps program2). With the goal of supporting the development of trustworthy AI, the European Union adopted in May 2024 the Artificial Intelligence Act (AI Act [10]), which is the first legal framework for regulating the use of AI-based systems. The framework takes a risk-based approach and applies the classification of the OECD summarizing an AI system into four levels of risk. On the top level, systems that pose a clear threat to people and businesses are categorized as systems with unacceptable risks. The development and use of such systems are forbidden. On the next level, systems are categorized as high-risk systems. They fall under the provisions of the AI Act and have to comply with strict requirements for developing, deploying, and using them. Examples of high-risk AI systems include AI-based exam scoring systems, robot-assisted surgery systems, and AI-based credit scoring systems among others. Limited-risk systems are grouped on the third level and have to adhere to certain transparency regulations. Minimal risk systems can be used without any limitations. Despite the many guidelines, recommendations, and regulations, trustworthy AI is not the same as trusted AI [11]. Recent investigations have shown that applying up-to-date guidelines and metrics for trustworthiness does not lead to an increase in actual trust in AI systems. The authors argue that public attitudes are largely built upon the perceived trustworthiness of an AI application, which in turn is influenced by typical constructs of technology acceptance such as perceived ease of use and perceived usefulness, as well as the attitude toward AI in general.
3. Challenges of applying AI in education From the very beginning developments in Artificial Intelligence depicted links to the field of education, and research and developments in AI were transferred to the field of education and stimulated new research approaches in the field of education [12]. Consequently, there is a long history of applications of AI technologies in education, and AI has been linked to numerous potentials and benefits in education (e.g., see Refs. [13, 14, 15]). Educators tend to quickly adapt all types of new technologies to enrich teaching and learning, and also ones not specifically targeted to the field of education. This also applies to novel AI-related technologies. Against this background, it is not surprising that approaches to describing and classifying forms and scenarios for the use of AI in education have to be incomplete and limited. Typical approaches to classify the use of AI in education (AIED) distinguish between (a) student-focused AIED, teacher-focused AIED, and institution-focused AIED [15, 16]. Scenarios and corresponding technological approaches in the context of student-focused AIED include, in particular, personalized learning and intelligent tutoring systems, while teacher-focused AIED scenarios are often related to automatic assessment of students’ learning and support in providing adequate feedback. A typical objective of institution-focused AIED is the identification of dropouts and students at risk. In addition, AI-related competencies and skills are considered an important aspect, both for students and teachers. On the students’ side, these are understood as a prerequisite for the effective and reflective use of generative AI (GenAI) technologies, while they are also considered a specific learning objective of AI-enhanced learning scenarios. Similarly, corresponding competencies are considered indispensable for teachers to effectively apply AI technologies in the classroom, but also for teaching fundamental skills and fostering competencies related to AI and AI technologies. Yet, in both cases, the characteristics and the extent of such competencies are still objects of scientific discussions. There is currently a consensus of opinion that such applications of AI technologies in the classroom and for learning and teaching also come with risks and challenges. This is based on general ethical concerns and requirements [16, 17]. The Beijing declaration [18] represents the first approach to list challenges and formulate policy recommendations specifically targeted to the field of AIED. Recently, challenges for the application of AI in education were raised in a number of publications, in some cases on a more general level and in others on a more detailed one, and closely related to specific AI technologies, such as generative AI (e.g., see Refs. [19, 20]). Many of the raised challenges may be related to the aspects of trustworthiness of AI technologies but also to trust in the use of humans [21]. Specific concerns may be related to aspects such as privacy and security, quality and effectiveness of AI tools, trust in presented results (e.g., with respect to possible algorithmic bias), and equity in access. For instance, in institution-focused AIED, targeted to identify possible dropouts and at-risk students, the corresponding AI system requires trust in the assessment of individual students, providing a sufficient degree of transparency on how the decision was made. At the same time, privacy must be respected.
4. Trustworthy AI by design Despite the availability of ethical guidelines for trustworthy AI, there seems to be a gap between defining general guidelines and actually putting them into practice [22]. As the guidelines need to be applied during the whole engineering process of AI-based systems and also when deploying and using them, the design and development process of AI-based systems needs special consideration. There are various approaches on how to design and develop trustworthy AI-based systems. In the following, we present approaches that take a holistic view on developing AI-based systems and that realize a Trustworthiness-By-Design paradigm. All outlined approaches target and include trustworthiness as a core element of the design and development process from the beginning. In a collection of 62 Responsible AI Patterns , the book [23] describes best practices in the form of solution templates for coping with the challenges associated with the design, the implementation, and the management of AI-based systems. The patterns are grouped into three categories related to product, processes, and governance considerations. Depending on the context of the application at hand, these patterns can be reused and adapted to the specific requirements of the respective domain. In order to establish a trustworthy and responsible AI development process, [23] identifies the potential issues that can arise in the individual stages of the software development process. For each issue, the authors propose a solution to specifically address and mitigate the identified problems and risks. As an example, in the requirements phase, it is essential to collect, elicit, and document requirements with respect to trustworthy AI. As a solution, so-called Responsible AI User Stories can be introduced as a new type of user story. Based on predefined templates and guiding questions, the user stories are defined and worked on as part of the product backlog in an agile project. Another example of how to integrate ethical considerations in the design process is the use of envisioning cards [24] in order to strengthen awareness and reflection on how AI systems may impact human values. Envisioning cards focus on four envisioning criteria namely stakeholder, time, value, and pervasiveness. Each card describes a specific concept related to these criteria and suggests design activities to initiate discussion and engagement with possible effects and implications of AI-based systems with respect to this concept. In addition to general best-practice guidelines, there are also company-specific approaches that are published and used in practice. Examples are the responsible AI practices recommended by Google [25], which emphasize a human-centric design approach and the importance of testing activities; the Guidelines for Human-AI Interaction [26] developed by Microsoft Research with a focus on user interface design of AI-based applications; and the IBM Design for AI [27], which explains the rationales and driving forces underlying the design of AI systems.
5. Use case: AI-based analysis of e-portfolios In the following, we present a real-life example of how AI-based technology and tools can be applied in higher education. The application performs an AI-based analysis of e-portfolios and shows how both teachers and students can benefit from using such tools in teaching and learning. E-portfolios are collections of digital artifacts that students create to document their individual learning. In the e-portfolio, they present individual project results, summarize learning content, and reflect on the learning process and goals they have achieved. E-portfolios are similar to online blogs that contain a variety of multimedia content and can be highly personal. In the context of higher education, e-portfolios are generally used as a competency-based learning tool but also as a means to perform holistic assessments of the learning process and learning outcomes. At the University of Education Weingarten, e-portfolios have been used in introductory courses in computer science and learning technologies for over 10 years. 5.1 Teaching and learning scenario based on e-portfolios A typical scenario on how to integrate e-portfolios in university courses is as follows. Students take part in the lecture and are encouraged to deepen the learning content independently. They choose their own focus topics and work on these independently. This includes researching relevant information as well as carrying out small projects to apply what they have learned in practice. Students document the entire learning process, rephrase the knowledge they have synthesized, and develop content in their personal e-portfolio. They can share their e-portfolios: It is up to the students to decide who they grant access to the e-portfolio. By doing so, they can receive feedback on the e-portfolio presented in the composition system from their fellow students or the teacher and use the feedback to improve the e-portfolio. At the end of the semester, students submit the completed e-portfolio. The composition system is, in the case of the University of Education Weingarten, the widely used Mahara platform3. Latest, at the end of the semester, the teachers assess the e-portfolio based on predefined criteria. The assessment is typically done based on rubrics [28]. In the rubrics, all relevant assessment criteria are listed along with a description of different performance level characteristics. Figure 1 shows an extract of an example of a rubric for e-portfolio evaluation. 5.2 AISOP: AI-supported observation of e-portfolios In the AISOP project, we have developed a web application that carries out an AI-based analysis of the e-portfolio contents. Every time the user accesses their e-portfolio in the composition system, they can request an automatic analysis and see the result of this analysis in the AISOP web application. The web application employs thematic classification and concept maps to allow for an interactive concept-based coverage analysis and navigation as depicted in Figure 2. It will also provide different perspectives on the e-portfolio contents based on linguistic characteristics such as text complexity, lexical variety, or coherence (see Ref. [29]). 5.3 Design and development process The AISOP web application has been designed and developed using the scenario-based design approach as proposed by Rosson and Carroll [30]. In the design process, various scenarios have been developed that illustrate the main usage scenarios for the analysis system from the perspective of the target users (see Ref. [31] for example scenarios). The resulting scenarios are the basis for system design and development and have been used to derive test scenarios for evaluating the application in a real-life context at the university. The evaluations yielded a number of experimental results as presented in Gantikow et al. [32]. The project giving birth to the AISOP system was created so as to offer a reproducible approach that can be summarized by the following steps to obtain a similar system in other teaching opportunities based on e-portfolios (the AISOP “recipe”): Formulate proposed scenarios of use that reflect the concrete teaching situation at hand. Make sure to consider all aspects that encourage a trusting use of the web application (e.g., inspired by the key questions in the assessment list by the AI HLEG [7]).
Have an e-portfolio composing system ready for the students, including the possibility of sharing with selected users.
Make sure the e-portfolio composing system can be interfaced with the AISOP web app (this may need to configure web services, authorize them, or write custom interfaces). This is the step where the users will express their authorizations and thus express their trust. Thus, a clear scenario is useful to envision the trust of the authorization.
Identify the courses where this is to be applied. Create concept maps for representing the knowledge domain of each course (e.g., using CmapTools 4 ). Scenarios of usage of the e-portfolios in the course of a term should be available.
Collect textual materials relevant to the course content, such as course slides or earlier e-portfolios, and make sure you are allowed to process them. This processing is necessary to generate training data for the natural language processing (NLP) pipeline incorporated in the e-portfolio analysis system. It is an internal process and can be made with protected content (copyrighted, personal data…).
Extract all the relevant text fragments within text files (e.g., using a clipboard tracker 5 ).
Perform the manual annotations of the topic classification of all the fragments (e.g., using Explosion AI’s Prodigy 6 ).
Train the text classifier and refine the training. This creates a classification model specialized to the course learning content (e.g., using Explosion AI’s Prodigy).
Install and configure the classification model as well as the concept map as a new course in the AISOP web application (see web application documentation 7 ).
Test the system implementation based on the proposed scenarios of use (see step 1). Assess whether the criteria for trustworthiness are met or whether the system needs to be optimized. All e-portfolios of the newly integrated course can now be analyzed and visualized in the web application by any user who has access to the e-portfolio composition system. The approach applies fairly generic tools (such as the topic classification) and manages a pool of data so as to train the classifiers, one of the cornerstones of the machine learning approach to developing artificial intelligence tools. As depicted in the recipe, the process starts by defining appropriate usage scenarios considering criteria for trustworthiness and ends with a practical evaluation of the solution based on the scenarios defined beforehand. If the evaluation results do not meet the defined criteria, a new development cycle will be initiated. This approach was elaborated and experimented with in the AISOP project. Among the experiments, we ran several rounds of marking supported by the AISOP tool so as to elucidate how the tool could support the teacher’s review process. Some of these experiments and their results are described in Gantikow et al. [32] and the papers cited therein. Another round of experiments is in preparation where the interpretation of the students of the colored topic maps and the induced navigation, which are a way to present the output of the text classification, is in focus. 5.4 OECD assessment of the AISOP AI service Before discussing the ethical and trust-building aspects of the AISOP approach, we first take the time to assess it as an artificial intelligence application according to OECD which “provides a structured way to assess AI systems’ potential to promote the development of human-centric, trustworthy AI” [8]. The complete assessment is in Appendix 1. The assessment covers the five key dimensions: People and planet, economic context, data and input, AI model, task and output. It qualifies the trustworthiness of the AI system embedded as a web application service. Being a system made for supporting the learning, the usage of the AISOP system carries core dimensions that can be reformulated as in Figure 3. The highlights of this assessment include the following observations: The service must be seen as a complete service, although the AI component (the topic recognition) is a modest part of the process: Indeed, multiple criteria, such as the optionality, the impact on critical processes (such as giving a mark), the agency of persons, or the personal nature of data, are only valid because of the way they are assessed as a service delivering a visualization. The transparency of the AI results cannot be offered. This lies in the relatively hidden neuronal network nature of the spaCy models but also in the probably homogeneous nature of the texts used for training the classifier. While transparency could become better defined in the scientific literature, there appears to be no pressing need to offer users a more transparent classification, instead, the paper [32] presents a study about the usability of the interactive concept map and highlights that better integrations could be closer to support the students’ in their use. Rights handling with training corpora for learning relevant material is a multifaceted process. While a university could be handling only its internal data, it is difficult for newcomers to embark, and the reuse of existing corpora is important. For this reason, reusable corpora (e.g., from course contents and from existing e-portfolios) are desirable. Repositories such as Germany’s research data repository in education,8 which allows access to limited researchers’ circles, can offer a solution. The highly personal nature of e-portfolios makes it so that, even if anonymized, a student would recognize their e-portfolio immediately. Thus, sharing in a completely open form is rare and needs explicit permission. However, there is no risk in terms of possible divulgation of training content in the AISOP case (contrary to the case of generative AI systems). Finally, it is important to acknowledge that the AISOP recipe involves course-specific data and thus a course-specific classification system. This implies that each application of the recipe operates for its restricted focus. We claim that, beyond the cold-start problem mentioned above, this allows every institution to carry responsibility for the relevance of the AI service, which is a fundamental value of a course and the services around it. The assessment of the OECD has given us the opportunity to ask ourselves how the software’s artificial intelligence dimensions (such as the flow of data and the personal data protection aspects) are being monitored. Based on this assessment, one can easily answer the European Union’s AI Act’s classification of the service [10]. This leads us to evaluate the AISOP web application as a limited-risk system for which there may be registration requirements.
6. Making a trustworthy process The proposed recipe to create an artificial intelligence is rather following common steps: It involves the reuse of software, the reuse of datasets (NLP corpora), the enrichment with context-specific data, and the interfacing so that students submit their own data and obtain, thus, a service powered by artificial intelligence. It can be seen as a typical system without employing large artificial intelligence models of which only a few exist on earth and for which the privacy terms are rarely respectful. The process can be assessed as trustworthy and respectful of the AI goals of the OECD. That means showing what data is stored, where it is transmitted, and how it is being analyzed. We claim that the AISOP experience has proven that the use of scenarios makes it clear how a user perceives how their data is exchanged and processed. This is a very important lever to attract trust and is somewhat independent of the assessment of the governance of data and algorithms. However, both are of fundamental importance to be able to offer a trustable service. As shown in the OECD assessment, it appears just as fundamental to give users freedom of choice as it is to show how the data is exchanged in a transparent and comprehensible manner. While some of the AISOP experiments have shown very little concern about privacy on the part of the students, the respect for privacy can be the subject of a sudden breach of trust that would have a fatal impact on the use of a service. Thus, it appears fundamental to be able to express properly which data is transferred, how much, to whom, for which purpose, and to what extent the user is obliged to use the service. Due to the interplay of multiple systems, it is not uncommon for users to feel overwhelmed by the selection options and simply click on “ok” in an authorization dialog, without actually understanding what they are giving their consent to. But this may stop at any time (e.g., when the news arouses mistrust about a certain aspect, which generally provokes the entire rejection reaction), and only a careful explanation may convince them otherwise. We claim that assessing the trust in workflows through scenarios even before a finalized software is available is an appropriate method to ensure long-term trust and long-term evolution of the software.
7. Conclusion In this paper, we have attempted to define trustworthiness and trustability for artificial intelligence applications based on the definitions of the literature. The wide spectrum of contributions and recommendations that we could encounter have not yet provided methodologies that have proven themselves as applicable in practice for learning systems. We have described the design and development process that we followed to build an AI-based web application service of which one can assess the trustability. Through the use of scenarios, we have been able to highlight challenging points of trust and the presentation of what to expect of a system and thus make sure that they are clear to all stakeholders. In our process, we realized that some uses by students or teachers may have been missed by our scenarios. While it is good for a development to limit its scope, some scenarios are unavoidable as they are fundamental to building trust, and some are even an obligation by law. Examples include the scenarios to operate in case of a request to be forgotten (as is a fundamental right) or the reactions as a teacher against fears of using the service (teachers could explain the web application’s privacy guarantees better, but they could also adjust the configuration). Among the few discoveries that appeared is the establishment of principles of “who should be able to decide whether an AI system is used to analyze an e-portfolio?”: While it appears natural to leave this choice to the authors of the e-portfolios, this is not what is done in practice: Any person who is reviewing an e-portfolio is in a position to submit the content to an AI system. Expressing this possibility (or its prohibition) as a scenario is an excellent way to evaluate its desirability.
Acknowledgments This research was partially funded by the grant 16DHBKI015 (AISOP) of the German Federal Ministry of Research and Education. We wish to thank the collaborators of the AISOP team, including Thierry Declerck†, Alexander Gantikow, Andreas Isking, Pierre Günthner, and Simon Ostermann, as well as the many students who helped by lending their e-portfolios.
| 2025-02-27T00:00:00 |
2025/02/27
|
https://www.intechopen.com/online-first/1195342
|
[
{
"date": "2023/01/01",
"position": 91,
"query": "AI economic disruption"
}
] |
The collaborative role of blockchain, artificial intelligence ...
|
The collaborative role of blockchain, artificial intelligence, and industrial internet of things in digitalization of small and medium-size enterprises
|
https://www.nature.com
|
[
"Khan",
"Abdullah Ayub",
"Department Of Computer Science",
"Sindh Madressatul Islam University",
"Karachi",
"Information Technology",
"Benazir Bhutto Shaheed University Lyari",
"Laghari",
"Asif Ali",
"Software Collage"
] |
by AA Khan · 2023 · Cited by 180 — Some third parties are outside of the European Economic Area, with varying standards of data protection. ... Industry 4.0 disruption and its neologisms in major ...
|
The climate of global business and enterprises has changed the nature of development and related connectivity of SMEs. It is also because of the competitive fluctuates in the market and day-to-day challenges rising in the recent era, in which small and medium-sized businesses are performing only as receiving and adopting regulatory bodies. Manufacturing sectors contribute most of the ratio to economic development1. Whereas small and medium-sized enterprises, especially the production and manufacturing units, are on the developing agenda of various developed countries across the globe. While designing and creating units, one needs to consider the constraints of production and manufacturing development by size, scaling, and fund availability. In addition, owing to the amount, geographical reach, ability and capability of employees, and working intensity of entrepreneurs to drive their ideas to function. These are the main building blocks of SMEs that help in economic development2. According to the recent report on US economic cooperation and development (2021), all the connected stakeholders, including small companies countrywide and SMEs represent market fluctuations, which is more than 90% of overall enterprises3,4. However, SMEs generate half of the employment in the country and provide a turn ratio of more than 47% of the total increment of the business gross domestic product5. In a customer-driven environment, the production and manufacturing units are designed according to the procedures to respond back to mass customization using internet of things (IoT) technology, which provides a new pathway to value its customers.
Digitalization is a new paradigm that provides an opportunity to maintain SMEs in a better manner as compared to the traditional ones and transform them to allow more flexibility and agility. And so, SMEs' engines maintain the customer requirements by providing improved responsiveness accordingly. However, quality is a core component of customer-oriented infrastructure, being too upfront the transformation focus under the process of digitalization. The process hierarchy of creating SMEs is categorized as follows: (i) designing, (ii) planning, (iii) manufacturing, and (iv) performing functions or services.
While the quality of product, which is dispatched before to the customers of SMEs, is the fundamental objective to measure the favorable impact of production and manufacturing initially. Until there are no standard quality processes proposed, and no proper hierarchy currently being followed by the developers to design manufacturing units of SMEs that have evolved with the time and are converted to production. And so, these changes in the process hierarchy with developers maintain mass customization. The quality measurement has increasingly facilitated decisions based on the data collected in the dynamic time, from the marketplace and customer side. It is important to prioritize the processes that support SMEs' production and manufacturing and mitigate product development-related risks to design, plan, manufacture, develop, and perform functions within the defined resource constraints, such as less time and limited cost while fulfilling the customer requirement6. It is well noted, thus, to analyze the impact of digital manufacturing on quality measurement and to ensure that events of node transactions are functionally connected and synchronized at the same time.
Whereas the Internet of Things (IoT) and wireless sensor networks (WSN)-enabled SMEs' manufacturing process to change the traditional working operation of data gathering, examination, analysis, preservation, and present industrial and production records among the connected units7. It is possible to react directly and efficiently to customer-generated records with the use of the recent version of smaller batch sizes. Industrial IoT intends to corporate effectively with the processes of manufacturing SMEs, which is general to detect and recognize from the huge scale production. And so, because of industrial settings, where products are manufactured by indie with the help of a customer-specific approach. Mass customization is a concept that has drastically evolved in industrial production, need to design a cost-efficient method, which means the cost is equivalent to the mass products. A manufacturing unit based on the industrial IoT provides a modular architecture for replacing traditional systems8. It mainly focuses on the centralized server-based decision-making processes, and specific value-added evaluation is strictly limited in nature. However, SMEs and industrial IoT-enabled framework collaborates replace with versatile, reconfigure manufacturing and decentralized systems that provide effectiveness, responsiveness, strategic management, and building capability for decision making, as shown in Fig. 1 (using Draw.io for image generation).
Figure 1 The current process of SMEs with IoT for data management and decision making. Full size image
In addition, the advancement in digital technology, such as IoT technology with SMEs provides improve productivity and income, captures market shares, creates brand awareness, mass customization, real-time feedback that enhances organizational implementation and necessary changes, helps in decision making, and evaluates customers sentiments9. On the other side, these highlighted factors pose a significant limitation in the SMEs-related transformation and digitalization. For this reason, various enterprises are unwilling and unsatisfied with speed cost, time, and related resource constraints because it consumes high engineering and investment initially, and the output is not cost-effective and satisfactory. However, to manage and optimize manufacturing and production-related data or transactions of SMEs in a ledger, various artificial intelligence (AI)-enabled machine learning (ML) techniques (supervised, unsupervised, and semi-supervised) are proposed9. Substantially, to expand the scope and context of AI development by tuning the mentioned SMEs' operations and integrated market fluctuations. Most importantly, the collaboration of AI with social computing performs a crucial role to develop a strong digital marketing strategies for SMEs by employing post and share mechanisms to spread awareness related to new manufacturing, production, and industrial development. Whereas performance and productivity depend to a certain degree. Therefore, it counts as long-term benefits.
In the current scenario, the centralized server-based network infrastructure is used for SMEs transactions acquisition towards deliverance. It affects directly SMEs' ledger integrity and privacy because of weak security, which means information is tracked and accessed easily, especially tracing customers' personal records through the Internet. Distributed ledger technology has been adopted widely in various small and medium-sized enterprise environments to avoid tampering and forgery10,11,12,13. Thus, blockchain is recently enabling SMEs to secure their running systems and process hierarchy to realize integrity, transparency, traceability, provenance, trustworthiness, and access ledger via distributed application (DApp). The existing SMEs are integrated with the collaborative approach of AI-blockchain, help to secure the process hierarchy, maintain customer-orientation strategy, encrypt exchanging information between customers and ecosystem, protected distributed node-to-node transactions, platform interoperability, and storage immutability. Furthermore, the individual event of node transaction is being stored before proper verification and validation using chain codes (smart contracts). A chain-like structure along with chronological order is designed that connects participating stakeholders in a public permissionless network to initiate SMEs’ transactions and exchange. This helps to achieve privacy and security for SMEs, which is hard to tamper with or forge and preserve optimized records in a secure storage container with hash-encrypted form.
The main research contributions and objectives of this paper are discussed as follows:
This paper addresses the current process between customers and SMEs, such as manufacturing, production, and industrial units interconnective, including data gathering, management, and optimization. It is also analyzed that the implementation of digital technology with AI creates a new paradigm. Probably analysis of the impacts of SMEs on the countries’ economy highlights the benefits of adoption.
In this paper, we highlight comparative research results related to digitalization, SMEs, industrial IoT, AI, blockchain, and their transformation conducted in Asia over the past few years.
The outcome of the research in which a standard process hierarchy is derived, that led to managing customer relationships with SMEs at a secure, protected, and standard level. The proposed B-SMEs (a blockchain and AI-enabled distributed framework) provide a platform where the DApp is designed, created, and deployed for the sake of a transparent transactional environment. The main objectives are to handle SMEs-related automation, especially transaction verification and validation, exhaling, and sharing of resources among participants.
With the development of blockchain distributed public permissionless networks integrated with AI provide a lightweight authentication mechanism that reduces the cost of computational resources along with network bandwidth and storage.
There are three different chaincodes created and deployed for stakeholders’ registration, SME transactions and exchange updates, and information management and optimization of immutable storage. However, individual transactions are protected with the use of the NuCypher threshold re-encrypted throughout the deliverance. And so, the proof-of-work (PoW) and proof-of-stack (PoS) pre-defined ethereum consensus is adopted along with a digital signature to schedule, initiate, manage, and approve transactions and related information exchange among participating stakeholders.
At last, this paper highlights a few of the open challenges, limitations, and issues involved in the implementation and deployment of DApp BSMEs in real-time, which will consider as future developments for technological maturity.
The remainder of this research paper is structured as follows: In Section “Related work”, there is various IoT, blockchain, and AI-enabled techniques involved in an industrial environment, and SMEs for better production and manufacturing are discussed. The primary knowledge of blockchain, IoT, and AI-enabling technologies is presented, along with the problem formulations and problem descriptions in Section “Fundamental knowledge and preliminaries”. B-SME, blockchain, IoT, and AI-enabled distributed framework, is proposed for smart SMEs development and related processes in Section “Proposed framework”. However, Section “Future direction” discusses the open implementation issues, challenges, and limitations and highlights future research directions with possible solutions. Finally, we conclude this paper in Section “Conclusion”.
| 2023-01-01T00:00:00 |
https://www.nature.com/articles/s41598-023-28707-9
|
[
{
"date": "2023/01/01",
"position": 92,
"query": "AI economic disruption"
}
] |
|
Human Resources Analytics for Public Personnel ...
|
Human Resources Analytics for Public Personnel Management: Concepts, Cases, and Caveats
|
https://www.mdpi.com
|
[
"Cho",
"Choi",
"Wonhyuk Cho",
"Seeyoung Choi",
"Hemin Choi"
] |
by W Cho · 2023 · Cited by 102 — ... Workplace Policy. Public Personnel Management 51 ... Big Data and AI: A transformational shift for government: So, what next for research?
|
This article begins by examining the definitions, concepts, core components, and process of HR analytics through a thematic literature review. Then, we present cases of HR analytics adoption in real-world situations in order to identify the necessary conditions for implementation. The final section offers key considerations for the successful implementation of HR analytics in public organizations and discusses potential issues and future challenges.
Despite high expectations for HR analytics, recent findings suggest that organizations’ data analysis capabilities may not be sufficient ( Gurusinghe et al. 2021 Van den Heuvel and Bondarouk 2017 ). For example, in a survey of over 7000 HR professionals from 35 countries, 55% reported needing help with analytics implementation ( KIRD 2021 ). One reason for this gap in capacity may be that organizations are new to advanced HR analytics tools and are facing challenges such as poor data quality and difficulty in building a strong business case for implementation ( Llorens 2021 Minbaeva 2018 ). The public sector has lower levels of adoption of HR analytics compared to the private sector, according to a survey of over 400 government HR leaders, though public sector HR managers agree on the need to develop advanced analytics capabilities ( Boston Consulting Group 2016 ).
In HR analytics, there are several levels of analysis that organizations can progress through as they mature in their use of data and technology ( Margherita 2021 ). These include descriptive analysis, which illustrates the past or current problems; predictive analytics, which seeks to identify potential/future issues; and prescriptive analytics, which guides organizations towards the most effective course of action. While descriptive analysis involves summarizing the current state, predictive analysis uses techniques such as correlation analysis, regression modeling, and structural equation modeling to answer “what-if” questions ( King 2016 ). More advanced data-driven decision making may involve conducting experimental algorithm-based studies to understand how exactly human capital inputs impact organizational performance ( Fitz-Enz and John Mattox 2014 Gelbard et al. 2018 ). Many organizations are still in the process of transitioning from descriptive or predictive to prescriptive analytics, which represents the ultimate goal of fully leveraging data technology in HR ( Gelbard et al. 2018 Song and Kim 2020 ).
Common features of HR analytics include advanced technologies for data analysis, the use of various (big) data sources, and the support of strategic decision making. In the public sector, the use of HR analytics is often referred to as data-driven HRM or human governance analytics ( Sousa et al. 2022 ). Falletta and Combs 2021 ) proposed a definition of HR analytics based on a survey of practitioners from Fortune 1000 companies—this study identified common elements such as metrics, external benchmarks, decision making, value creation, advanced statistical analysis, and data visualization to emphasize that HR analytics is a “process” with interconnected steps ( Falletta and Combs 2021 ). Van den Heuvel and Bondarouk 2017 ) also characterized HR analytics as a process rather than a tool, arguing that the success of HR analytics practices depends on well-formulated research questions, a strong dataset, and effective analysis ( Van den Heuvel and Bondarouk 2017 ).
Scholarly definitions of HR analytics have varied ( Tursunbayeva et al. 2018 ), and the concept itself has gained multiple, somewhat interchangeable labels, such as people analytics, talent management analytics, human capital analytics, algorithm-based HR decision making, and workforce analytics ( Nocker and Sena 2019 Saputra et al. 2022 ). These different terms all refer to the use of data in HR, but may have different focuses depending on the area of application ( Giermindl et al. 2022 ). Electronic HRM (e-HRM) and HRIS (human resource information systems) also introduce related concepts as they highlight the strategic use of data in people-related decision making. In this study, we use the term “HR analytics” as it is the most commonly used term in recent literature in the field ( Margherita 2021 ).
3. Process of HR Analytics Implementation
Several procedural approaches to implementing HR analytics have been proposed by researchers. One such approach is outlined by Fink 2017 ), who suggests a seven-step process for creating value and aligning HR analytics with organizational goals: (1) asking the right question, (2) identifying the appropriate method to answer the question, (3) locating or generating necessary data, (4) effectively analyzing the data, (5) developing insights from the analysis, (6) taking action based on those insights, and (7) measuring the results to determine the effectiveness of the action. Song and Kim 2020 ) propose a six-stage process: (1) prioritizing goals, (2) establishing logic, (3) gathering data, (4) preprocessing data, (5) analyzing data, and (6) making decisions—this process emphasizes the importance of preprocessing data, including cleaning and standardizing data formats, as a separate step.
Other conceptualizations emphasize specific procedural elements of HR analytics. Deloitte Insights 2018 ) organized its six-step process around big data smart principles focused on intra-organizational consensus: agree on customer objectives, identify relevant data, design analysis framework, implement analytics, allocate resources, provide feedback and reflect insights into the business process. Margherita 2021 ) highlighted three drivers (input, process, and output) for HR analytics implementation—in this model, “input” refers to the availability of a vast amount of integrated HR data of various sources and types, “process” includes the adoption and development of advanced analytics technologies, and “output” features the design of value-added HR metrics and advanced visualization/reporting systems ( Margherita 2021 ). Klimoski et al. 2016 ) drew a clear, logical connection between the analysis target and the expected result—their LAMP (Logic, Analysis, Measure, and Process) framework consists of logic (the story that connects numbers and outcomes), analysis (drawing the right conclusion), measure (using the right numbers), and process (using data to influence decisions).
Figure 1 summarizes the five common elements of the HR analytics process as suggested by the literature. The first step (“Define”) is to define the problem and subject of analysis clearly. The second stage (“Collect”) is sourcing, collecting, and securing appropriate data. In the third stage (“Analyze”), the relevant analytical framework is implemented. The fourth step (“Share”) involves sharing the insights derived from the analysis results with members of the organization through storytelling. The final step (“Reflect”) is decision making and implementation based on the analysis results. As the ultimate goal of HR analytics is to support an organization’s strategic decision making, all steps should be accompanied by meaningful actions and genuine feedback.
In the “Define” stage of the HR analytics process in the public sector, it is important to clearly identify the problem and subject of analysis. This involves understanding the specific organizational issues that need to be addressed in the public sector, taking into account the unique nature of the government organizations. HR analytics should consider factors such as the goals of the public organization, the needs and expectations of citizens and other stakeholders, and the legal and regulatory environment in which the organization operates. They should also think about the expected results of the HR analytics process, including how the insights and recommendations generated through the process will be used to improve public personnel management and support the government’s overall mission.
In the “Collect” stage of HR analytics, the focus of data collection in HR analytics may differ between the public and private sectors due to the different priorities of these organizations. Public sector organizations are often driven by a mission to serve citizens and the broader community, and as a result, they may place a greater emphasis on data related to citizen needs and taxpayer satisfaction. In contrast, private sector organizations are typically more focused on maximizing profits and shareholder value, and as a result, they may place a greater emphasis on data related to financial performance, such as profit margin or return on investment. However, it is important to note that the specific focus of data collection will vary depending on the needs of each organization; therefore, it is crucial for HR analytics in the public sector to carefully consider the specific data needs of their organization and to work with relevant stakeholders to identify and collect the appropriate data. It is also important to ensure that the data are collected and stored in a secure and confidential manner, in compliance with any relevant privacy laws and regulations. Collection process should ensure that the data is available in a usable format, considering a variety of factors, including quality of data, systems or technologies used to collect and store the data, or a standardization in data collection processes.
In the “Analyze” stage of HR analytics, the relevant analytical framework is implemented by selecting the appropriate algorithm and designing the effective predictive tools to ensure accurate and meaningful analysis. HR analytics in the public sector should consider the specific goals and needs of their organization when selecting the algorithm and tools, ensuring that they are suitable for the type and volume of data being analyzed and capable of providing the desired level of detail and accuracy. HR analysts in the public sector may consider partnering with external vendors or developing in-house expertise through training and development programs ( Johnson et al. 2022 ). Public organizations must exercise caution and carefully evaluate the possibility of algorithmic biases and detrimental effects associated with the utilization of HR analytics during the analysis phase.
The “Share” stage of HR analytics in the public sector involves the communication of insights and recommendations derived from the analysis to internal management and external stakeholder. To do this, HR analytics should use clear and simple language and provide context and background information to help managers understand the significance of the insights. Data visualization and other tools, such as charts, graphs, and infographics, can be effective in illustrating the results and their implications for the organization in a visually appealing and easy-to-understand manner. It is important for HR analytics to tailor their storytelling approach to the specific needs and goals of the public organization and to consider the challenges and opportunities facing the organization, as well as the benefits and implications of the insights for different stakeholders.
The “Reflect” stage of HR analytics in the public sector involves using the insights and recommendations from the analysis to inform decision making and drive meaningful change within the government organization. HR analytics should identify specific actions that can be taken based on the insights generated by the analysis. This may involve implementing new policies or procedures, reorganizing HR departments or teams, or making changes to the way that HR services are delivered. It is important to develop and implement plans for monitoring and evaluating the effectiveness of the changes. It is also important to be proactive in seeking various feedback throughout the implementation process, and to be open to adapting and refining the plans based on this feedback. Predictive insights can be useful in the public sector, but they may need to be implemented through changes to laws and policies; therefore, it is important to secure stakeholder support especially when it requires legislation.
| 2023-02-14T00:00:00 |
2023/02/14
|
https://www.mdpi.com/2076-3387/13/2/41
|
[
{
"date": "2023/01/01",
"position": 67,
"query": "government AI workforce policy"
}
] |
How did you break into AI and Machine Learning?
|
The heart of the internet
|
https://www.reddit.com
|
[] |
I am a sophomore computer science major, and none of my coursework has covered anything to do with artificial intelligence or machine learning so far.
|
I am a sophomore computer science major, and none of my coursework has covered anything to do with artificial intelligence or machine learning so far. I don't know much about either topic, so I am hesitant to apply to internships related to them even though I think they would be interesting.
Did you follow specific video tutorials? Or read certain textbooks? I learn well from textbooks and could definitely go through one over winter break. I just feel like the topics are so broad that I don't know what I should do to feel like I have a solid grasp on the concepts and so I can be effective in internships related to those fields.
| 2023-01-01T00:00:00 |
https://www.reddit.com/r/csMajors/comments/102woa0/how_did_you_break_into_ai_and_machine_learning/
|
[
{
"date": "2023/01/01",
"position": 33,
"query": "generative AI jobs"
}
] |
|
Artificial Intelligence won't take our jobs yet, but things are ...
|
Artificial Intelligence won't take our jobs yet, but things are going to get weird
|
https://secondguess.substack.com
|
[
"Ama Udofa"
] |
While we can't know when AI will come for our jobs, most experts peg it between 2045 and the end of the century.
|
Welcome to this week’s edition of Second Guess. Did you know that January is the longest month of the year? That’s why I’m doing a countdown to salary day. Join the movement. We got 6 days left, people! #WAGMI
If you missed last week’s edition of this newsletter, catch up: I wrote about how the myth of multiple income streams (or how side-hustle culture is killing us).
And now, to today’s story…
In 2016, Microsoft launched an AI personality on Twitter named “Tay”. They wanted the bot to engage in online conversations with Twitter users as a fun, interactive demo of Microsoft’s natural language processing technology. The experiment turned out to be one of the most unforgettable tech fails ever.
Within hours, internet trolls had gotten Tay to tweet the most offensive messages you could think of, ranging from “Hitler was right” to “I hate feminists and they should all die and burn in hell.” It was a hot mess and Microsoft quicky shut Tay down.
Fast-forward to December 2022 when I watched MKBHD’s YouTube video on AI where he revealed he’d used ChatGPT to generate the script—including the argument against AI. I was astounded when he said it and started to ponder about the existential threat AI poses to my daily bread, how much the world has evolved to the point that my career as a creative would be at such risk of extinction.
But just two weeks ago, netizens exposed tech publication CNET for quietly publishing dozens of AI-generated feature articles. CNET admitted that it was true, but claimed they were just experimenting. Whether the statement was just PR bullshit is up for debate, but one thing is clear: despite all the hype and FOMO around AI, it’s far from ready to take over the world.
CNET’s “experiment” failed and—colour me shocked—proved artificial intelligence isn’t any better at journalism than humans. In fact, it’s actually worse. Earlier this week, The Washington Post reported that CNET started adding lengthy correction notices to some of its AI-generated articles after Futurism, another tech publication, called out the stories for containing some “very dumb errors.”
Other tech sites like Bankrate have also come out to admit that their AI-generated articles have been riddled with silly errors since November and they will be effecting corrections. Which brings me to my argument—TLDR: Despite the noise, AI is still not ready to take over our jobs.
Artificial intelligence has rapidly become more and more sophisticated over the last decade. We now use AI in our daily life to learn our preferences and serve us ads, suggest movies, recognise our faces and even complete our sentences in ways our lovers can’t dream of.
Dall-E and OpenAI’s Chat GPT took the world by storm in 2022 when these tools showed they could create entire complex pieces of art and content with simple prompts. So when news broke out that CNET had been using AI to generate entire stories, the anxiety around its threat to journalists’ jobs was understandable. Robots could finally generate copy without needing salaries or bathroom breaks. “W” for capitalism, right?
Lol. Let’s be calming down.
The problem AI is trying to solve is harder than we think
The fundamental blocker to AI taking over is the difference in specificity between how humans carry out instructions vs how AI does.
I came across an analogy by AI expert Stuart Russel where he explained to TED-Ed that asking a human to do something and giving the same thing as an objective to an artificial intelligence system.
When you ask a human to run an errand for you—say, order food delivery, the human understands it’s not their life’s mission, neither must they bring your food to you by all means. With AI algorithms, it’s exactly that; we must give them a fixed objective and account for every specific scenario for everything, else they’ll make it their life’s mission even if they break everything else.
If you asked an AI system to get you food from a restaurant and it arrived just as the restaurant was closing, it could kill everyone at the restaurant just to get you your amala because well, it made it its primary purpose to get your food to you per instructions. AI simply doesn’t have common sense or empathy or the ability to understand its surroundings.
According to Russel, if you asked AI to fix the acidification of the oceans, it could cause a catalytic reaction that deacidifies the oceans very quickly and efficiently but also consume a quarter of all the oxygen in the atmosphere, which would apparently cause all of us slow, unpleasant deaths.
In theory, saying, “Just be more careful about specifying the objective” is a simple enough fix but what about atmospheric oxygen? What about possible side effects of the reaction in the ocean that poisons all the fish? Then you tell AI not to kill the fish, which opens another probability: well, what about the seaweed? Then you say, “Don’t do anything that might kill the seaweed”, and on and on and on.
We don’t have to go through these processes with humans because humans have intuition. Humans’ ability to emphatise, ask questions, seek clarification and basically take initiative isn’t something we consider very sophisticated. We just know, but AI doesn’t. In 2023, AI will tell you wrong answers with confidence and wouldn’t give a fuck, because it can’t think for itself.
In Microsoft’s Tay situation mentioned earlier, the problem wasn’t that the bot was immoral; it was that she was well, amoral. She didn’t have any understanding of the conception of right or wrong, and her utterances were just the output of a mindless statistical analysis from training data with no ability to evaluate the ethical significance of her statements. Welp.
Even if an AI system were to work well enough 90% of the time but had instances of being deeply harmful or inaccurate the rest of the way, there’s “still a lot of homework left”, as Maximilian Gahntz tells Techcrunch, “before a company should make it widely available.”
The recently documented failures of generative AI (Dall-E and ChatGPT) attempting to create but were hindered by glaring problems further buttress the fact that AI is still a long way from taking over. And even on the business side, companies aren’t ready to roll out something that generates messed up stuff frequently because it’ll only drive their customers away.
The intellectual property problem
Alex Kantrowitz, the author of Big Technology, recently caught a Substack writer that used AI to “copy, remix, and publish” content stolen from his newsletter.
The Kantrowitz incident is particularly interesting seeing that most generative AI crawl through mountains of publicly available information to generate their content or art. What happens is that, in journalism and the creator economy, even the most authentic-looking stories are essentially cut-and-join jobs, which lack new findings or thoughtful creation. In essence, AI still can’t do research, ask questions, show empathy, apply common sense, or actually create new things, so no, it’s not taking over our jobs just yet.
I’m no programmer but I remember when Github released Copilot and the entire dev community on Twitter was overran with hysteria. Nobody has lost their jobs because of AI yet. In fact, Microsoft, GitHub and OpenAI are currently being sued in a class action lawsuit that accuses them of violating copyright law by letting Copilot regurgitate sections of licensed code without providing credit.
I’ll go out on a limb to argue that when AI art becomes more sophisticated, artists will reinvent themselves. Naturally created art will only become more valuable, just like how handmade products (e.g. shoes) are typically more valuable than mass-produced junk, but I digress.
TL/DR: The doomsday chants about AI are a little too premature.
But things are about to get weird
While AI isn’t yet ready to take over, it still represents an important existential threat. For a long time, creatives and creators were fine with automation reducing the need for human labour and rendering millions of manual jobs redundant. But now, automation is making giant strides on its way to disrupt highly creative work once thought to be outside its reach.
I’m also concerned that we’re becoming more and more dependent on machines. These AI models feed on data to learn about us and assist us. And now, we’re all too willing to hand our information over to machines as long as they make our lives easier. We must then ask ourselves: how much assistance is too much assistance? We might be inadvertently fast-tracking the process of AI dependence even though we keep expressing hysteria about it taking over.
Humans evolve by teaching younger generations—an unbroken chain that goes back thousands of generations. Right now, there is a real danger of losing the incentive to teach the next generation how to understand the machines powering the world they’re being born into. What happens when the chain is broken? Are we getting to the point of giving the keys to our civilisation to AI? I’s not our generation I’m worried about; it’s our children’s
We’re living in truly exciting times as AI is both fascinating and terrifying. While we can’t know when AI will come for our jobs, most experts peg it between 2045 and the end of the century.
Without a doubt, AI will continue to grow in leaps and bounds and will have to navigate ethical and practical concerns. But it’s still a long way away from replacing humans. Meantime, as artificial intelligence evolves, I’m cautiously optimistic that humans will evolve with it.
Thank you for reading Second Guess. This post is public so feel free to share it. Share
Have a lovely weekend and see you next Friday!
| 2023-01-01T00:00:00 |
https://secondguess.substack.com/p/artificial-intelligence-wont-take
|
[
{
"date": "2023/01/01",
"position": 38,
"query": "generative AI jobs"
}
] |
|
A Brief History of Generative AI - Matt White
|
A Brief History of Generative AI
|
https://matthewdwhite.medium.com
|
[
"Matt White"
] |
The jobs market will be heavily impacted as generative AI can not only augment or automate current creative functions of jobs but can be used to entirely ...
|
A Brief History of Generative AI Matt White 6 min read · Jan 7, 2023 -- 3 Listen Share
How did we get to where we are today in the field of generative AI?
DALL-E 2’s Classic Avocado Chair
Generative AI will be the most disruptive technological innovation since the advent of the personal computer and the inception of the Internet with the potential to create 10s of millions of new jobs, permanently alter the way we work, fuel the creator economy, and displace or augment 100s of millions of workers in roles from computer programmers to computer graphics artists, photographers, video editors, digital marketers and yes, even journalists. Even with all the hype around generative AI this year, it’s true power has not yet been seen or felt, in 2023 there will be significant innovations that will begin a revolution that will leave no industry or job function un-impacted in one way or another.
Generative AI research can trace its history back to the 1960s. However generative AI began to develop into something similar to its current form in 2006, with the first significant paper in the field, Geoffrey Hinton and his co-author’s “A Fast Learning Algorithm for Deep Belief Nets” which re-introduced Restricted Boltzmann Machines in the context of deep learning (he originally introduced the RBM concept in 1983.)
However few innovations took place in the field, until in 2014, with the introduction of GANs by Ian Goodfellow and his colleagues. Generative AI developments in research were made in the following years, most significantly the introduction of the transformer architecture for natural language processing applications, presented in the paper “Attention is all you Need” by Vaswani and colleagues from Google.
Although most people will admit that they were not aware of generative AI until 2022. This is when the technology was put into the hands of consumers with the release of several text-to-image model services like MidJourney, Dall-E 2, Imagen, and the open-source release of Stability AI’s Stable Diffusion. This was quickly followed up by OpenAI’s ChatGPT which mesmerized consumers with a version of GPT-3 re-trained on conversational dialog that seemingly had an answer for everything and delivered responses in a very human-like manner. At the same time VCs looking for the hot new technology to invest in caught the generative AI bug and both Stability AI and Jasper both became instant unicorns with Series A funding exceeding $100 million. GitHub’s Copilot also saw widespread adoption, a tool built on Open AI’s Codex which was trained on all public code repositories in Github and assists developers by converting natural language into executable software code.
However, there has been significant backlash against generative AI. Many concerns have been raised about possible copyright infringements for generative AI art, text, and code as well as the impact to creative jobs. A class action lawsuit brought against Microsoft for Copilot will set a valuable precedence in the courts for which other lawsuits may be filed as many developers contend their intellectual property has been stolen. Artists, authors, and developers want to have their work excluded from the wide-scale scraping performed to create viable datasets for the large language and image models and artists on ArtStation have revolted requesting that all AI-generated art be banned from the platform.
Image prompt generated image by Midjourney (prompter: @AFWTMT)
Generative AI has been an active area of research since the 1960s when Joseph Weizenbaum developed the first chatbot named ELIZA. It was one of the first examples of Natural Language Processing (NLP) and was designed to simulate conversations with a human user by generating responses based on the text it received. Although the system was a primitive rules-based implementation intended to synthesize a human conversation, it paved the way for further developments over the coming decades in the field of NLP.
Modern generative AI is built on deep learning, which can trace its beginnings back to the 1950s. Deep learning innovations were fairly quiet for decades then saw a resurgence in the 80s and 90s with the advent of artificial neural networks (ANNs) and backpropagation algorithms. By the 2000s and 2010s the amount of data available and computational capabilities improved to the point where it would make deep learning practical. It was in 2012 that Geoffrey Hinton and his team made a breakthrough in the field of speech recognition using convolutional neural networks (CNNs) and then again in 2014 he and his team made a similar breakthrough in the field of image classification, which paved the way for major subsequent innovations in the study of artificial intelligence.
Original training samples and results from the paper Generative Adversarial Nets. by Goodfellow et al. published in 2013. GAN model outputs are highlighted in yellow.
In 2014 Ian Goodfellow released his seminal paper on Generative Adversarial Networks (GANs) which positioned two networks against each other in a zero-sum game to create viable novel images that were similar in appearance to the images the model was trained on, but not the same. This work led to incremental developments in the GAN architecture which yielded increasingly better results in image synthesis over the following years, and the same methods began to be applied to new applications like music composition. New model architectures were developed in the form of convolutional and recurrent neural networks (text generation, video), long short-term memory (LSTM) (text generation), transformers (text generation), variational auto encoders (VAEs) (image generation), diffusion models (image generation) and various flow model architectures (audio, image, video.) Additional adjacent work in generative AI produced neural radiance fields (NeRF) which can construct 3D scenes and assets out of 2D images and reinforcement learning which uses simulations to train an agent through reward-based trial and error.
Although significant achievements in the space have been realized in recent years, including the generation of photorealistic images, viable deepfake videos, believable audio synthesis and human-like generative text produced by large language models like OpenAI’s GPT-1 it was not until the second half of 2022 with the release of a number of diffusion-based image services (MidJourney, Dall-E 2, Stable Diffusion), the release of OpenAI’s ChatGPT and the peppering of various text-to-video (Make-a-Video, Imagen Video) and text-to-3D (DreamFusion, Magic3D & Get3D) papers that the media and the mainstream took notice.
Results from ChatGPT, the fine-tuned version of OpenAI’s large language model GPT-3.
We are still in the infancy of generative AI, it is currently a novelty for consumers and businesses, but it will soon find its way into products, services, processes and all facets of business and our daily lives as it becomes a technological enabler for creating content and improving productivity. The jobs market will be heavily impacted as generative AI can not only augment or automate current creative functions of jobs but can be used to entirely replace certain job functions, making those jobs irrelevant.
The impact of generative AI will no doubt be a substantial topic in 2023. The use cases of generating image, text, code, audio, music, video, and 3D models we have seen thus far are just the tip of the iceberg, expect more innovations to come in 2023 along with further backlash from communities whose jobs will be affected by the commoditization of generative AI.
| 2023-07-08T00:00:00 |
2023/07/08
|
https://matthewdwhite.medium.com/a-brief-history-of-generative-ai-cb1837e67106
|
[
{
"date": "2023/01/01",
"position": 47,
"query": "generative AI jobs"
}
] |
AI: The Coming Disruption of Human Jobs
|
AI: The Coming Disruption of Human Jobs
|
https://www.linkedin.com
|
[] |
Artificial intelligence (AI) is a rapidly advancing technology that has the potential to greatly impact many industries and the way we live our lives.
|
Artificial intelligence (AI) is a rapidly advancing technology that has the potential to greatly impact many industries and the way we live our lives. One of the concerns that has been raised about AI is that it may lead to increased unemployment. However, the relationship between AI and unemployment is complex and not fully understood.
On one hand, AI has the ability to automate many tasks that were previously done by humans. This automation can lead to increased efficiency and productivity, but it can also result in job loss for those whose tasks have been automated. For example, in manufacturing, the use of robots and other forms of AI has led to the replacement of human workers in some cases. Similarly, in the retail industry, self-checkout kiosks and automated inventory management systems have also replaced human workers.
On the other hand, AI can also create new jobs and industries. For example, the development and implementation of AI systems require skilled professionals such as data scientists, engineers, and software developers. Additionally, AI can also lead to the creation of new products and services, which can generate new job opportunities.
| 2023-01-01T00:00:00 |
https://www.linkedin.com/pulse/ai-coming-disruption-human-jobs-er-suraj-kumar-soni
|
[
{
"date": "2023/01/01",
"position": 49,
"query": "generative AI jobs"
}
] |
|
Impact of ChatGPT on Jobs: What to Expect in the Future? - YVI
|
Impact of ChatGPT on Jobs: What to Expect in the Future? – YVI
|
https://yvi.ai
|
[] |
The development of advanced artificial intelligence models like ChatGPT contributes to a profound transformation in the job market.
|
The development of advanced artificial intelligence models like ChatGPT contributes to a profound transformation in the job market. While AI has the potential to increase productivity, streamline recruitment processes, and create new opportunities, it is also reshaping the nature of work in various ways. We will explore the impact of AI, like ChatGPT, on the changing landscape of jobs.
1. Augmentation, Not Replacement:
One common misconception is that AI models like ChatGPT are here to replace humans. Will ChatGPT replace jobs? GPT-4 will only partially supplant jobs. While it can automate specific programming tasks like generating code and documentation, more is needed to replace the human ingenuity and critical thinking essential for intricate software development. In reality, the current focus is on augmenting human capabilities. These AI systems can assist professionals in various domains, helping them make more informed decisions, automate repetitive tasks, and enhance productivity. ChatGPT can manage regular customer support enquiries, allowing human agents to concentrate on complicated issues and empathy-driven conversations.
2. New Skill Requirements:
As AI and automation take over routine and repetitive tasks, the demand for uniquely human skills is increasing. These include critical thinking, problem-solving, creativity, emotional intelligence, and adaptability. To be competitive in the ever-changing labour market, people must continuously improve their abilities and be lifelong learners.
3. The Rise of Hybrid Jobs:
AI is giving rise to a new category of “hybrid jobs”. These positions call for both technical proficiency and domain-specific knowledge. For example, a data scientist needs data analysis skills and an understanding of their industry. These roles are versatile and less susceptible to automation. Why hybrid work is the future? Hybrid work is considered the future because it fosters a highly engaged and productive workforce, enhancing company performance. Additionally, it contributes to higher employee retention by strengthening connections to colleagues and company culture, thereby promoting long-term commitment.
4. AI in Decision-Making:
AI models like ChatGPT are used in decision support across various sectors. Doctors use AI for diagnosing diseases, financial analysts rely on AI for investment advice, and managers use AI for strategic planning. The role of humans in these professions is evolving from making routine decisions to overseeing AI systems and creating complex, high-level judgments.
5. Ethical and Regulatory Roles:
The deployment of AI also requires oversight, ethics, and regulations. This has led to the emergence of roles focused on ensuring that AI systems are transparent, unbiased, and adhere to ethical standards. Ethical AI auditors, AI ethicists, and regulatory compliance experts are becoming increasingly important.
6. Reskilling and Upskilling:
Organizations and educational institutions focus on reskilling and upskilling programs to adapt to the changing job market. These initiatives aim to prepare the workforce for roles currently in demand and likely to remain in the future.
7. Gig Economy and Remote Work:
AI and digital technologies have enabled the gig economy to flourish. Freelancers and remote workers often use AI-driven platforms to find work and manage their careers. The boundary between traditional employment and independent contracting is becoming increasingly blurred.
8. Collaboration with AI:
The ability to work alongside AI systems is a valuable skill. Professionals need to understand how to interact with AI tools effectively. This includes configuring AI models, interpreting their outputs, and making decisions based on AI recommendations.
Conclusion
By automating repetitive processes and generating new job categories, introducing sophisticated AI models such as ChatGPT transforms the labour market. To prosper in this dynamic environment, people and institutions need to be proactive, flexible, and agile in seizing the chances that artificial intelligence presents. Rather than fearing AI, we should view it as a partner in reshaping the world of work. Our ability to collaborate effectively with AI, such as YVI, in the context of talent acquisition will define the future of jobs. Embracing platforms like YVI enhances our ability to identify and onboard top talent, making the collaboration between humans and AI a driving force in shaping the workforce of tomorrow.
| 2023-10-30T00:00:00 |
2023/10/30
|
https://yvi.ai/impact-of-chatgpt-on-jobs-what-to-expect-in-the-future-yvi/
|
[
{
"date": "2023/01/01",
"position": 62,
"query": "ChatGPT employment impact"
},
{
"date": "2024/05/01",
"position": 61,
"query": "ChatGPT employment impact"
},
{
"date": "2024/07/01",
"position": 61,
"query": "ChatGPT employment impact"
},
{
"date": "2024/08/01",
"position": 61,
"query": "ChatGPT employment impact"
}
] |
Does AI Displace Work? The Impact of ChatGPT Launch on the ...
|
Does AI Displace Work? The Impact of ChatGPT Launch on the Demand for Work
|
https://ideas.repec.org
|
[
"Kässi",
"Author",
"Listed"
] |
Downloadable! We examine the effects of generative artificial intelligence (GenAI) on the labor market, specifically focusing on the impact of ChatGPT on ...
|
We examine the effects of generative artificial intelligence (GenAI) on the labor market, specifically focusing on the impact of ChatGPT on job demand. Using micro-level data from one of the largest online labor platforms, we classify new job postings into three categories: substitutable, augmenting, and unaffected. We apply a difference-in-differences method to explore how ChatGPT’s deployment has altered labor demand within these categories. Our findings show a slight decrease in openings for substitutable jobs, where GenAI can fully perform tasks without loss of quality. However, there is an increase in demand for augmenting and unaffected jobs, which either benefit from faster task completion due to GenAI assistance or remain unchanged by it. The data indicates that ChatGPT’s introduction has not uniformly decreased labor demand but rather redistributed it, leading to growth in some sectors and declines in others.
Corrections
All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:rif:briefs:136. See general information about how to correct material in RePEc.
If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.
We have no bibliographic references for this item. You can help adding them by using this form .
If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Kaija Hyvönen-Rajecki (email available below). General contact details of provider: https://edirc.repec.org/data/etlaafi.html .
Please note that corrections may take a couple of weeks to filter through the various RePEc services.
| 2024-06-06T00:00:00 |
2024/06/06
|
https://ideas.repec.org/p/rif/briefs/136.html
|
[
{
"date": "2023/01/01",
"position": 84,
"query": "ChatGPT employment impact"
},
{
"date": "2023/07/01",
"position": 79,
"query": "ChatGPT employment impact"
},
{
"date": "2023/08/01",
"position": 82,
"query": "ChatGPT employment impact"
},
{
"date": "2023/09/01",
"position": 82,
"query": "ChatGPT employment impact"
},
{
"date": "2023/12/01",
"position": 86,
"query": "ChatGPT employment impact"
},
{
"date": "2024/05/01",
"position": 84,
"query": "ChatGPT employment impact"
},
{
"date": "2024/07/01",
"position": 81,
"query": "ChatGPT employment impact"
},
{
"date": "2024/08/01",
"position": 84,
"query": "ChatGPT employment impact"
},
{
"date": "2024/12/01",
"position": 84,
"query": "ChatGPT employment impact"
},
{
"date": "2025/02/01",
"position": 92,
"query": "ChatGPT employment impact"
},
{
"date": "2025/05/01",
"position": 92,
"query": "ChatGPT employment impact"
}
] |
How AI & ChatGPT Will Impact The Job Search Process - Work It Daily
|
How AI & ChatGPT Will Impact The Job Search Process
|
https://www.workitdaily.com
|
[
"J.T. O'Donnell",
"Aaron Sanborn",
"Jenna Arcand"
] |
AI is about to completely disrupt how we look for work. If you haven't used AI or ChatGPT in your job search, chances are your competition has.
|
How AI & ChatGPT Will Impact The Job Search Process
| 2023-09-11T00:00:00 |
2023/09/11
|
https://www.workitdaily.com/ai-chatgpt-job-search-process
|
[
{
"date": "2023/01/01",
"position": 91,
"query": "ChatGPT employment impact"
},
{
"date": "2023/07/01",
"position": 86,
"query": "ChatGPT employment impact"
},
{
"date": "2023/08/01",
"position": 92,
"query": "ChatGPT employment impact"
},
{
"date": "2023/09/01",
"position": 92,
"query": "ChatGPT employment impact"
},
{
"date": "2023/12/01",
"position": 94,
"query": "ChatGPT employment impact"
},
{
"date": "2024/05/01",
"position": 93,
"query": "ChatGPT employment impact"
},
{
"date": "2024/07/01",
"position": 93,
"query": "ChatGPT employment impact"
},
{
"date": "2024/08/01",
"position": 93,
"query": "ChatGPT employment impact"
},
{
"date": "2024/12/01",
"position": 93,
"query": "ChatGPT employment impact"
}
] |
How Will ChatGPT Change Your Job? - Public Affairs Council
|
How Will ChatGPT Change Your Job?
|
https://pac.org
|
[] |
The Wall Street Journal reports that as “with every wave of automation technologies, the latest will have a significant impact on jobs. Whereas blue-collar ...
|
Guess what. The preceding paragraph was produced by ChatGPT itself, when asked to write an article on how ChatGPT can change the way public affairs professionals do their jobs.
Maybe it’s not ideal — the word choices are robotic — but as a rough draft, it’s not bad and might be better than what some communications professionals could themselves produce in a half-hour, maybe more.
And it was produced for free, on the spot, in seconds — which is why ChatGPT and artificial intelligence (AI) in all its forms hold such promise for public affairs professionals, but also why they can be scary.
Scary, How?
Goldman Sachs reported earlier this year that AI could “significantly disrupt” global labor markets, exposing some 300 million jobs to automation. The Wall Street Journal reports that as “with every wave of automation technologies, the latest will have a significant impact on jobs. Whereas blue-collar workers bore the brunt of earlier waves, generative AI will likely have a greater effect on white-collar professions.”
“AI will have profound implications for the entire economy and for every industry, including public affairs professionals” says Michael O’Brien, vice president of global public affairs for BSA/The Software Alliance, who will speak at the Council’s 2023 Digital Media & Advocacy Summit (DMAS) on June 12 in Washington, D.C. “This technology will accelerate rapidly, which is why it’s difficult to say where exactly we’re headed.”
Most of us don’t even have a firm grasp of where we’ve been or where we are. “AI is already operating in ways we take for granted,” says Alexandra Reeve Givens, president and CEO of the Center for Democracy and Technology (CDT), who spoke at the Council’s Spring Executive Conference. “AI is operating in the GPS in your car, in your social media feeds and in the ordering of results when you do a Google search. There are ways AI operates that we don’t even think about, much less question.”
But it is ChatGPT, released just this past November, that people have been “sort of fixated on,” according to Chandler T. Wilson, founder of Bridge Corporate Intelligence. “They’re obsessed with the content-creation side of machine learning, which of course not only produces text but images and sounds, as well as writes code. ChatGPT amasses gigantic data sets, which includes not just articles that have been published and posted online but also tweets that go viral and other forms of social media messaging.”
This can give you access to data that Wilson says “is simply beyond the capacity of human intuition to make sense of — to create structure around, linking key facts and key themes, breaking down the complexity of this data. It can turn the ‘soft’ knowledge we’re used to relying on as individuals, with all these mistaken conclusions we come to and predictions we make, into statistics-based information that can mathematically model outcomes, and do so with far greater accuracy and is ultimately far more useful. For example, you can now predict engagement with press releases with — this is no exaggeration — 93% accuracy.”
An ‘Impression of Greatness’
There are limits, too, of course. ChatGPT “is incredibly limited, but good enough at some things to create a misleading impression of greatness,” according to OpenAI’s Sam Altman, one of its founders with Elon Musk. It would be “a mistake to be relying on it for anything important right now,” Altman tweeted just after ChatGPT’s release. This advice was ignored, largely, as more than a million users were taking advantage of it within five days of its launch. Within weeks, it had 100 million users, making it “the fastest growing app of all time,” ZDNET reports.
ChatGPT “is good for generating a first draft,” says Vlad Eidelman, chief technology officer at FiscalNote. “And it is very good at doing that because it’s trained on such a huge amount of data it has learned a useful representation of a lot of different information. It can write a plausible-sounding email for you, and even be quickly adapted through prompting to using your own style to do it, but it is still limited in important ways. It can produce something that sounds plausible but might not even be accurate or true.” (One obvious shortcoming: ChatGPT — unlike a simple Google search — has access to information up to 2021 only.)
Public affairs professionals can use ChatGPT for content creation — for writing a press release, an email or an op-ed — saving a great deal of time and trouble in the process. But that’s just for starters. By asking the right question — by creating a smart and useful “prompt” — you can access vast amounts of information otherwise unavailable to you, and it can be analyzed and sorted. Too often, trying to develop a plan of action in response to some development in the political world, we just read articles, talk to a few experts and make educated guesses.
“I can’t speak for individual companies, but I believe major companies in media and finance, for example, are already figuring out ways to take the information they have amassed internally for decades and use it as a reliable data source to allow others — for example, journalists, lobbyists and policymakers — to interact with the data through a natural language interface in ways that were not possible before,” Eidelman says. “The value down the road is the ability to interact in this new paradigm with more customized and even proprietary data sets, such as your own organization’s documents, statements, research and other forms of information. Then you can apply it to your own specific needs.”
| 2023-01-01T00:00:00 |
https://pac.org/impact/how-will-chatgpt-change-your-job
|
[
{
"date": "2023/01/01",
"position": 92,
"query": "ChatGPT employment impact"
},
{
"date": "2023/05/18",
"position": 4,
"query": "ChatGPT employment impact"
},
{
"date": "2023/07/01",
"position": 87,
"query": "ChatGPT employment impact"
},
{
"date": "2023/08/01",
"position": 93,
"query": "ChatGPT employment impact"
},
{
"date": "2023/09/01",
"position": 93,
"query": "ChatGPT employment impact"
},
{
"date": "2023/12/01",
"position": 93,
"query": "ChatGPT employment impact"
},
{
"date": "2024/05/01",
"position": 94,
"query": "ChatGPT employment impact"
},
{
"date": "2024/07/01",
"position": 94,
"query": "ChatGPT employment impact"
},
{
"date": "2024/08/01",
"position": 94,
"query": "ChatGPT employment impact"
},
{
"date": "2024/12/01",
"position": 92,
"query": "ChatGPT employment impact"
}
] |
|
AI and ML: Now is the Time to Invest in Skilling Your Workforce - AWS
|
Artificial Intelligence and Machine Learning: Now is the Time to Invest in Skilling Your Workforce
|
https://aws.amazon.com
|
[] |
Machine learning engineers design and implement the machine learning infrastructure that supports the AI models, while software engineers build and maintain ...
|
AWS helps customers at every stage of their ML adoption journey with the most comprehensive set of AI and ML services, infrastructure, and implementation resources. AWS recently announced Amazon Bedrock, a new service for customers to build and scale generative AI-based applications using FMs, democratizing access for all builders. Also, we are delivering applications like Amazon CodeWhisperer for free, which revolutionizes developer productivity by generating code suggestions in real time. As customers seek to leverage these technologies to automate tasks, improve decision-making, and gain insights from data, they require workers with expertise in cloud-based data analytics, machine learning models, and cloud-based AI platforms. AWS Training and Certification is passionate about helping organizations of all sizes upskill their workforce to capture the full value of AI and ML.
To capture this value, leaders are adapting their business strategies to invest in workforce skilling. One of our customers, ENGIE, a multinational utility company and global reference in low-carbon energy and services, partnered with AWS Training and Certification to develop a cloud skills training program to equip its decentralized team of 4,000 IT professionals with proper skill sets to act on the data in a timely manner. Because of the training, ENGIE’s engineers adopted more advanced functionalities such as machine learning for predictive maintenance models used at its power plants. “Every time someone is trained, that person can start innovating,” says Frédéric Poncin, head of the Cloud Center of Excellence at ENGIE. “They can help transform the old system into a brand-new cloud-native application.”
"Every time someone is trained, that person can start innovating. They can help transform the old system into a brand-new cloud-native application."
—Frédéric Poncin, Head of the Cloud Center of Excellence, ENGIE
Organizations are also recognizing the importance of cloud technology beyond the IT department and are now focusing on developing cloud expertise throughout different departments, including finance, sales, human resources, marketing, and administration. Volkswagen, for example, invested in strengthening its employees’ cloud knowledge and skills using a cloud-centric framework. This resulted in reduced time to market and improved cross-team collaboration.
Now is the time to invest in workforce upskilling and reskilling to maximize opportunities to grow your business with AI and ML. Our online learning center, AWS Skill Builder, offers digital training built by experts at AWS, including more than 80 courses and learning resources on AI and ML. With the emergence of generative AI, AWS is empowering learners and decision-makers to build their knowledge and skills in generative AI with many new trainings. Organizations can deepen and accelerate their talent transformation with a Team subscription offering unlimited access to hands-on, game-based learning, such as AWS Cloud Quest: Machine Learning Specialist. Leaders can partner with AWS Training and Certification to utilize these resources and more to enable continuous development of new skills across their organization to drive innovation and growth for their business.
For leaders and decision-makers who want to learn even more about generative AI, the Generative AI for Executives video series provides a high-level picture what generative AI is and how it can address your business challenges, drive growth, and why it has the potential to revolutionize industries.
| 2023-01-01T00:00:00 |
https://aws.amazon.com/executive-insights/content/artificial-intelligence-and-machine-learning-now-is-the-time-to-invest-in-skilling-your-workforce/
|
[
{
"date": "2023/01/01",
"position": 2,
"query": "machine learning workforce"
},
{
"date": "2023/02/01",
"position": 2,
"query": "machine learning workforce"
},
{
"date": "2023/04/01",
"position": 2,
"query": "machine learning workforce"
},
{
"date": "2023/07/11",
"position": 14,
"query": "AI labor market trends"
},
{
"date": "2023/07/11",
"position": 68,
"query": "AI workers"
},
{
"date": "2023/07/11",
"position": 65,
"query": "artificial intelligence workers"
},
{
"date": "2023/07/11",
"position": 1,
"query": "machine learning workforce"
},
{
"date": "2023/08/01",
"position": 2,
"query": "machine learning workforce"
},
{
"date": "2023/09/01",
"position": 2,
"query": "machine learning workforce"
},
{
"date": "2023/10/01",
"position": 2,
"query": "machine learning workforce"
},
{
"date": "2024/03/01",
"position": 2,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 2,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 2,
"query": "machine learning workforce"
},
{
"date": "2024/10/01",
"position": 2,
"query": "machine learning workforce"
},
{
"date": "2024/12/01",
"position": 2,
"query": "machine learning workforce"
},
{
"date": "2025/01/01",
"position": 2,
"query": "machine learning workforce"
},
{
"date": "2025/02/01",
"position": 2,
"query": "machine learning workforce"
},
{
"date": "2025/03/01",
"position": 2,
"query": "machine learning workforce"
},
{
"date": "2025/04/01",
"position": 2,
"query": "machine learning workforce"
}
] |
|
How Machine Learning is Transforming the Workplace - Encapture
|
How Machine Learning is Transforming the Workplace
|
https://encapture.com
|
[
"Encapture User"
] |
With ML, large teams aren't needed to process documents and front-office employees can spend less time on tedious tasks and more time with customers. Because ...
|
Machine learning (a form of artificial intelligence) has been around for years as a tool to help researchers, scientists, and academics process vast amounts of information to gain better insights. More recently, machine learning has been applied to very practical use cases in business settings and is changing the way employees do their jobs.
Interestingly, only 29% of companies are regularly using any form of artificial intelligence today – which means current adopters who embrace machine learning will gain a significant advantage over their competitors.
What is machine learning (ML)?
Machine learning is a form of artificial intelligence where computer systems use algorithms and statistical models to perform tasks without receiving explicit instructions. In other words, an ML system can detect patterns in a set of data and use that “knowledge” to make a recommendation, prediction, or find an answer. The reason we use the term “learning” is that the system can become “smarter” (ie more efficient or more confident) in its tasks over time by learning from mistakes made along the way.
We humans have a popular game that mimics how ML works: “20 Questions.” In this game, a player thinks of an object and then allows other players to ask yes or no questions to guess what they’re thinking. The crowd of players can ask more targeted questions as the game goes on to help improve the quality of their guesses, with the ultimate goal of correctly identifying the object.
ML works much the same way: a system is trained to ask questions about the data it’s reviewing and then will “guess” the answer. Of course, the system isn’t limited to just 20 “yes or no” questions, but can ask thousands of questions and receive all sorts of answers back. The more answers it receives, the more likely it will make a successful guess. That’s how intelligent capture (IC), a form of ML, can impact tedious workplace operations: by taking over the document classification and extraction processes, which are primary elements of IC.
How machine learning impacts document processing
There are dozens of ways to apply ML in any company, but a really practical and valuable use of ML is document processing. Most companies have tons of documents flowing into their various functions (think invoices in accounting, new employee forms in HR, customer orders in sales, loan applications in a bank, etc.).
Today, these documents get handled by workers who review the content to answer a bunch of questions: Did I receive the correct documents? If not, which documents are missing and how can I track them down? Are the documents properly filled out and signed? Can I find the information I need to make a decision?
Of course, the practical result of these processes is to get to very concrete answers: Should I pay this invoice, can I hire this employee, should I approve this loan, when do I fulfill this customer order, and so on.
Unfortunately, humans are not great at processing lots of unstructured data at high volumes — we make errors and miss important information. We’ve seen error rates for document identification in the 5-10% range and data entry error rates up to 25-30%, which really adds up if your company is making thousands of decisions every hour. These errors can lead to significant issues – delays in processing, poor decision-making, and general inefficiencies trying to track down the correct data. Thankfully, machine learning is a great solution for processing lots of unstructured content and resolving operational issues.
Here are two simple examples of how ML can help address workplace documentation processing:
Document classification
ML can review a document and figure out its type; for example, a driver’s license, an invoice, a loan application, or customer order. This is really helpful when collecting multiple types of documents from a single source, like when approving a mortgage application at a bank or reviewing medical claims at an insurance company. Letting ML work off a “checklist” of documents to automatically determine what’s been received and what’s missing provides tremendous value to organizations.
Data extraction
ML can also read through documents and pull out important information. There are various extraction techniques that ML utilizes to find the correct information, ranging from structured forms to contextual entities to natural language processing. For example, an ML system can look at an invoice and find the payee’s name, mailing address, PO number, total invoice amount, and due date — and then check it against the accompanying purchase order to ensure the amounts match. Or, in a mortgage origination process, an ML system can review a paystub to ensure that the borrower’s name matches the application and income can be verified.
There are dozens of ways ML can assist companies when handling documents, and we won’t go through all of them here. However, let’s talk about the benefits of using ML in a document-intensive business process.
Better, Faster, Cheaper
Machine learning, when properly implemented, truly is a transformational solution and provides incredible benefits to a company. Here are a few:
Higher-quality data
When ML takes the first pass at pulling information out of documents, employees don’t have to focus on the 85-90% of data entry that’s straightforward and repetitive (after all, the ML system can figure that out) and instead can function as a “second set of eyes” on data that the system can’t decipher easily (for example, a scanned page that’s really blurry or a page with chicken-scratch handwriting). When employees transition away from data entry and into reviewing exception cases, their efficiency skyrockets, and error rates drop substantially (not to mention improved morale!). With this approach, accuracy rates can approach near perfect (100%).
Quicker turnaround times
ML systems process data fast – they can read an entire page of text in a few seconds – and can locate pertinent information instantaneously. Coupled with cloud computing, an ML system can digest documents and data at massive speeds, which means time wasted by humans reviewing documents is mostly eliminated. Consequently, decisions can be made much faster, which results in a better experience for customers, employees, and vendors.
Lower costs
With ML, large teams aren’t needed to process documents and front-office employees can spend less time on tedious tasks and more time with customers. Because documents are digitized from the onset, expensive courier systems, and physical storage solutions are eliminated. Further, your company can grow more efficiently as the incremental cost of ML technology is negligible, especially compared to hiring staff.
Embrace machine learning for future growth
Encapture, an intelligent capture platform, can help you easily deploy machine learning across your enterprise for a variety of use cases. Utilizing intelligent automation doesn’t have to be hard, and the benefits are transformational – better data, faster decisions, more productive employees, and happier customers.
Reach out so we can help you solve your biggest problems using machine learning.
| 2020-03-09T00:00:00 |
2020/03/09
|
https://encapture.com/how-machine-learning-is-transforming-the-workplace/
|
[
{
"date": "2023/01/01",
"position": 3,
"query": "machine learning workforce"
},
{
"date": "2023/02/01",
"position": 3,
"query": "machine learning workforce"
},
{
"date": "2023/04/01",
"position": 4,
"query": "machine learning workforce"
},
{
"date": "2023/08/01",
"position": 3,
"query": "machine learning workforce"
},
{
"date": "2023/09/01",
"position": 4,
"query": "machine learning workforce"
},
{
"date": "2023/10/01",
"position": 4,
"query": "machine learning workforce"
},
{
"date": "2024/03/01",
"position": 4,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 3,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 3,
"query": "machine learning workforce"
},
{
"date": "2024/10/01",
"position": 4,
"query": "machine learning workforce"
},
{
"date": "2024/12/01",
"position": 3,
"query": "machine learning workforce"
},
{
"date": "2025/01/01",
"position": 3,
"query": "machine learning workforce"
},
{
"date": "2025/02/01",
"position": 3,
"query": "machine learning workforce"
},
{
"date": "2025/03/01",
"position": 3,
"query": "machine learning workforce"
},
{
"date": "2025/04/01",
"position": 3,
"query": "machine learning workforce"
}
] |
7 Best Use Cases of Machine Learning in HR - Aisera
|
7 Best Use Cases of Machine Learning in HR
|
https://aisera.com
|
[
"Aayush Sharma",
"Author"
] |
Machine learning impacts HR operations by focusing on three main areas: optimizing workforce performance and management, personalizing employee development and ...
|
Machine learning impacts HR operations by focusing on three main areas: optimizing workforce performance and management, personalizing employee development and automating routine tasks.
Optimizing Workforce Management
For an organization looking for ways to become more productive, workforce management plays a very critical role. This means finding the right talent at the right time which essentially has an impact on various aspects of business like customer satisfaction and even bottom line profitability.
Predictive Analytics: ML-powered predictive analytics help anticipate workforce demands by analyzing historical data and market trends. This helps in finding skills gaps and plan accordingly.
ML-powered predictive analytics help anticipate workforce demands by analyzing historical data and market trends. This helps in finding skills gaps and plan accordingly. Enhanced Productivity: Organizations can have a significant impact on productivity by simply optimizing scheduling and resource allocation. Organizations end up achieving more without an increase in workforce.
Personalizing Employee Development
This aspect is crucial for having a skilled and motivated workforce. By focusing on personalized development, organizations can increase retention and overall performance. This also incentivizes employees to contribute effectively to organizational goals since the organization is also contributing to employees personal growth.
Performance Analysis: Machine learning analyzes company-wide performance data to identify individual strengths and weaknesses.
Machine learning analyzes company-wide performance data to identify individual strengths and weaknesses. Personalized Development Plans: By getting visibility on the organization-wide employee skills, HR teams can create personalized plans that are sync with employees and organizational long term goals.
By getting visibility on the organization-wide employee skills, HR teams can create personalized plans that are sync with employees and organizational long term goals. Strategic Growth: Personalized development initiatives ensure that employees are equipped with the skills needed to drive strategic growth and innovation within the organization.
Automating Routine Tasks
Automating routine tasks is crucial for freeing up resources and enhancing operational efficiency. Manual administrative tasks can be time-consuming and divert attention from strategic initiatives. This also helps HR teams to focus more on tasks that have a direct impact on employee satisfaction and avoid employee attrition for business growth.
| 2025-03-18T00:00:00 |
2025/03/18
|
https://aisera.com/blog/machine-learning-hr/
|
[
{
"date": "2023/01/01",
"position": 6,
"query": "machine learning workforce"
},
{
"date": "2023/02/01",
"position": 6,
"query": "machine learning workforce"
},
{
"date": "2023/08/01",
"position": 6,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 6,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 6,
"query": "machine learning workforce"
},
{
"date": "2024/12/01",
"position": 6,
"query": "machine learning workforce"
},
{
"date": "2025/01/01",
"position": 6,
"query": "machine learning workforce"
},
{
"date": "2025/02/01",
"position": 12,
"query": "machine learning workforce"
},
{
"date": "2025/03/01",
"position": 7,
"query": "machine learning workforce"
},
{
"date": "2025/04/01",
"position": 7,
"query": "machine learning workforce"
}
] |
Boost Workplace Productivity with Machine Learning
|
Boost Workplace Productivity with Machine Learning
|
https://www.deliberatedirections.com
|
[
"Brett Wharton",
"Allison Dunn"
] |
With machine learning, you can expect more efficient processes and increased collaboration between employees. It also helps ensure compliance with industry ...
|
Machine learning is a game-changer in the workplace, and companies are using it to boost productivity in various ways and become more successful than ever.
Machine learning is an artificial intelligence that uses algorithms to analyze data and make predictions. It’s been around for decades, but it wasn’t until recently that it became accessible enough to be used by companies on a large scale.
Machine learning is helping companies across industries improve their workflow and make better business decisions. Here are some examples of how businesses are using machine learning in the workplace.
1. Automated Scheduling
Automated scheduling can include many things, and one of the most common ones is using machine learning to increase productivity and efficiency within an organization. This is done in several ways, including:
Workforce Planning And Forecasting: Planning ahead allows companies to ensure they have enough workers on hand when they need them. It also helps forecast how many people will be needed for a particular project or event;
Planning ahead allows companies to ensure they have enough workers on hand when they need them. It also helps forecast how many people will be needed for a particular project or event; Workforce Management: With automated scheduling software, managers can receive alerts when specific processes or tasks are delayed or completed outside their normal time frames. This allows them to take corrective action or notify other departments if necessary;
With automated scheduling software, managers can receive alerts when specific processes or tasks are delayed or completed outside their normal time frames. This allows them to take corrective action or notify other departments if necessary; Workforce Optimization: One of the best uses for machine learning in the workplace is optimizing your workforce based on historical data. For example, suppose your employees typically work 40 hours per week but only report 30 hours due to overtime. In that case, you may want to schedule fewer workers during certain times and more during others so that you don’t have any idle time and still meet customer demand.
Automated scheduling is a key component of many machine learning-based workplace productivity solutions. It allows businesses to reduce the time spent on scheduling by automating the process and providing employees with more consistent schedules. This will enable managers to focus on other tasks, resulting in increased productivity for both parties involved.
Here is an example of a scheduling tool:
Teamsense: Teamsense is an absence management software designed specifically for hourly and remote employees. With text-based access from mobile phones and integrations with popular HRIS providers, TeamSense provides detailed reports on absences and easily helps you stay compliant with employee records.
2. HR Chatbots
One of the ways companies use machine learning to improve workplace productivity is through HR chatbots. The first step in using a chatbot for HR is to determine your company’s goals and how the bot can help you achieve them.
Next, you need to figure out what kind of data you have to work with and what kind of questions can be answered by your data. For example, if you want to know when employees are likely to leave their jobs, you need to collect data on employee turnover and other relevant metrics.
Once you have this information, it’s time to start building your chatbot! You can do this using any tool that allows you to make a conversational user interface (CUI). There are many CUI builders available, and they all have different features, but they all allow users to create chatbots without coding experience.
Once your bot is created, it needs some training so that it’ll be able to answer customer queries correctly most of the time. This process involves feeding it lots of examples of human interactions with similar questions and responses so that it can learn from them and make its own decisions about how best to respond.
HR chatbots can be used to answer routine questions or provide help with company policies. Here are some benefits of chatbots for HR:
Improve employee engagement by reducing the time spent on repetitive tasks. This reduces employee turnover and increases productivity;
Provide better customer support and increase customer satisfaction by providing easy access to information about benefits, policies, and other HR issues;
Improve onboarding new employees’ efficiency and ensure they have all the information they need before starting work;
Chatbots can also be used for scheduling meetings or events to avoid double bookings or having too many meetings scheduled at once.
HR Chatbots are digital assistants that can be used to help employees with their day-to-day tasks. They can answer questions, schedule meetings, and suggest solutions to problems. Here are some examples of chatbots:
Talmundo: Talmundo is an HR chatbot that facilitates hiring by connecting employers with candidates. It’s a free service that saves recruiters time and effort by eliminating the need to review resumes manually, schedule interviews, and respond to candidates. The Talmundo chatbot will do it all for you.
Talmundo is an HR chatbot that facilitates hiring by connecting employers with candidates. It’s a free service that saves recruiters time and effort by eliminating the need to review resumes manually, schedule interviews, and respond to candidates. The Talmundo chatbot will do it all for you. Newton: Newton is a chatbot that helps you schedule meetings with your coworkers by suggesting times when everyone is available or looking for new ways to find common ground between conflicting schedules.
3. Time Management Software
One of the primary uses for machine learning is time management software, which helps you track how much time you spend on different tasks. Using this software, you can see what is taking up your time and how long each activity takes to schedule more effectively.
There are many different uses for machine learning technology in the workplace today, including:
Recruiting: Machine learning algorithms can scan resumes and provide recommendations based on keywords and skills listed in them;
Machine learning algorithms can scan resumes and provide recommendations based on keywords and skills listed in them; Training: It can be used to train new workers through simulations or by providing feedback on their performance while they’re working on real-life projects;
It can be used to train new workers through simulations or by providing feedback on their performance while they’re working on real-life projects; Sales: Sales teams often use machine learning programs to predict which leads will convert into paying customers or what products they should push harder during sales presentations.
Here are some of the most common AI time management software:
Evernote: Evernote can help you organize your time and take notes on important tasks. It also allows you to share notes with others to work together on projects;
Evernote can help you organize your time and take notes on important tasks. It also allows you to share notes with others to work together on projects; Google Calendar: Google Calendar is a tool to schedule your meetings, appointments, and other events. You can also use it as a reminder for upcoming deadlines and tasks;
Google Calendar is a tool to schedule your meetings, appointments, and other events. You can also use it as a reminder for upcoming deadlines and tasks; Slack: Slack is a popular team messaging app that allows you to create channels for different projects or topics of discussion within your organization. It’s also useful for sharing documents and images with colleagues who aren’t necessarily located in the same building or office location as you are.
Time-tracking software has become increasingly popular over the years due to its ability to save businesses time, money, and resources. Not only does this type of software help businesses keep track of their employees’ work hours but it also allows them to make more efficient use of their employees’ time by providing them with tools to monitor their productivity levels.
Many companies have started using machine learning algorithms within their time-tracking software solutions to understand better how employees spend their time throughout the day and week.
4. AI-Powered Meeting Tools
Meetings can be a big drain on productivity, especially when they’re poorly planned. To address this issue, many companies are using AI to power meeting tools and help make meetings more effective and efficient. The main benefits of these tools include the following:
Identify Unproductive Meetings: The first benefit is that AI-powered meeting tools can identify unproductive meetings. This means that managers will know which sessions are a waste of time and money and can focus on the ones that matter most;
The first benefit is that AI-powered meeting tools can identify unproductive meetings. This means that managers will know which sessions are a waste of time and money and can focus on the ones that matter most; Improve Planning: Another benefit is that AI-powered meeting tools can help you plan your next meeting better by providing suggestions based on past results from previous meetings, so you don’t have to waste time brainstorming ideas repeatedly;
Another benefit is that AI-powered meeting tools can help you plan your next meeting better by providing suggestions based on past results from previous meetings, so you don’t have to waste time brainstorming ideas repeatedly; Increased Accuracy: Machine learning algorithms can make predictions more accurately than humans can achieve through intuition alone. This means they can provide better insights into what drives customer behavior, which makes it easier to optimize sales and marketing campaigns using predictive analytics. It also means they can analyze large amounts of data more efficiently than humans could ever hope to do manually, resulting in faster results with less effort required from employees.
Here are some examples of AI meeting tools:
Calendly: Calendly online scheduler allows you to create a visual calendar for your customers or clients and book appointments with them automatically. The app also allows you to send bulk invitations and manage recurring meetings easily;
Calendly online scheduler allows you to create a visual calendar for your customers or clients and book appointments with them automatically. The app also allows you to send bulk invitations and manage recurring meetings easily; Meeting Planner: With Meeting Planner, you can easily organize your schedule and find open slots in which to meet with others. Meeting Planner will automatically suggest times when everyone is available so that you can book the best time possible for your group. It also lets you send automatic reminders before each scheduled event so that no one forgets about their commitment.
Meetings are one of the most common reasons people cite for not being productive at work. As a result, it’s no surprise that they’re also one of the top causes of stress and burnout. That’s why it’s important to use AI-powered meeting tools to reduce the time spent in meetings and make them more efficient.
5. Predictive Maintenance
Predictive maintenance is a type of data analytics that helps companies predict when their equipment will fail, so they can take action before it does. This can be done using machine learning algorithms that look at historical data about previous failures and trends.
The benefits of predictive maintenance include the following:
Reduced Downtime: If you know your equipment is going to fail, you can take action to prevent it from happening during peak hours or when customers are present;
If you know your equipment is going to fail, you can take action to prevent it from happening during peak hours or when customers are present; Reduced Repair Costs: You’ll also be able to replace parts before they break down completely, which will reduce repair costs by allowing you to buy fewer replacement parts overall;
You’ll also be able to replace parts before they break down completely, which will reduce repair costs by allowing you to buy fewer replacement parts overall; Improved Safety: Predictive maintenance helps ensure that employees aren’t working in unsafe conditions due to malfunctioning equipment.
With an experienced development team, you can even create complex, multi-stage, sophisticated systems that can both help with industrial monitoring and predictive maintenance.
For example, this can be accomplished by implementing ML solutions together with IoT in telecom. Such a solution will enable your team to monitor equipment in real time and predict breakdowns.
6. Predict Sales and Demand
Sales and demand forecasting are one of the most important aspects of any business. It’s a complex process, so making mistakes can be really easy. If a company doesn’t have accurate demand forecasts, it could end up overstocking its inventory, which can negatively affect the bottom line.
Machine learning can help companies with their sales and demand forecasting by providing them with more accurate predictions than human analysts can make alone.
Machine learning algorithms take data from historical sales patterns and then use algorithms to find patterns within that data. The algorithm then uses these patterns to predict future product sales and demand levels.
In practice, machine learning algorithms can be used to analyze customer purchasing behavior to make predictions about future customer purchases based on past trends. This allows businesses to understand better what products will sell well at certain times of the year or during certain seasons.
Conclusion
The future of work is here, bringing with it a new set of challenges and opportunities. Companies are looking for new ways to improve workplace productivity, but they don’t always know where to start.
Luckily, machine learning offers a solution: by leveraging the power of artificial intelligence and extensive data analysis, companies can create more efficient workflows and stay ahead of their competitors.
With machine learning, you can expect more efficient processes and increased collaboration between employees. It also helps ensure compliance with industry standards and government regulations—all while freeing up time for employees to do what they love most: make your company great!
| 2022-12-02T00:00:00 |
2022/12/02
|
https://www.deliberatedirections.com/machine-learning-workplace-productivity/
|
[
{
"date": "2023/01/01",
"position": 7,
"query": "machine learning workforce"
},
{
"date": "2023/02/01",
"position": 7,
"query": "machine learning workforce"
},
{
"date": "2023/03/13",
"position": 1,
"query": "machine learning workforce"
},
{
"date": "2023/03/13",
"position": 97,
"query": "artificial intelligence workers"
},
{
"date": "2023/04/01",
"position": 5,
"query": "machine learning workforce"
},
{
"date": "2023/08/01",
"position": 7,
"query": "machine learning workforce"
},
{
"date": "2023/09/01",
"position": 5,
"query": "machine learning workforce"
},
{
"date": "2023/10/01",
"position": 5,
"query": "machine learning workforce"
},
{
"date": "2024/03/01",
"position": 5,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 7,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 7,
"query": "machine learning workforce"
},
{
"date": "2024/10/01",
"position": 5,
"query": "machine learning workforce"
},
{
"date": "2024/12/01",
"position": 7,
"query": "machine learning workforce"
},
{
"date": "2025/01/01",
"position": 7,
"query": "machine learning workforce"
},
{
"date": "2025/02/01",
"position": 10,
"query": "machine learning workforce"
},
{
"date": "2025/03/01",
"position": 9,
"query": "machine learning workforce"
},
{
"date": "2025/04/01",
"position": 9,
"query": "machine learning workforce"
}
] |
Integrating Artificial Intelligence (AI) With Workforce Solutions for ...
|
Integrating Artificial Intelligence (AI) With Workforce Solutions for Sustainable Care: A Follow Up to Artificial Intelligence and Machine Learning (ML) Based Decision Support Systems in Mental Health
|
https://pubmed.ncbi.nlm.nih.gov
|
[
"Higgins O Wilson Rl",
"Chiu Sc",
"Wei Lc.",
"Et Al.",
"Najeeb M",
"Islam S.",
"Higgins O",
"Short Bl",
"Chalup Sk",
"Wilson Rl."
] |
This integrative literature review examines the evolving role of artificial intelligence (AI) and machine learning (ML) based clinical decision support systems ...
|
This integrative literature review examines the evolving role of artificial intelligence (AI) and machine learning (ML) based clinical decision support systems (CDSS) in mental health (MH) care, expanding on findings from a prior review (Higgins et al. 2023). Using and integrative review framework, a systematic search of six databases was conducted with a focus on primary research published between 2022 and 2024. Five studies met the inclusion criteria and were analysed for key themes, methodologies, and findings. The results reaffirm AI's potential to enhance MH care delivery by improving diagnostic accuracy, alleviating clinician workloads, and addressing missed care. New evidence highlights the importance of clinician trust, system transparency, and ethical concerns, including algorithmic bias and equity, particularly for vulnerable populations. Advancements in AI model complexity, such as multimodal learning systems, demonstrate improved predictive capacity but underscore the ongoing challenge of balancing interpretability with innovation. Workforce challenges, including clinician burnout and staffing shortages, persist as fundamental barriers that AI alone cannot resolve. The review not only confirms the findings from the first review but also adds new layers of complexity and understanding to the discourse on AI-based CDSS in MH care. While AI-driven CDSS holds significant promise for optimising MH care, sustainable improvements require the integration of AI solutions with systemic workforce enhancements. Future research should prioritise large-scale, longitudinal studies to ensure equitable, transparent, and effective implementation of AI in diverse clinical contexts. A balanced approach addressing both technological and workforce challenges remain critical for advancing mental health care delivery.
| 2023-01-01T00:00:00 |
https://pubmed.ncbi.nlm.nih.gov/40055746/
|
[
{
"date": "2023/01/01",
"position": 8,
"query": "machine learning workforce"
},
{
"date": "2023/02/01",
"position": 8,
"query": "machine learning workforce"
},
{
"date": "2023/04/01",
"position": 8,
"query": "machine learning workforce"
},
{
"date": "2023/08/01",
"position": 8,
"query": "machine learning workforce"
},
{
"date": "2023/09/01",
"position": 8,
"query": "machine learning workforce"
},
{
"date": "2023/10/01",
"position": 8,
"query": "machine learning workforce"
},
{
"date": "2024/03/01",
"position": 8,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 9,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 8,
"query": "machine learning workforce"
},
{
"date": "2024/10/01",
"position": 6,
"query": "machine learning workforce"
},
{
"date": "2024/12/01",
"position": 9,
"query": "machine learning workforce"
},
{
"date": "2025/01/01",
"position": 8,
"query": "machine learning workforce"
},
{
"date": "2025/02/01",
"position": 5,
"query": "machine learning workforce"
},
{
"date": "2025/03/01",
"position": 5,
"query": "machine learning workforce"
},
{
"date": "2025/04/01",
"position": 5,
"query": "machine learning workforce"
}
] |
|
How AI and machine learning can optimise your workforce
|
How AI and machine learning can optimise your workforce
|
https://www.guidantglobal.com
|
[] |
AI brings yet another monumental shift in workforce management. From pre-screening resumes to removing bias from job adverts, predicting future hiring needs.
|
Artificial intelligence (AI) is driving huge change in almost every industry. But how can AI technology assist HR and talent acquisition teams to find the right candidates in an increasingly competitive talent market?
Technology has been changing the way we attract, engage and retain top talent for some time. The digital transformation of HR is, without doubt, well underway.
Workforce technologies — such as applicant tracking systems (ATS) and vendor management systems (VMS) — are already used in some forward-thinking organisations, either through a business’ own technologies or through the tech implemented by their MSP or RPO provider.
AI brings yet another monumental shift in workforce management. From pre-screening resumes to removing bias from job adverts, predicting future hiring needs to enhancing employee engagement, artificial intelligence is poised to be truly transformational.
Of course, there are some that see artificial intelligence as yet another highly-publicised technology that won’t see the light of day in the workforce solutions industry. But the truth of the matter is AI is already with us.
Addressing some of the ethical concerns of AI
As with any new technology, there are some ethical concerns. In recent years, recruitment AI and machine-learning technologies have sometimes favoured male candidates over female candidates when supplied with bad data — the most high-profile case being at Amazon. But if these technologies are well-utilised and fed with validated data, such biases can be eliminated.
Meanwhile, some techno-futurists predict AI will replace human HR altogether. But the reality is destined to be very different. Rather than replace people, artificial intelligence will optimise processes — enabling HR professionals to create more strategic workforce plans, expand their skillsets and increase their influence within their businesses.
Instead of full-scale automation, the future of HR seems to be one of augmentation, with people increasingly at the heart of big, impactful decision-making.
Such a future certainly looks bright for human resources professionals, but where exactly will we see AI making the biggest impact?
Machine-learning technology will optimise job adverts (and help you find the best talent)
Writing effective job adverts is time-consuming, as is distributing them across multiple channels. AI technology has the potential to optimise both elements.
Programmatic advertising’s machine-learning technology is an excellent example of automating job ad placement. It automatically buys, places and optimises job ads across multiple platforms — from Facebook ads to job board posts — to improve the quality of hire.
Likewise, Textio, an innovative augmented writing platform, optimises the language and removes bias from job adverts, ensuring maximum traction among people from all backgrounds. For HR, recruiters and hiring managers, both of these HR technologies have the potential to remove a great deal of wasted time and effort from the hiring process.
AI-powered VMS technology helps predict future hiring needs
A large part of MSP implementation is the introduction of technology, such as a vendor management system (VMS). VMS technologies assist in talent acquisition, services and contingent workforce management processes.
Both
Like MSP solutions, AI-backed VMS technologies are only really efficient with a high-volume contingent talent need. Naturally, larger quantities of data produce better actionable insights. Without such data, the impact of employing a VMS within an MSP program is negligible.
For large organisations, the insights generated by VMS technologies can, however, help businesses predict future talent needs. In an age of digital transformation, skills shortages and agility by necessity, utilising artificial intelligence can be the difference between attracting the right talent at the right time and trailing behind the competition. Managing a complex contingent workforce can be exceptionally difficult for HR managers. Many choose to partner with managed service providers like Guidant Global to help manage and optimise their temporary and contractor talent.A large part of MSP implementation is the introduction of technology, such as a vendor management system (VMS). VMS technologies assist in talent acquisition, services and contingent workforce management processes.Both SAP Fieldglass and Beeline (utilised by Guidant Global in our MSP programs) harness the power of AI to turn complex, big data into actionable insights to enable better, more strategic workforce management decisions.Like MSP solutions, AI-backed VMS technologies are only really efficient with a high-volume contingent talent need. Naturally, larger quantities of data produce better actionable insights. Without such data, the impact of employing a VMS within an MSP program is negligible.For large organisations, the insights generated by VMS technologies can, however, help businesses predict future talent needs. In an age of digital transformation, skills shortages and agility by necessity, utilising artificial intelligence can be the difference between attracting the right talent at the right time and trailing behind the competition.
The takeaway: AI will drive huge growth in the future job market
One aspect that often gets lost in discussions around the impact of AI and machine-learning on workforce management is the number of technical jobs that will be created. As more organisations utilise AI and machine learning technologies, the need for talent that can build, manage and oversee this tech will require millions of specialists.
By 2022, the World Economic Forum predicts that AI will globally create 133 million new roles. With skills shortages already at acute levels in many industries, these roles will inevitably be difficult to fill. But with the AI-powered workforce management technologies in place, you can predict when they’ll be needed in your organisation and ensure you find the best talent on the market.
| 2023-01-01T00:00:00 |
https://www.guidantglobal.com/news/how-ai-and-machine-learning-can-optimise-your-workforce/
|
[
{
"date": "2023/01/01",
"position": 10,
"query": "machine learning workforce"
},
{
"date": "2023/02/01",
"position": 9,
"query": "machine learning workforce"
},
{
"date": "2023/04/01",
"position": 7,
"query": "machine learning workforce"
},
{
"date": "2023/09/01",
"position": 7,
"query": "machine learning workforce"
},
{
"date": "2023/10/01",
"position": 7,
"query": "machine learning workforce"
},
{
"date": "2024/03/01",
"position": 7,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 10,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 10,
"query": "machine learning workforce"
},
{
"date": "2024/12/01",
"position": 10,
"query": "machine learning workforce"
},
{
"date": "2025/02/01",
"position": 11,
"query": "machine learning workforce"
},
{
"date": "2025/03/01",
"position": 10,
"query": "machine learning workforce"
},
{
"date": "2025/04/01",
"position": 10,
"query": "machine learning workforce"
}
] |
|
Machine Learning and Data at the Heart of Most Loved Workplace®
|
Machine Learning and Data at the Heart of Most Loved Workplace®
|
https://mostlovedworkplace.com
|
[] |
Uncover how machine learning and data transform companies with valuable insights and data-driven strategies to make them a Most Loved Workplace®.
|
Being a Most Loved Workplace® proves you listen to employees and strive to create a happier, healthier, and more productive workforce.
There are many ways that you can reach this goal, one of which is with machine learning (ML) and data. This focuses on emotional connectedness among employees – the key for organizations and employees to prosper.
We explore this in our whitepaper, documenting how the Love of Workplace Index™ (LOWI) helps predict employees’ love for their workplace and their level of commitment. Using a custom ML model, feedback from workers was extensively analyzed to gain valuable insights that would have originally been a guessing game.
In this article, we will use the findings from our whitepaper to paint a bigger picture of how machine learning and data are at the heart of a Most Loved Workplace®.
Understanding Machine Learning and Data
To fully understand the concept this article explores, it is worth understanding the fundamentals of machine learning and data, particularly when applied in the workplace.
Machine Learning (ML)
Machine learning is a branch of artificial intelligence (AI) that builds algorithms and models to allow computers to learn from data.
This knowledge is then used to make predictions or informed decisions without being explicitly programmed for each task. Patterns, trends, and relationships within large datasets also enable these models to improve continuously, making for a more efficient, accurate tool.
Data
Data is the information collected by ML models to be used in algorithms. In this instance, Most Loved Workplace® gathered employee feedback through quantitative and qualitative surveys to understand their sentiments and emotions toward where they work.
This data is then used to train and refine the ML model, allowing it to make accurate predictions and provide insights on how to improve the organization’s work culture, employee engagement, and more.
Combining ML and data, Most Loved Workplace® can delve much deeper into employee experiences to tailor strategies for a more positive and productive work environment.
The Importance of Emotional Connectedness
With our help, many organizations can recognize that their employees play a vital role in achieving long-term, ethical success. Emotional connectedness must be nurtured to keep employees engaged, motivated, and productive.
It is worth noting that the need for emotional connectedness is only growing, with the COVID-19 pandemic being one of the biggest catalysts to burnout and decreased productivity in the workplace.
Feeling connected to where you work can lead to:
A sense of belonging: Emotionally connected employees develop a strong sense of belonging as they are part of a supportive and collaborative team. This improves job satisfaction, retention rates, and overall well-being. Positive relationships: Emotional connectedness encourages positive relationships among employees, no matter the department or hierarchy. These relationships enable a streamlined workflow and a harmonious work environment. Improved mental health: Through emotional connectedness, employees have an emotional support system and a sense of understanding from colleagues and leaders. This safety net reduces stress, anxiety, and other mental health issues. Increased productivity: Happy, emotionally connected employees are more motivated and productive. With more mental energy and creativity to put into work, employees can increase their productivity and overall performance. Strengthened company culture: The prior benefits listed are key ingredients to a strong company culture with a shared commitment and motivation to achieving the organization’s goals.
Most Loved Workplace® developed the Love of Workplace Index (LOWI) Pulse Validation to gauge emotional connectedness. This survey-based tool consisted of 28 questions covering five areas, allowing employees to rate their sentiments using a scale from one to five.
Using Custom-Built Models for Employee Insights
Manually extracting valuable insights can be challenging and time-consuming despite how useful qualitative data is. To address this, Most Loved Workplace® turned to ML.
Traditional Natural Language Processing (NLP) models offer high-level analysis but cannot simultaneously analyze multiple angles of qualitative employee feedback.
So, Most Loved Workplace® built a custom BERT (Bidirectional Encoder Representations from Transformers) model that allows for more accurate and personalized feedback by focusing on the following:
Sentiment: This is the overall feeling expressed by employees in their feedback towards the organization as a whole or in regards to specific aspects of the workplace. It helps to understand whether the feedback is positive, neutral, or negative. Emotion: Analyzing emotions such as gratitude, annoyance, and optimism provides deeper insight into employees’ experiences and helps companies see the emotional impact of their practices and policies. Topic: This concerns the overall trends or subjects discussed in the employee feedback. Categorizing by topic helps organizations find key areas that are the most significant to employees and thus need attention first. Theme: Similarly to the topic, the theme is the specific strengths and weaknesses mentioned most by employees. The theme tends to be more specific than the topic and helps companies pinpoint niche areas that need attention.
Gaining Insights from Qualitative Data
For deeper insights, employees were also asked to respond to qualitative statements which showed the main reasons why they loved working for their company and gave suggestions for further improvement.
Over 4000 samples of qualitative feedback were analyzed with ML to reveal common themes and create an extensive list of recurring topics, providing a full understanding of the employee experience.
With this qualitative feedback, it is much easier for organizations to identify their strengths as well as areas that need improvement to benefit employees. When input into ML algorithms, outcomes such as employee performance can be predicted, along with other areas that would aid the organization’s success.
Regarding employees, using ML to analyze qualitative feedback allows for personal insights into areas they can focus on in order to grow within the organization, set their goals, and achieve career success.
How Machine Learning Benefits Employees
Providing leaders with in-depth feedback and employee performance data allows for informed decisions that have long-term benefits for everyone.
This includes identifying areas that need improvement and creating a work environment that aligns with employees’ needs and preferences. There are many ways in which ML can facilitate this process.
Personal Employee Guidance
ML algorithms analyze employee feedback and sentiments to provide personalized insights and recommendations. Employees receive tailored feedback on areas where they excel, potential career growth opportunities, and suggestions for performance.
By analyzing large amounts of data covering employees’ preferences, challenges, and aspirations, ML can offer support that they would not have gotten otherwise.
This benefits employees as it helps with tailoring career paths, developing training courses, and evolving personal needs, which enhances job satisfaction and retention rates due to the ability to grow within the company.
Transparent Communication
Data analytics enables organizations to find areas of improvement, particularly when it comes to issues that have arisen due to poor communication.
Management can create transparent and inclusive communication channels by using insights from employee feedback. Employees are encouraged to voice their opinions and concerns, knowing what they have to say will be thoroughly analyzed and considered.
This fosters a company culture that values open communication where every employee feels empowered and comfortable to contribute to the success.
Proactive Problem Solving
It is always best to prevent an issue rather than deal with the repercussions. With ML, organizations can predict employees’ commitment, performance, and willingness to go beyond the call of duty to benefit the company.
This predictive ability enables potential issues to be proactively addressed to create a more positive and supportive work environment.
Work-Life Balance
Data analysis can shed light on employees’ work-life balance and potential burnout risks. This allows for measures that support employees in maintaining a healthy balance between work and personal life to be implemented, promoting well-being and reduced stress.
How Machine Learning Benefits Employers
As well as benefiting employees, ML, and data processing offer several advantages to employers, empowering them to create a thriving work environment and drive organizational success.
Employee Management
Through ML, employers can see those within their workforce that have a lot of potential, are experiencing issues, or would be better suited in another department. This makes managing and developing employees much more straightforward and decreases the chance of error and upset.
Increased Retention
Because employees are being listened to and are seeing active improvements as per their feedback, they will feel valued. This makes them want to stay in the organization and continue to perform to the best of their abilities.
High employee retention is a huge benefit for employers as they won’t have to worry about regularly sourcing and training new staff. In addition, having a high staff turnover does no favors to an organization’s reputation and can damage its image with potential employees and stakeholders.
Supported Decision-Making
ML enables employers to make data-driven decisions that give great odds, especially in risky situations.
Using insights from employee feedback and performance data, employers can install initiatives that align with the organization’s goals and values, leading to more successful outcomes and employees who trust their leaders.
Continuous Improvement
Finally, employers can continuously assess and improve their workplace culture and practices using ML and data analysis.
Regularly gathering data and analyzing feedback allows leaders to adapt to changing employee needs and preferences and, in some instances, keep them one step ahead.
Questions to Ask Before Applying Machine Learning and Data
Before using ML and data to create a Most Loved Workplace®, it is crucial to carry out some introspection and ask difficult questions that your organization may not be prepared to have the answers to yet.
The integration of these advanced AI technologies can revolutionize many aspects of a company, from employee engagement and productivity to decision-making and overall success.
However, to harness their full potential and ensure everything goes smoothly, businesses must carefully consider the impact it will have on their company structure and workforce.
Asking the right, difficult questions allows them to get into the complexities of ML and data utilization; it will be easier to optimize the process and use data-driven insights to power a healthier, happier, and more efficient workplace.
What are your goals?
The first thing to do is define the goals that ML and data integration should achieve when introduced into the organization. Determine the specific areas where data analysis and ML can provide valuable insights and improvements.
How will the data be collected?
Next, carefully consider how the data will be collected – many privacy regulations must be considered. Collected data must be securely stored, which can be done in databases, cloud storage solutions, or data warehouses for larger companies.
What about data quality assurance?
There is no point in collecting and securely storing data that will not provide you with what you need. The data must be high-quality and reliable, achieved by removing errors, inconsistencies, or irrelevant information that affect conclusions drawn from the feedback and every step that takes place because of it.
Can pre-existing systems be integrated?
To ensure ML and data aren’t doing more harm than good, it is crucial that it can be integrated into current software and applications before any more steps are taken. This could involve working with IT teams to ensure that everything is compatible and won’t cause any technical issues.
The Future of Machine Learning and Data in the Workplace
The future of ML and data in the workplace is promising and, from experience, holds a lot of potential for transforming how organizations of all sizes operate and ensure happy employees. Here are some key aspects that highlight the future of ML and data in the workplace:
AI-powered HR: AI-driven HR platforms will likely revolutionize hiring practices, employee engagement, and performance management. Advanced algorithms will also have the required data to match candidates to the right roles based on their strengths, weaknesses, and preferences.
Real-time feedback: ML will enable real-time analysis of employee feedback, enabling organizations to respond quickly to concerns and provide recognition for achievements. This will create a work environment that values continuous feedback and incentives, driving employee morale and motivation.
Ethical challenges: As ML and data become more involved in workplace operations, companies will need to face the ethical challenges that come with it. Ensuring the responsible use of employee data, maintaining data privacy, and addressing AI biases will be vital to building trust and maintaining a positive work culture and reputation.
Final Thoughts
It’s about time that companies really listened to their employees through personalized qualitative data from employees. The combination of ML and data analytics helps create a Most Loved Workplace® for many reasons.
If it weren’t for the in-depth, valuable insights from employees, then organizations wouldn’t have the ability to make performance predictions, be proactive with problem-solving, and make changes in the workplace that actually matter.
So, take heed of our whitepaper and leverage advanced technologies to gain a deeper understanding of your employees and watch as they become more engaged, productive, and proud to be a member of a Most Loved Workplace® – all thanks to machine learning and data.
| 2023-08-16T00:00:00 |
2023/08/16
|
https://mostlovedworkplace.com/how-machine-learning-and-data-are-at-the-heart-of-most-loved-workplaces/
|
[
{
"date": "2023/01/01",
"position": 13,
"query": "machine learning workforce"
},
{
"date": "2023/02/01",
"position": 13,
"query": "machine learning workforce"
},
{
"date": "2023/08/01",
"position": 12,
"query": "machine learning workforce"
},
{
"date": "2023/09/01",
"position": 15,
"query": "machine learning workforce"
},
{
"date": "2023/10/01",
"position": 15,
"query": "machine learning workforce"
},
{
"date": "2024/03/01",
"position": 15,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 13,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 14,
"query": "machine learning workforce"
},
{
"date": "2024/10/01",
"position": 11,
"query": "machine learning workforce"
},
{
"date": "2024/12/01",
"position": 13,
"query": "machine learning workforce"
},
{
"date": "2025/01/01",
"position": 12,
"query": "machine learning workforce"
},
{
"date": "2025/02/01",
"position": 19,
"query": "machine learning workforce"
},
{
"date": "2025/03/01",
"position": 13,
"query": "machine learning workforce"
},
{
"date": "2025/04/01",
"position": 13,
"query": "machine learning workforce"
}
] |
launch your career in ai & machine learning - WorkForce Institute
|
ML Online Course with Paid Internship Guarantee
|
https://workforceinstitute.io
|
[] |
Become a Certified AI & Machine Learning Professional with our 18-week Immersive Program. Live, online classes with expert instructors. 15-Day Tuition ...
|
Module 1: Introduction to Python & Its Libraries Many AI and ML processes today depend on Python, a programming language used by developers to create automated solutions. Students grow familiar with Python as a general-purpose code. They’ll also learn how to identify and navigate Python libraries — and use the modules inside — to source code that can expedite complicated, code-dependent projects.
Module 2: Introduction to Machine Learning Students learn to collect, examine and learn from data — all through a machine learning lens. This module teaches you how to refine raw data and arrive at actional conclusions, while evaluating how well your machine learning algorithms perform. You’ll also learn how to optimize active machine learning algorithms, to create even more effective data mining results.
Module 3: First Models & Tests This hands-on module sees students create their first AI models, and test those models against real industry benchmarks to determine their effectiveness.
Module 4: Common Machine Learning Models Students grow familiar with the most familiar machine learning models in this module. You’ll learn how to identify the machine learning model, or models, that best address a particular challenge you face. You’ll also learn how to use supervised, unsupervised and reinforcement learning algorithms to achieve specific results.
Module 5: Neural Networks This two-part module immerses students in neural networks — computer systems meant to process data similarly to the human brain. You’ll learn the characteristics that separate a standard system from a neural network, and how you can begin creating a neural network for use in a business environment.
Module 6: Natural Language Processing Engineers and developers use Natural Language Processing (NLP) to create systems dependent on human speech patterns. In this module, you’ll learn how to integrate NLP best practices to create systems that can process, and respond, to human language input.
Module 7: AWS & SQL for Machine Learning Students learn the role that both AWS and SQL play in successful machine learning. You’ll identify how to integrate AI and ML features in cloud providers like AWS, and how to run Python and other code-based scripts in SQL servers
Module 8: Designing & Implementing an Azure AI Solution In this module, students learn how to create and deploy AI solutions for business applications. You’ll learn to work alongside solutions architects to create end-to-end Azure AI solutions. After growing familiar with coding languages earlier in this program, you’ll now learn how to design solutions that integrate concepts like NLP and data science.
| 2023-01-01T00:00:00 |
https://workforceinstitute.io/ai-machine-learning/
|
[
{
"date": "2023/01/01",
"position": 18,
"query": "machine learning workforce"
},
{
"date": "2023/02/01",
"position": 17,
"query": "machine learning workforce"
},
{
"date": "2023/08/01",
"position": 14,
"query": "machine learning workforce"
},
{
"date": "2023/09/01",
"position": 21,
"query": "machine learning workforce"
},
{
"date": "2023/10/01",
"position": 21,
"query": "machine learning workforce"
},
{
"date": "2024/03/01",
"position": 21,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 17,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 17,
"query": "machine learning workforce"
},
{
"date": "2024/10/01",
"position": 17,
"query": "machine learning workforce"
},
{
"date": "2024/12/01",
"position": 17,
"query": "machine learning workforce"
},
{
"date": "2025/01/01",
"position": 15,
"query": "machine learning workforce"
}
] |
|
Supercharging America's AI Workforce | Department of Energy
|
Supercharging America's AI Workforce
|
https://www.energy.gov
|
[] |
This web portal highlights a non-exhaustive collection of DOE and NSF AI education, training, and workforce opportunities.
|
An artificial intelligence (AI)-ready workforce is essential for the United States to fully realize AI’s potential to advance scientific discovery, economic prosperity, and national security. DOE has been preparing future scientists to be AI research leaders by leveraging decades of sustained R&D investments in high-performance computing (HPC) that have led to significant advances in both fundamental studies and world-leading supercomputing tools. By planting the seeds of curiosity through discovery learning, over the decades, DOE national laboratories have introduced basic AI concepts and skills to hundreds of thousands of students and educators at all levels. Training programs at DOE national laboratories deliver opportunities for best-in-class hands-on research experiences, including through access to leading AI research expertise, world-class supercomputing facilities, and a science-driven approach. These training opportunities complement AI education and training offered through other pathways, such as AI education and training supported by both DOE and NSF at institutions of higher education and various other settings for learning.
| 2023-01-01T00:00:00 |
https://www.energy.gov/cet/supercharging-americas-ai-workforce
|
[
{
"date": "2023/01/01",
"position": 20,
"query": "machine learning workforce"
},
{
"date": "2023/02/01",
"position": 25,
"query": "machine learning workforce"
},
{
"date": "2023/08/01",
"position": 96,
"query": "government AI workforce policy"
},
{
"date": "2023/08/01",
"position": 18,
"query": "machine learning workforce"
},
{
"date": "2023/09/01",
"position": 20,
"query": "machine learning workforce"
},
{
"date": "2023/10/01",
"position": 20,
"query": "machine learning workforce"
},
{
"date": "2024/01/01",
"position": 90,
"query": "government AI workforce policy"
},
{
"date": "2024/02/27",
"position": 2,
"query": "government AI workforce policy"
},
{
"date": "2024/02/27",
"position": 5,
"query": "machine learning workforce"
},
{
"date": "2024/03/01",
"position": 20,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 20,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 21,
"query": "machine learning workforce"
},
{
"date": "2024/07/01",
"position": 92,
"query": "government AI workforce policy"
},
{
"date": "2024/08/01",
"position": 89,
"query": "government AI workforce policy"
},
{
"date": "2024/10/01",
"position": 19,
"query": "machine learning workforce"
},
{
"date": "2024/12/01",
"position": 40,
"query": "government AI workforce policy"
},
{
"date": "2024/12/01",
"position": 20,
"query": "machine learning workforce"
},
{
"date": "2025/01/01",
"position": 19,
"query": "machine learning workforce"
},
{
"date": "2025/02/01",
"position": 16,
"query": "machine learning workforce"
},
{
"date": "2025/03/01",
"position": 19,
"query": "machine learning workforce"
},
{
"date": "2025/04/01",
"position": 20,
"query": "machine learning workforce"
},
{
"date": "2025/06/01",
"position": 70,
"query": "government AI workforce policy"
}
] |
|
Machine Learning and Workforce Planning with Legion AI
|
Machine Learning and Workforce Planning with Legion AI
|
https://legion.co
|
[
"Naman Gupta",
".Wp-Block-Co-Authors-Plus-Coauthors.Is-Layout-Flow",
"Class",
"Wp-Block-Co-Authors-Plus",
"Display Inline",
".Wp-Block-Co-Authors-Plus-Avatar",
"Where Img",
"Height Auto Max-Width",
"Vertical-Align Bottom",
".Wp-Block-Co-Authors-Plus-Coauthors.Is-Layout-Flow .Wp-Block-Co-Authors-Plus-Avatar"
] |
Discover how Legion AI uses machine learning to boost forecast accuracy, reduce labor costs, and align staffing with real-time business demand.
|
Workforce planning has undergone a profound transformation. What was once driven by static spreadsheets and reactive staffing decisions has evolved into a strategic capability essential for navigating today’s complex and fast-paced business environment. Forward-thinking organizations recognize that traditional approaches can no longer keep up with market volatility, rising customer expectations, and the need for real-time operational agility.
Despite this shift, many companies still rely on outdated forecasting methods that fail to reflect the dynamic nature of demand. The consequences are all too familiar: under- or overstaffed shifts, missed revenue targets, overburdened teams—and at the core of it all, inaccurate labor forecasting.
Imagine walking into a bustling store on a Saturday afternoon, only to find your frontline workforce stretched thin. Not because talent wasn’t available, but because outdated forecasting missed the mark. These blind spots don’t just disrupt operations; they affect the bottom line, degrade customer satisfaction, and erode employee engagement.
In this blog post, we’ll explore how Legion AI is leveraging machine learning to enable businesses to predict labor demand with greater accuracy and how that capability directly contributes to improved operational efficiency, workforce alignment, and revenue growth.
Machine learning is a subset of AI that uses algorithms to enable computers to learn from and make predictions or decisions based on data.
The Evolution of Forecasting in Workforce Planning
Forecasting has long played a critical role in workforce planning, helping businesses align labor with expected demand. However, as operational complexity increases and the pace of change accelerates, forecasting based solely on historical trends often struggles to keep up. Today’s organizations require forecasting that reflects past patterns and adapts in real time to shifting demand drivers and external conditions.
Legion’s forecasting engine is built specifically for this modern labor environment. It doesn’t just predict based on past behaviors; it continuously learns and adjusts by integrating a wide range of data inputs, including weather, local events, sales promotions, and even custom events unique to the business. This allows Legion to anticipate demand shifts with greater accuracy and context.
The core of Legion’s forecasting engine is built on advanced machine learning, layered with a proprietary AI infrastructure that processes vast volumes of operational data. Legion generates highly tailored forecasts for each location, customer, and demand driver, such as foot traffic and transaction volume. On top of these primary drivers, Legion also accounts for store-specific variables such as events, promotions, and location-specific factors like weather and local events. The result is a smarter, more responsive approach to labor planning that evolves with the business and delivers actionable insights that drive both cost efficiency and service excellence.
Make Accurate Decisions with Legion Demand Forecasting
Legacy workforce solutions often force businesses to compromise, offering fragmented capabilities instead of a comprehensive approach. It’s time to move beyond outdated systems and embrace a solution that delivers smarter, faster, and more adaptive workforce planning. Here’s how:
Integrated External Events
Legion’s system processes various external data sources, such as weather forecasts, economic conditions, community events, and internal events like sales volume and staffing trends. Legion AI evaluates how these factors have historically influenced demand, identifies patterns, and applies this learning to future projections. As a result, forecasts reflect not only past behavior, but also the real-time impact of what’s happening now and what’s coming next.
Adaptive Training and Retraining
A key differentiator for Legion is the adaptive nature of its forecasting process. Models are retrained weekly using the latest available data, allowing the system to respond quickly to emerging trends or disruptions. If a protest, sports event, or sudden weather shift is expected to affect demand, Legion AI automatically factors it in. Additionally, the system provides smart forecast boundaries—upper and lower ranges—so operations teams can plan with full visibility into potential best- and worst-case labor needs.
Intelligent Automation
Legion’s forecasting doesn’t end with prediction, it powers intelligent automation across workforce planning. Forecasts feed directly into labor plans and schedules, eliminating manual guesswork. With demand predicted at 15-minute, 30-minute, or daily intervals, managers gain precise control over labor allocation. This level of granularity ensures that staffing is not only aligned to customer traffic but also optimized for cost efficiency, compliance, and employee satisfaction.
Measurable Impact
Forecasting accuracy isn’t just a technical advantage—it delivers real financial results. According to a study by Forrester, a 1% improvement in forecast accuracy can reduce labor costs by 0.5% and increase sales conversion by up to 0.25%. At scale, this level of precision translates to substantial gains in profitability and operational efficiency. The link between accurate forecasting and business performance is both clear and measurable.
Transparency
Most forecasting tools function as black boxes, offering little to no insight into what’s driving projections. Legion solves this through built-in transparency. Features like event attribution clearly show which external or internal factors influence demand. If a forecasted spike is tied to a nearby event or weather system, managers see that information directly, enabling them to act confidently and explain decisions when needed.
Forecast Intervals
Instead of presenting a single rigid forecast, Legion provides predictive ranges for each projection. By offering upper and lower bounds, the platform gives managers a statistically reliable window for labor planning. This is especially valuable in volatile conditions, where flexibility is more practical than pinpoint certainty. Leaders can better balance risk, cost, and service expectations with this approach.
What Makes Legion AI’s Forecasting So Unique?
Forecasting isn’t just about prediction—it’s about adaptability, scale, strategy, and people. Legion AI stands out by approaching labor forecasting with real-world complexity in mind, delivering accurate, dynamic insights that power better decisions across every level of the organization.
Value Human Inputs and Feedback
Legion’s AI is designed to navigate real-world unpredictability. It incorporates robust feedback mechanisms that allow users to adjust forecasts when human insight is needed— like unexpected store closures or a local disruption. These manual interventions are not ignored; they’re incorporated into Legion’s learning loop, helping the model learn from each real-world correction. This creates a collaborative relationship between AI and human expertise, blending automation with on-the-ground intelligence for smarter, more refined forecasting over time.
Built for Scale
Legion’s forecasting engine is designed to scale effortlessly. Whether a company has ten locations or ten thousand, the AI infrastructure supports high-volume, distributed forecasting without compromising performance. The system doesn’t just scale technically, it learns the unique operational rhythms of each location and adapts its models accordingly. Legion is ideal for enterprises operating across diverse geographies, business models, and customer patterns.
Short & Long Range Forecasting
Legion doesn’t just focus on short-term scheduling. Its forecasting engine supports both immediate planning and long-term strategic analysis. Businesses can model various ‘what-if’ scenarios to evaluate the labor impact of upcoming marketing campaigns, new store openings, or regional events. Legion’s ability to support scenario planning at scale gives organizations a powerful advantage in navigating uncertainty and planning for growth.
Continuous Accuracy Monitoring
Legion doesn’t leave accuracy to chance. The platform continuously measures and benchmarks forecasting performance using a weighted accuracy model tailored to the specific dynamics of each dataset. If performance degrades or new data patterns emerge, Legion automatically retrains its models to preserve precision and reliability. This approach ensures forecasts remain aligned with real-time business conditions, without manual intervention.
Designed & Built for People
Legion’s forecasting engine is built with both the business and the workforce in mind. Forecasts integrate directly into schedule automation and employee self-service tools, ensuring optimized planning that delivers real value to the frontline. Employees benefit from more predictable schedules, better alignment with their preferences, and fairer shift assignments, leading to higher engagement and lower attrition. Smarter forecasting isn’t just a business win—it’s a workforce win.
Legion’s Demand Forecasting stands apart as a true enabler of operational agility. It brings together the power of artificial intelligence, real-time data, and human expertise to create forecasts that are not only accurate but meaningful and that translate directly into better business outcomes.
Every Week With Legion AI 1.2M shifts automatically generated
1.7M optimizations performed
300K models trained
1.6B data points forecasted
Win-Win for Both the Business and Employees
Legion’s forecasting capabilities deliver strategic value to the business. By ensuring that labor deployment is consistently aligned with real-world demand, companies can avoid the high costs of overstaffing, reduce the chaos of reactive scheduling, and build more predictable operating models. The benefits for employees are equally clear: smarter staffing leads to more consistent schedules, fewer last-minute changes, and higher engagement. Customers see the impact with faster service, better coverage, and improved brand experience.
As organizations face continued uncertainty, tighter margins, and higher expectations from both employees and customers, demand forecasting can no longer be an afterthought. It must be a strategic function—automated, intelligent, and deeply embedded into how labor is planned, deployed, and managed.
Take Our Demand Forecasting Accuracy Challenge
Ready to compare our forecast accuracy to your existing solution and against predictability scores?
Let us prove what we can deliver for your company by taking our Demand Forecasting Accuracy Challenge.
| 2025-06-26T00:00:00 |
2025/06/26
|
https://legion.co/blog/2025/06/26/machine-learning-workforce-planning/
|
[
{
"date": "2023/01/01",
"position": 21,
"query": "machine learning workforce"
},
{
"date": "2023/02/01",
"position": 20,
"query": "machine learning workforce"
},
{
"date": "2023/08/01",
"position": 13,
"query": "machine learning workforce"
},
{
"date": "2023/09/01",
"position": 29,
"query": "machine learning workforce"
},
{
"date": "2023/10/01",
"position": 30,
"query": "machine learning workforce"
},
{
"date": "2024/03/01",
"position": 29,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 21,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 20,
"query": "machine learning workforce"
},
{
"date": "2024/10/01",
"position": 18,
"query": "machine learning workforce"
},
{
"date": "2025/06/26",
"position": 21,
"query": "machine learning workforce"
},
{
"date": "2025/01/01",
"position": 14,
"query": "machine learning workforce"
}
] |
Machine Learning in Workforce Development Research: Lessons ...
|
Machine Learning in Workforce Development Research: Lessons and Opportunities Issue Brief
|
https://www.dol.gov
|
[] |
The brief summarizes lessons learned from using machine learning to study the implementation of career pathways programs. First, this brief describes the ...
|
About the Brief
Download Brief
The brief summarizes lessons learned from using machine learning to study the implementation of career pathways programs. First, this brief describes the research questions that guided the study and summarizes the machine learning methods designed for the data collection and analysis activities, including study limitations and challenges encountered. It then provides lessons learned on using machine learning methods for social science research. Finally, the brief discusses strategies for using these methods in future workforce development projects and other areas, particularly federally funded efforts.
Download this Summary (PDF)
Key Takeaways
Machine learning can be a powerful tool in the right context.
Machine learning involves some risk and users should be cognizant of the limitations and expected results of this approach.
Machine learning may struggle to replicate the detail or nuance of human research in the context of implementation research.
Machine learning may require human researchers to dedicate substantial time and resources to define key concepts.
Machine learning may require substantial input from human researchers.
Machine learning may require a team with interdisciplinary skill sets to be completed successfully.
Machine learning operates in an evolving legal, computing, and cost environment.
Citation
De La Rosa, S. M., Greenstein, N., Schwartz, D., Lloyd, C. (2021). Abt Associates. Machine Learning in Workforce Development Research: Lessons and Opportunities. Chief Evaluation Office, U.S. Department of Labor.
Download Brief View Study Profile
The Department of Labor’s (DOL) Chief Evaluation Office (CEO) sponsors independent evaluations and research, primarily conducted by external, third-party contractors in accordance with the Department of Labor Evaluation Policy and CEO’s research development process.
| 2023-01-01T00:00:00 |
https://www.dol.gov/resource-library/machine-learning-workforce-development-research-lessons-and-opportunities-issue
|
[
{
"date": "2023/01/01",
"position": 22,
"query": "machine learning workforce"
},
{
"date": "2023/02/01",
"position": 34,
"query": "machine learning workforce"
},
{
"date": "2023/08/01",
"position": 28,
"query": "machine learning workforce"
},
{
"date": "2023/09/01",
"position": 31,
"query": "machine learning workforce"
},
{
"date": "2023/10/01",
"position": 22,
"query": "machine learning workforce"
},
{
"date": "2024/03/01",
"position": 31,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 28,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 29,
"query": "machine learning workforce"
},
{
"date": "2024/10/01",
"position": 21,
"query": "machine learning workforce"
},
{
"date": "2024/12/01",
"position": 22,
"query": "machine learning workforce"
},
{
"date": "2025/01/01",
"position": 28,
"query": "machine learning workforce"
},
{
"date": "2025/02/01",
"position": 25,
"query": "machine learning workforce"
},
{
"date": "2025/03/01",
"position": 28,
"query": "machine learning workforce"
},
{
"date": "2025/04/01",
"position": 28,
"query": "machine learning workforce"
}
] |
|
Machine Learning Enables Employers to Gain More Insights on Skills
|
Machine Learning Enables Employers to Gain More Insights on Skills
|
https://blog.workday.com
|
[] |
Machine learning and AI allow us to use raw skills data in a wide variety of ways to support talent and business decisions.
|
We then ran that same data through an algorithm that looked at sentiment within the comments. The output was incredibly dense and rich with insights. For instance, we could see specific stressors—such as manager relationships, working conditions, and family responsibilities—by gender, race, job, or geographic location.
This proved to us that AI is better than humans at analyzing feedback data to help us take action as organizational leaders.
Just like in the experiment above, there are other areas where rich data sets exist within the business that haven't been mined for insights. We’ll explore some of the areas where AI can suggest actions, offer insights, and create value for employers who leverage technology to examine one of their richest, untapped data sources: employee skills.
Skills and the Spatial Relationship
Understanding the spatial representation of skills provides a clear picture of how closely skills are related to one another, as well as to those entities represented with skills (jobs, for example). This enables us to determine a more optimal path toward a target result—in this case matching workers or candidates to jobs, content, learning, mentors, and so on; and vice versa, matching jobs to candidates, learning to workers, and more.
Let’s use a basic example to explore the concept. In a marketing job, these might be relevant skills:
Writing
Research
Analysis
However, in a software engineering job, these skills may apply:
Coding
Collaboration
Analysis
In each of these two jobs, there’s a need for analysis of outputs, but otherwise, the skills don’t overlap heavily. That means the relationship between coding and writing skills (while both of them actually mean sitting and typing at a computer) is relatively far apart spatially. However, within each job, the skills have a much closer relationship. It helps to think about jobs not as discrete and distinct entities, but as clusters of skills.
Now, when you expand this very basic explanation across the thousands of possible skills across the millions of jobs people do, you start to see how the challenge of identifying and relating this universe of skills is something that is well-suited for an algorithm to support.
| 2022-01-07T00:00:00 |
2022/01/07
|
https://blog.workday.com/en-us/machine-learning-enables-employers-gain-more-insights-skills.html
|
[
{
"date": "2023/01/01",
"position": 26,
"query": "machine learning workforce"
},
{
"date": "2023/02/01",
"position": 30,
"query": "machine learning workforce"
},
{
"date": "2023/08/01",
"position": 27,
"query": "machine learning workforce"
},
{
"date": "2023/09/01",
"position": 25,
"query": "machine learning workforce"
},
{
"date": "2023/10/01",
"position": 26,
"query": "machine learning workforce"
},
{
"date": "2024/03/01",
"position": 25,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 25,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 25,
"query": "machine learning workforce"
},
{
"date": "2024/10/01",
"position": 25,
"query": "machine learning workforce"
},
{
"date": "2024/12/01",
"position": 26,
"query": "machine learning workforce"
},
{
"date": "2025/01/01",
"position": 27,
"query": "machine learning workforce"
},
{
"date": "2025/02/01",
"position": 27,
"query": "machine learning workforce"
},
{
"date": "2025/03/01",
"position": 26,
"query": "machine learning workforce"
},
{
"date": "2025/04/01",
"position": 26,
"query": "machine learning workforce"
}
] |
Building the AI-ready workforce: Challenges and opportunities
|
Building the AI-ready workforce: Challenges and opportunities
|
https://www.aiacceleratorinstitute.com
|
[
"Dr. Hemachandran K",
"Dr. Raul V. Rodriguez",
"Ai Accelerator Institute"
] |
We will explore the difficulties in developing a workforce that is AI-ready and the approaches that can assist businesses in overcoming these obstacles.
|
Artificial intelligence (AI) is no longer the stuff of science fiction; it is already firmly established at the core of industries, changing how businesses function, make decisions, and provide value to customers.
AI continues to impact industries across the board, from manufacturing and retail to healthcare and finance. But with such quick technical development comes the urgent need for an AI-ready workforce that can fully use these developments.
The difficulties and opportunities that various businesses confront as they train their workforce for the AI future are explored in this article. The need for knowledgeable AI specialists is growing rapidly as AI is more and more incorporated into everyday activities.
However, there is a severe skills shortage, and many workers are unprepared for the adjustments AI will surely make to their job functions. In this context, we will explore the difficulties in developing a workforce that is AI-ready and the approaches that can assist businesses in overcoming these obstacles.
The article also emphasizes the positive aspects of this AI revolution, focusing on the benefits that sectors might realize from developing a workforce that is equipped to make use of AI's capabilities.
It also analyzes how government regulations have shaped the environment of the AI workforce and provides information on upcoming developments in AI workforce development. This article serves as a compass to navigate the always-changing terrain of AI-driven workplaces in a world where AI's effect on sectors is expected to increase.
The AI revolution in industries
Artificial intelligence has quickly transformed from a specialized field of technology to a pervasive force that is upending entire sectors of the global economy.
Smart algorithms, machine learning, and data-driven decision-making have been included in the fundamental business processes as part of this AI revolution. Industries that formerly depended on conventional techniques are now undergoing a fundamental transition as they use AI to obtain a competitive advantage and solve difficult problems.
Through predictive analytics, early illness identification, and improved medication discovery, artificial intelligence (AI) in healthcare is increasing patient care. In the world of finance, this entails automating repetitive procedures, identifying fraudulent activity, and improving investment methods.
Smart factories are becoming more common in manufacturing, as AI-powered robots and systems improve production efficiency and quality control. AI is used in retail to make customized product suggestions and manage inventories, while AI-enabled precision farming methods assist agriculture.
These illustrations just begin to scrape the surface of AI's impact. Although AI is not a panacea, it does have the potential to improve productivity, accuracy, and creativity.
It enables enterprises to extract insights from enormous databases, automate tedious operations, and develop totally new business models. Industries need to adapt and change as AI's influence spreads in order to compete in this changing environment. To manage the difficulties and take advantage of the enormous potential given by the AI revolution, it is crucial to develop a workforce that comprehends, values, and uses AI.
The need for an AI-ready workforce
An AI-ready workforce is more important than ever in the age of AI. A traditional skill set is no longer adequate to succeed in the modern workplace as firms integrate AI technology into their operations, goods, and services.
This section explores the persuasive arguments for why it is crucial for businesses to have an AI-ready workforce.
A. The pervasiveness of AI
AI across industries: AI is no longer just used in tech-related industries. From healthcare and banking to education and transportation, it has impacted almost every sector of the economy and profoundly altered how work is done.
Automating routine tasks: Artificial intelligence (AI) may automate tedious and routine processes, freeing up human workers to concentrate on more innovative and value-added jobs.
B. Competitive advantage and innovation
Staying competitive: By increasing productivity, cutting costs, and offering cutting-edge goods and services that fit changing consumer expectations, businesses that use AI gain a competitive edge.
Adaptation to market dynamics: An AI-ready workforce is essential for firms to be able to pivot, expand, and stay relevant as market dynamics change quickly.
C. Skill gap and job evolution
Emerging job roles: As a result of the AI revolution, new professions like data scientists, machine learning engineers, and AI ethics specialists are emerging that call for expertise in AI.
Reskilling: As AI improves human skills, current work positions are shifting. To work effectively with AI technologies, employees must develop new abilities.
D. Maximizing AI's potential
Unlocking AI's full potential: When a company's staff knows how to utilize AI tools, comprehend insights produced by AI, and make data-driven choices, it can fully realize the potential of AI.
Minimizing resistance: An AI-ready workforce lowers opposition to AI adoption, creating an innovative and ever-improving culture within enterprises.
As a result of AI's pervasiveness, its revolutionary potential, and the necessity for sectors to remain competitive and adaptive in a quickly changing environment, there is a clear need for an AI-ready workforce. The difficulties and methods involved in creating such a workforce will be covered in the sections that follow.
Challenges in preparing an AI-ready workforce
Although there is an evident need for a workforce that is AI-ready, businesses, and sectors face significant obstacles as they set out on this transformational journey. To properly prepare the workforce for the AI future, it is crucial to recognize and solve these difficulties.
A. Shortage of AI talent
Skills gap: The abilities needed for jobs using AI and those that are already accessible in the workforce are significantly different. Finding people with the appropriate knowledge is a significant challenge.
Competition for talent: The tight rivalry among businesses to recruit and keep talent as a result of the high demand for AI specialists has raised compensation expectations.
B. Resistance to change and fear of job displacement
Employee apprehension: Many workers worry that the introduction of AI might result in job loss. This apprehension may make people reluctant to learn new AI-related technology and abilities.
Cultural shift: It might be challenging to change an organization's culture so that it accepts AI and continuous learning.
C. Budget constraints and resource limitations
Cost of training: It might be expensive to invest in AI education and training programs. Allocating resources for this reason may be particularly difficult for small and medium-sized businesses (SMEs).
Infrastructure and technology: A large infrastructure and resource commitment is needed to implement AI tools and technologies, which may not be realistic for many enterprises.
D. Ethical and privacy concerns
Bias and fairness: A complicated task, ensuring fairness and objectivity in AI systems needs care to avoid discriminating outcomes.
Data privacy: Massive volumes of data handling generate privacy and security issues, needing strict regulations and procedures.
Regulatory compliance: Organizations must negotiate the problem of adhering to ethical norms and laws governing AI that are constantly changing.
A complex strategy, including strategic planning, spending on education and training, encouraging a culture of adaption, and proactive engagement with ethical and privacy issues, is needed to address these difficulties.
To fully utilize AI technology and keep their competitive edge, industries must continue to be dedicated to developing an AI-ready workforce in the face of these challenges. The ways to meet these issues will be covered in the section that follows.
Strategies for overcoming challenges
Organizations and sectors must implement proactive measures to handle the significant difficulties of developing an AI-ready workforce:
Investment in education and training: Allocate funds to develop thorough AI education and training programs, both internally and through collaborations with academic institutions, in order to retrain and upskill personnel.
Collaboration between academia and industry: To guarantee that educational curricula are in line with the changing needs of the labor market and produce graduates with pertinent AI capabilities, encourage collaboration between academics and industry.
Cultivate a culture of continuous learning: To make adopting AI less daunting, foster a culture at work that values ongoing learning, experimentation, and adaptability.
Responsible AI practices: Focus on developing AI responsibly by tackling prejudice, protecting data privacy, and abiding by moral and legal requirements.
Organizations may overcome the challenges of developing a workforce that is AI-ready and put themselves in a position to succeed in the AI-driven future by putting these tactics into practice.
Opportunities for industries
A wide range of prospects for development and innovation are presented by the integration of AI into several sectors. A firm may maintain its competitive edge by utilizing an AI-ready workforce to optimize processes, increase productivity, and save expenses.
Additionally, by providing AI-driven goods and services, improving consumer experiences through personalization, and making data-informed strategic choices, organizations might investigate new income streams.
In an AI-driven environment, industries have the opportunity to not only improve on their current business models but also to lead ground-breaking innovations that will eventually change how they conduct business and engage with their customers.
Case Studies
Here we discussed some notable examples of successful AI-ready workforce preparation case studies:
Woxsen University, Hyderabad, India
Woxsen University, a provider of educational services, has made considerable expenditures in developing its workforce's AI expertise. AI Research Centre powered by Brandscapes Worldwide Pvt., Ltd., launched in 2021 offers a variety of AI courses that cover machine learning and natural language processing.
A Center of Excellence and Knowledge Centre has also been formed by Woxsen University, encouraging cooperation among international specialists for information sharing and the promotion of best practices. These initiatives have made it possible for Woxsen University to develop a highly skilled workforce capable of utilizing AI to efficiently handle both academic and business concerns.
Accenture
Accenture, a multinational provider of professional services, has extensively invested in preparing its workers for AI. It introduced an AI Academy in 2020 that provides training in a range of AI subjects, including machine learning and natural language processing.
A Center for AI Excellence has also been established by the business, bringing together specialists from several Accenture divisions to exchange expertise and best practices. Accenture has been able to create a workforce that is well-equipped to employ AI to address business challenges as a consequence of these efforts.
Bank of America
The industry leader in financial services, Bank of America, has likewise committed significantly to preparing its personnel for AI. It declared a goal to train 100,000 employees in AI by 2025 in its 2021 announcement.
The business provides a range of training initiatives, such as online courses, live seminars, and on-the-job training. In order to create new AI-powered goods and services, Bank of America is also making investments in AI research and development.
General Electric
General Electric, a massive industrial company, is transforming its operations with AI. The business has created AI-powered solutions for a range of jobs, including supply chain management, quality assurance, and predictive maintenance. Additionally, GE is training its staff in new capabilities using AI. It opened an AI Academy in 2020 with classes on subjects including data science and machine learning.
Walmart
Walmart, a major retailer, is utilizing AI to enhance both its operations and customer service. The business has created chatbots using AI that can solve problems and respond to client inquiries. Walmart is utilizing AI to streamline its supply chain and enhance inventory control. In order to create new goods and services that are driven by AI, the firm is investing in AI research and development.
UnitedHealth Group
UnitedHealth Group, a major player in the healthcare industry, is employing AI to raise the standard of care it offers. For a range of functions, including predictive analytics, clinical decision support, and patient interaction, the business has created AI-powered products.
Additionally, UnitedHealth Group is training its personnel in new capabilities using AI. It introduced an AI Academy in 2021 that provides training in subjects like machine learning and natural language processing.
These are just a handful of the many companies that are funding worker preparedness for AI. technology is obvious and being able to use AI properly will become more and more crucial as technology continues to develop. These businesses are setting themselves up for success in the AI future by investing in research and development and upskilling their workforce.
The role of government and policy
The evolution of the AI workforce is significantly shaped by government and policy. The aim of policymakers is to foster the development of AI capabilities while preserving ethical and privacy concerns.
Their duties include creating rules that guarantee ethical AI activities, encouraging cooperation between academic institutions and businesses, and offering incentives for businesses to spend money on AI education and training.
Additionally, by giving funds for research and development, supporting programs that close the AI skill gap, and encouraging the diffusion of AI knowledge to guarantee equal access to opportunities in an AI-driven future, governments may help prepare the workforce for AI.
Future trends in AI workforce development
The evolution of the AI workforce is expected to be dynamic and ever-changing in the future. This landscape is anticipated to be shaped by a number of significant trends.
AI-first curriculum: Institutions of higher learning will include AI and data science in core courses, ensuring that graduates have a solid understanding of AI.
AI ethics specialization: Specialized jobs and training programs to handle ethical issues in AI research and deployment will result from an increasing emphasis on AI ethics.
Remote learning and online credentials: AI education will become more widely available as remote learning and digital credentials continue to grow in popularity.
Public-private partnerships: To close the AI skills gap and spur innovation, government, academic, and industrial partnerships will multiply.
Lifelong learning: As professionals constantly upgrade their skills to be relevant in settings improved by AI, lifelong learning will become the norm.
These patterns emphasize the value of flexibility and ongoing education for the AI workforce of the future.
Conclusion
In conclusion, the AI revolution has transformed from a science fiction concept to an unavoidable reality with significant ramifications for global business sectors. It is more important than ever to train a workforce that is AI-ready.
AI presents both potential and difficulties as it continues to enter every part of the business. Although there are many challenges, like a lack of skilled AI workers and ethical issues, there are also many benefits, including increased creativity and competitiveness.
Organizations must make educational investments, encourage cooperation, cultivate a culture of lifelong learning, and give priority to ethical AI practices in order to meet these difficulties. Developing policies that facilitate fair access to AI education and promote responsible AI deployment are major responsibilities of governments.
As we look to the future, the key to success is ensuring that the labor force is capable of utilizing AI's disruptive potential while preserving ethics and creativity. The growth of the AI workforce emphasizes the importance of adaptability and lifelong learning.
The industry may not only flourish but also spearhead ground-breaking technologies that will transform our world in the AI-driven future by adhering to these values and cooperating.
| 2025-02-03T00:00:00 |
2025/02/03
|
https://www.aiacceleratorinstitute.com/building-the-ai-ready-workforce-challenges-and-opportunities-for-industries/
|
[
{
"date": "2023/01/01",
"position": 27,
"query": "machine learning workforce"
},
{
"date": "2023/02/01",
"position": 24,
"query": "machine learning workforce"
},
{
"date": "2023/08/01",
"position": 24,
"query": "machine learning workforce"
},
{
"date": "2023/09/22",
"position": 11,
"query": "AI labor market trends"
},
{
"date": "2023/09/22",
"position": 5,
"query": "AI skills gap"
},
{
"date": "2023/09/22",
"position": 2,
"query": "government AI workforce policy"
},
{
"date": "2023/09/22",
"position": 69,
"query": "machine learning job market"
},
{
"date": "2023/09/01",
"position": 26,
"query": "machine learning workforce"
},
{
"date": "2023/10/01",
"position": 27,
"query": "machine learning workforce"
},
{
"date": "2024/03/01",
"position": 26,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 29,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 27,
"query": "machine learning workforce"
},
{
"date": "2024/10/01",
"position": 27,
"query": "machine learning workforce"
},
{
"date": "2024/12/01",
"position": 29,
"query": "machine learning workforce"
},
{
"date": "2025/01/01",
"position": 24,
"query": "machine learning workforce"
},
{
"date": "2025/02/01",
"position": 18,
"query": "machine learning workforce"
},
{
"date": "2025/03/01",
"position": 100,
"query": "government AI workforce policy"
},
{
"date": "2025/03/01",
"position": 22,
"query": "machine learning workforce"
},
{
"date": "2025/04/01",
"position": 25,
"query": "machine learning workforce"
},
{
"date": "2025/06/01",
"position": 96,
"query": "government AI workforce policy"
}
] |
Artificial Intelligence and Machine Learning Suite - Ed2Go
|
Artificial Intelligence and Machine Learning Suite
|
https://www.ed2go.com
|
[] |
AI and the Workforce; AI Ethics; The Future of AI. Introduction to Machine Learning. Introduction to Machine Learning; Which Problems Can Machine Learning Solve ...
|
Details
The Artificial Intelligence and Machine Learning Suite will prepare you with a practical knowledge foundation of key definitions, applications, processes, techniques, and more, enabling you to sharpen your knowledge and skills in the fields of AI and machine learning.
Introduction to Artificial Intelligence
This course will introduce you to various forms of artificial intelligence (AI) and how we interact with AI as consumers in applications like chatbots and recommendation engines. You will see how AI provides analytics in business and consider industries that may be transformed or even disrupted by AI implementations. Next, you will go under the hood to see how computers can "learn" using artificial neural networks and various forms of machine learning. You will review AI applications such as natural language processing, forecasting, and robotics. You will also learn about the AI development process and how AI will affect the workforce. And lastly, you will consider some of the ethical factors in AI deployment.
Introduction to Machine Learning
Machine learning can be used to solve specific kinds of problems when key considerations in selecting data for a machine learning project are implemented properly. You will learn about specific techniques used in supervised, unsupervised, and semi-supervised learning, which applications each type of machine learning is best suited for, and the type of training data each requires.
You will also be able to differentiate offline and online training and predictions, automated machine learning, and how the cloud environment affects machine learning functions. Finally, you will explore some of the most significant areas in the very active area of machine learning research.
Suite bundles are not eligible for partial drops or refunds. Transfers to other open sessions of the same course are available. Please refer to your school for additional details regarding drops, transfers, and refunds on Suite bundles. Courses should be taken two months apart to avoid overlapping.
| 2023-01-01T00:00:00 |
https://www.ed2go.com/workforce/online-courses/artificial-intelligence-machine-learning-suite/
|
[
{
"date": "2023/01/01",
"position": 52,
"query": "machine learning workforce"
},
{
"date": "2023/02/01",
"position": 54,
"query": "machine learning workforce"
},
{
"date": "2023/09/01",
"position": 51,
"query": "machine learning workforce"
},
{
"date": "2023/10/01",
"position": 52,
"query": "machine learning workforce"
},
{
"date": "2024/03/01",
"position": 51,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 51,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 51,
"query": "machine learning workforce"
},
{
"date": "2024/12/01",
"position": 51,
"query": "machine learning workforce"
},
{
"date": "2025/02/01",
"position": 51,
"query": "machine learning workforce"
},
{
"date": "2025/03/01",
"position": 52,
"query": "machine learning workforce"
},
{
"date": "2025/04/01",
"position": 52,
"query": "machine learning workforce"
}
] |
|
Machine Learning In The Human Resource Space - HR Future
|
Machine Learning In The Human Resource Space
|
https://www.hrfuture.net
|
[] |
... workforce. Below we identify some of the powerful applications of Supervised Machine Learning that can shape the future of your organization, one algorithm ...
|
The vast majority of businesses plan to increase their investments in data, analytics, and AI, yet many will fail to see a strong return on their investment.
Why will many fail? The reasons are countless, including a lack of clear objectives, poor data quality, inadequate technology infrastructure, insufficient talent and experience, integration challenges, resistance to change, and inadequate training.
By leveraging the power of data analytics and machine learning, HR professionals can gain deeper insights into employee behavior, predict future trends, and make evidence-based decisions. This approach enables a more strategic and personalized management style, from optimizing recruitment processes to tailoring employee development programs.
In this article, we explore the multifaceted ways in which data science is revolutionizing the HR domain, offering innovative solutions to traditional challenges and paving the way for a more data-driven, efficient, and employee-centric workplace.
The two main categories of machine learning are supervised and unsupervised learning. Supervised learning is about predicting outcomes. We train the model on past data—performance reviews, skills assessments, survey responses—and it learns patterns and trends.
The models are then used to predict future outcomes, like whether an employee is likely to succeed in a new role or which candidates possess the hidden potential to take your company to the next level.
Unsupervised learning isn’t about prediction, but rather segmentation or grouping. For example, by analyzing patterns in employee data such as performance metrics, engagement levels, skill sets, and personal interests, unsupervised learning algorithms can group employees into different clusters. These clusters can help HR to tailor specific training programs, team assignments, or career development plans that are more aligned with each group’s characteristics.
Both supervised and unsupervised learning empower HR professionals to move beyond gut instincts and delve into the depths of data. They become tools for smarter decision-making, optimized processes, and a future-proofed workforce.
Below we identify some of the powerful applications of Supervised Machine Learning that can shape the future of your organization, one algorithm at a time.
Candidate Identification: Resumes, job descriptions, social media profiles and past application data can be used to develop models to support candidate identification. This can include doing automated screening where models scan resumes and profiles for keywords, skills, and qualifications specific to the open position. This saves time and resources by focusing on relevant candidates. Models can also be used to diversify the talent pool by identifying qualified candidates who might not have applied through traditional channels, thus expanding the pool beyond those actively seeking new positions. Fraud detection in recruiting: A complementary model for the candidate identification model is one in which fraudulent applications are identified. This type of model leverages the same information as applications such as resumes, job descriptions, social media profiles and past application data but also past fraud cases. The model scans for inconsistencies, keywords linked to known fraud, and discrepancies between stated qualifications and online information. This protects the organization from hiring unqualified candidates and potential legal risks. Talent marketplace matching: This is an extension of the candidate identification modeling that matches internal talent to open positions. Models such as collaborative filtering and recommendation systems can use input data such as employee skills, experience, career aspirations, open positions, and past internal moves. These models develop recommendations of positions that best fit an employee’s skills, interests, and career goals. This increases employee engagement and internal mobility, and reduces external recruitment costs. Predicting attrition: Past employee data such as performance, demographics, and engagement surveys can be inputs to models that predict the probability of attrition. There are a broad set of possible model structures for predicting attrition but, regardless of the model details, they seek to identify high-risk employees. Patterns linked to past resignations, like low performance, low engagement, specific demographics, or recent changes in job responsibilities, are likely to be strong predictors of attrition. These models are useful in that they can allow for proactive retention strategies. For example, HR can target these employees with personalized interventions like mentorship, increased career development opportunities, or addressing specific concerns identified by the model. Predicting employment success/future job promotion: From a modeling point of view, the methodology for this modeling is very similar to predicting attrition, but the target variable is quite different. Using data like performance data, skills assessments, personality tests, promotion history, this model can predict the probability of promotion or achieving success. A well-crafted model could remove some of the bias and subjectivity associated with promotion decisions, ensuring those with the greatest potential are recognized and offered opportunities for advancement. Compensation analysis: Leveraging salary data, job descriptions, employee demographics, location adjustments and benefits utilization data are inputs for models that are used to detect and address pay discrepancies: The model identifies potential discriminatory pay gaps based on gender, race, or other protected characteristics. This helps ensure fair compensation practices and avoids legal issues.
As with all modeling decisions, it is important to assess whether these models should be built internally or if externally developed software should be leveraged. That “build or buy” decision is a cost-benefit analysis, one that should be systematically explored.
Remember, these are just examples of supervised machine learning applications. The specific models and data used will vary depending on the organization and its needs. It’s crucial to ensure ethical considerations and transparency throughout the supervised machine learning implementation process in HR.
Howard Steven Friedman is a data scientist, health economist, and writer with decades of experience leading data modeling teams in the private sector, public sector, and academia.
Akshay Swaminathan leads the data science team at Cerebral and is a Knight-Hennessy scholar at Stanford University School of Medicine. Together they are authors of Winning with Data Science: A Handbook for Business Leaders (Columbia Business School Press).
| 2024-01-22T00:00:00 |
2024/01/22
|
https://www.hrfuture.net/talent-management/technology/machine-learning-in-the-human-resource-space/
|
[
{
"date": "2023/01/01",
"position": 54,
"query": "machine learning workforce"
},
{
"date": "2023/02/01",
"position": 59,
"query": "machine learning workforce"
},
{
"date": "2023/08/01",
"position": 52,
"query": "machine learning workforce"
},
{
"date": "2023/09/01",
"position": 55,
"query": "machine learning workforce"
},
{
"date": "2023/10/01",
"position": 55,
"query": "machine learning workforce"
},
{
"date": "2024/01/22",
"position": 2,
"query": "machine learning workforce"
},
{
"date": "2024/03/01",
"position": 55,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 53,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 55,
"query": "machine learning workforce"
},
{
"date": "2024/10/01",
"position": 52,
"query": "machine learning workforce"
},
{
"date": "2024/12/01",
"position": 54,
"query": "machine learning workforce"
},
{
"date": "2025/01/01",
"position": 51,
"query": "machine learning workforce"
}
] |
"The Role of Artificial Intelligence in Workforce Learning and ...
|
The Role of Artificial Intelligence in Workforce Learning and Development: A Systematic Review
|
https://digitalcommons.odu.edu
|
[
"Mildred V. Jones",
"Jones",
"Mildred V.",
"Old Dominion University"
] |
... machine learning, and 3) natural language processing. Grounded coding revealed five trends for affordances: 1) learning approaches, 2) learner experience, 3 ...
|
Abstract
The purpose of this study is to investigate how artificial intelligence (AI) is currently employed in workforce learning and development. The study examined the types of AI employed and the affordances realized for organizations and employees. A PRISMA systematic review methodology was utilized to address the overarching problem statement and answer the three questions guiding the study. The PRISMA extension Preferred Reporting Items for Systematic Reviews and Meta Analysis for Protocols was used to direct each phase of the research. In addition, the Preferred Reporting Items for Systematic Reviews and Meta Analysis was used to conduct the article selection process. Findings revealed studies were distributed predominantly between Asia, Europe, and the United States. For types of AI, grounded coding resulted in three prominent trends: 1) Applied AI, 2) machine learning, and 3) natural language processing. Grounded coding revealed five trends for affordances: 1) learning approaches, 2) learner experience, 3) usability 4) organization efficiency and 5) cost. This systematic review is limited as it only examined peer-reviewed journal and conference publications available in English with reported organizational and learning outcomes. This study is unique in that it provides organizations and educators with the first systematic review examining AI’s role in the development and delivery of workforce training and development.
| 2023-01-01T00:00:00 |
https://digitalcommons.odu.edu/efl_etds/398/
|
[
{
"date": "2023/01/01",
"position": 55,
"query": "machine learning workforce"
},
{
"date": "2023/02/01",
"position": 56,
"query": "machine learning workforce"
},
{
"date": "2023/08/01",
"position": 55,
"query": "machine learning workforce"
},
{
"date": "2023/09/01",
"position": 56,
"query": "machine learning workforce"
},
{
"date": "2023/10/01",
"position": 57,
"query": "machine learning workforce"
},
{
"date": "2024/03/01",
"position": 56,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 56,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 56,
"query": "machine learning workforce"
},
{
"date": "2024/10/01",
"position": 55,
"query": "machine learning workforce"
},
{
"date": "2024/12/01",
"position": 56,
"query": "machine learning workforce"
},
{
"date": "2025/01/01",
"position": 54,
"query": "machine learning workforce"
},
{
"date": "2025/02/01",
"position": 62,
"query": "machine learning workforce"
},
{
"date": "2025/03/01",
"position": 60,
"query": "machine learning workforce"
},
{
"date": "2025/04/01",
"position": 61,
"query": "machine learning workforce"
}
] |
|
Machine Learning in the Workplace: its actual and future impact
|
Machine Learning in the Workplace: its actual and future impact
|
https://howtolearnmachinelearning.com
|
[] |
Machine Learning in the workplace will revolutionize how we work, from productivity to socialization and meetings. Read on and learn how!
|
How to Learn Machine Learning gives you the best information to learn about machine learning, one of the main drivers of the next technological revolution. Read more informative articles today!
Machine learning is a subset of Artificial Intelligence that relies on the use of algorithms and statistical models to analyze and draw inferences from data sets.
A key benefit of machine learning systems is that they do not need to be explicitly coded to complete tasks, rather they can ‘learn’ as they work and become better at assigned projects.
According to research by Finance Online, 51% of businesses have already adopted machine learning in the workplace in some capacity.
And the scale of its use is expected to increase in the coming years.
In this article, we explores the impact machine learning in the workplace, in domains like business operations and employee performance.
Machine Learning in the workplace’s 1st improvement: Process Mining-Based Workflows
A workflow is a series of tasks that are repeatedly followed in sequential order to achieve an expected result. Modern workflows are dominantly implemented through cloud-based apps, such as a customer relationship management (CRM) tool, social media management software, or more.
Over time it is normal for workflows to become less efficient, but given its digital nature, it can be tough to spot inefficiencies manually and fix them before it starts to majorly affect business performance. Here’s where machine learning-based process mining tools prove to be the perfect solution.
A process mining tool can be integrated with all software used across the organization, post-which it can start learning about your workflow and remove inefficiencies. Here’s how the tool works:
First, it reads data related to your work processes
Second, it converts the data into event logs
Third, it creates visualizations of your workflows which can then be used by relevant stakeholders to solve bottlenecks
Given the fact that the tool will interact with your workflow 24/7, the process of mining efficiencies increases the probability of promptly identifying and solving inefficiencies, leading to higher productivity and faster decision making.
This is similar to SEO and website performance statistics; by scrutinizing the information available to your business, you can capitalize on opportunities and alter or cut weak spots.
Higher Productivity Through AI Tools
There are various machine learning and AI-based tools used by businesses today that help employees achieve higher productivity numbers than ever before. Here are a few examples:
Writing Assistants: These are extensively used by creative professionals (writers, marketing professionals, sales agents) to frame messaging for specific audiences. Not only do they help achieve error-free writing but also provide insights on how to maintain a particular voice and tone.
Intranet Chatbots: Using these bots, employees can retrieve documents and files in a flash from the company’s knowledge base. This significantly reduces the time needed to access information, leading to fast and informed decision-making.
By leveraging the power of machine learning, employees can now spend less time deliberating on their actions and achieve higher productivity levels daily.
Accurate Performance Tracking
Workplace bias has been a prevalent problem in organizations across all industries. Research conducted by Deloitte shows that 68% of employees report that workplace bias harms their productivity, and 84% report that these biases affect their level of happiness and self-confidence even beyond the workplace.
While it is difficult to completely remove bias from the workplace, it can now be severely minimized through the use of machine learning-based performance management systems.
Rather than managers being given the responsibility to track the performance of individual employees, it can now be placed in the hands of unbiased algorithms which accurately track daily performance, compare it to set metrics, and provide on-demand reports for any given time frame.
These reports can then be used for appraisals, promotions, and contract renewals.
The number one benefit of these systems will be the transparency it provides as employees can request reports themselves as well.
The Machine Learning era is already upon us. Sooner rather than later, you can expect machine learning tools such as process mining software and chatbots to become commonly used in your workplace.
But, rather than viewing them in a negative light, learn to embrace them as tools that will help you achieve greater productivity and develop a fair and transparent work environment.
Thank you very much for reading How to Learn Machine learning, as always keep leaning and have a great day!
| 2023-03-26T00:00:00 |
2023/03/26
|
https://howtolearnmachinelearning.com/articles/machine-learning-in-the-workplace-its-actual-and-future-impact/
|
[
{
"date": "2023/01/01",
"position": 58,
"query": "machine learning workforce"
},
{
"date": "2023/02/01",
"position": 61,
"query": "machine learning workforce"
},
{
"date": "2023/08/01",
"position": 80,
"query": "machine learning workforce"
},
{
"date": "2023/09/01",
"position": 59,
"query": "machine learning workforce"
},
{
"date": "2023/10/01",
"position": 60,
"query": "machine learning workforce"
},
{
"date": "2024/03/01",
"position": 59,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 58,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 59,
"query": "machine learning workforce"
},
{
"date": "2024/10/01",
"position": 82,
"query": "machine learning workforce"
},
{
"date": "2024/12/01",
"position": 58,
"query": "machine learning workforce"
},
{
"date": "2025/01/01",
"position": 80,
"query": "machine learning workforce"
},
{
"date": "2025/02/01",
"position": 65,
"query": "machine learning workforce"
},
{
"date": "2025/03/01",
"position": 63,
"query": "machine learning workforce"
},
{
"date": "2025/04/01",
"position": 64,
"query": "machine learning workforce"
}
] |
AI for Future Workforce Program - Intel
|
AI for Future Workforce Program
|
https://www.intel.com
|
[] |
AI skills are the most sought-after skills for jobs in the digital economy. All industries need AI Solution Builders and AI Power Users, along with more AI ...
|
Republic of Poland
"Digital technologies in agricultural schools are becoming more and more popular and knowledge in this field is increasing. Thanks to the establishment of cooperation between the Ministry of Agriculture and Rural Development and Intel, the Intel® AI for Future Workforce program is being implemented in agricultural schools affiliated with the Agricultural Schools Network, raising the level of digital competence of teachers and students."
| 2023-01-01T00:00:00 |
https://www.intel.com/content/www/us/en/corporate/artificial-intelligence/digital-readiness-ai-for-future-workforce.html
|
[
{
"date": "2023/01/01",
"position": 60,
"query": "machine learning workforce"
},
{
"date": "2023/02/01",
"position": 64,
"query": "machine learning workforce"
},
{
"date": "2023/08/01",
"position": 60,
"query": "machine learning workforce"
},
{
"date": "2023/09/01",
"position": 64,
"query": "machine learning workforce"
},
{
"date": "2023/10/01",
"position": 64,
"query": "machine learning workforce"
},
{
"date": "2024/03/01",
"position": 64,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 64,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 66,
"query": "machine learning workforce"
},
{
"date": "2024/10/01",
"position": 61,
"query": "machine learning workforce"
},
{
"date": "2024/12/01",
"position": 87,
"query": "government AI workforce policy"
},
{
"date": "2024/12/01",
"position": 64,
"query": "machine learning workforce"
},
{
"date": "2025/01/01",
"position": 59,
"query": "machine learning workforce"
},
{
"date": "2025/02/01",
"position": 76,
"query": "machine learning workforce"
},
{
"date": "2025/03/01",
"position": 73,
"query": "machine learning workforce"
},
{
"date": "2025/04/01",
"position": 75,
"query": "machine learning workforce"
}
] |
|
Workforce AI: Healthcare Workforce Management - LotusOne
|
Workforce AI: Healthcare Workforce Management
|
https://www.lotusone.com
|
[] |
Workforce AI uses predictive analytics, AI and machine learning to forecast patient demand and workforce needs months in advance.
|
Forecast when — and where — resources are needed most
Workforce AI uses predictive analytics, AI and machine learning to forecast patient demand and workforce needs months in advance, ensuring you always have the right resources in place at the right time.
With three distinct modules for hiring, scheduling and staffing, Workforce AI provides actionable recommendations that optimize labor costs, improve resource allocation and free up your time to focus on other important tasks.
| 2023-01-01T00:00:00 |
https://www.lotusone.com/solutions/workforceai/
|
[
{
"date": "2023/01/01",
"position": 69,
"query": "machine learning workforce"
},
{
"date": "2023/02/01",
"position": 57,
"query": "machine learning workforce"
},
{
"date": "2023/08/01",
"position": 48,
"query": "machine learning workforce"
},
{
"date": "2023/09/01",
"position": 67,
"query": "machine learning workforce"
},
{
"date": "2023/10/01",
"position": 67,
"query": "machine learning workforce"
},
{
"date": "2024/03/01",
"position": 67,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 67,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 68,
"query": "machine learning workforce"
},
{
"date": "2024/10/01",
"position": 63,
"query": "machine learning workforce"
},
{
"date": "2024/12/01",
"position": 67,
"query": "machine learning workforce"
},
{
"date": "2025/01/01",
"position": 62,
"query": "machine learning workforce"
},
{
"date": "2025/02/01",
"position": 15,
"query": "machine learning workforce"
},
{
"date": "2025/03/01",
"position": 12,
"query": "machine learning workforce"
},
{
"date": "2025/04/01",
"position": 59,
"query": "machine learning workforce"
}
] |
|
How is workforce change management impacted by Machine ...
|
How is workforce change management impacted by Machine Learning Enhancements?
|
https://boscoanthony.com
|
[
"Bosco Anthony"
] |
Artificial intelligence (AI) and machine learning have been transforming the workforce for several years now. Many experts predict that future generative AI ...
|
Artificial intelligence (AI) and machine learning have been transforming the workforce for several years now. Many experts predict that future generative AI, like ChatGPT, could eventually replace the need for human workers in certain industries. While this may be true for some industries, it is important to understand that AI technology is not a silver bullet that can replace all human workers. In this blog post, we will explore the potential impact of future generative AI on the workforce and what it could mean for the future of work.
Where are we already seeing AI make an impact in change management in the workforce?
Automation of routine and repetitive tasks
One of the most significant trends caused by AI is the automation of routine and repetitive tasks. AI-powered technologies, such as machine learning algorithms and chatbots, are increasingly being used to automate tasks such as data entry, customer service, and administrative tasks. This is leading to a reduction in the number of workers needed to perform these tasks, as well as changes in the types of skills that are required for these roles.
The rise of the gig economy
Another trend caused by AI is the rise of the gig economy. AI-powered platforms such as Uber, Lyft, and TaskRabbit are enabling workers to earn money by performing a range of tasks, such as driving, delivering food and completing odd jobs. This is leading to a shift away from traditional employment models as more workers choose to work on a freelance or contract basis.
Increased demand for workers with specialized skills
As AI and automation become more prevalent in the workforce, there is an increasing demand for workers with specialised skills in areas such as data analysis, machine learning and software development. Many organisations are investing in training programs and partnerships with educational institutions to help their workers develop the skills they need to succeed in the AI-driven workforce.
New models of work
AI is also driving the development of new models of work. For example, flexible work arrangements, remote work and job sharing are becoming more common as organisations seek to better utilise their workforce and respond to changing business needs. AI-powered technologies are enabling workers to work from anywhere, collaborate with colleagues around the world and work on projects in new and innovative ways.
Ethical considerations
Finally, AI is raising important ethical considerations in the workforce. For example, there are concerns about the impact of AI on job displacement and inequality, as well as concerns about the ethical use of AI in areas such as hiring and performance evaluation. As AI becomes more prevalent in the workforce, it will be important for organisations to consider the ethical implications of these technologies and to take steps to ensure that they are used in a fair and equitable manner.
Should we be concerned as a human race about the future of work?
Artificial intelligence (AI) is having a significant impact on the workforce and we are already seeing a range of changes in the way that work is organised and performed. One area where AI is causing change management is in the way that organisations structure their workforces.
One of the most significant changes that we are seeing is the automation of routine and repetitive tasks. Many organisations are using AI and machine learning to automate tasks such as data entry, customer service, and administrative tasks. This is leading to a reduction in the number of workers needed to perform these tasks, as well as changes in the type of skills that are required for these roles.
Another area where AI is causing change management is in the way that work is organised and managed. With the increasing use of AI and automation, there is a growing need for workers who have skills in areas such as data analysis, machine learning, and software development. This is leading to changes in the way that organisations structure their workforce, with an increasing focus on hiring workers with specialised skills and expertise.
AI is also changing the way that workers are trained and educated. With the increasing importance of skills in areas such as data analysis and machine learning, there is a growing need for workers to receive training and education in these areas. Many organisations are investing in training programs and partnerships with educational institutions to help their workers develop the skills they need to succeed in the AI-driven workforce.
Finally, AI is causing change management in the way that organisations think about work and the role of workers. With the increasing use of automation and AI, there is a growing recognition that work can be done in new and innovative ways. Many organisations are exploring new models of work, such as flexible work arrangements, remote work, and job sharing, that can help them to better utilise their workforce and respond to changing business needs.
In conclusion, AI is causing significant change management in the workforce, leading to new models of work, changes in the types of skills that are required and changes in the way that organisations are structured and managed. As organisations continue to adopt AI and automation, it will be important for them to consider the impact on their workers and to take steps to ensure that the benefits of these technologies are shared fairly across society.
| 2023-01-19T00:00:00 |
2023/01/19
|
https://boscoanthony.com/how-is-workforce-change-management-impacted-by-machine-learning-enhancements/
|
[
{
"date": "2023/01/01",
"position": 71,
"query": "machine learning workforce"
},
{
"date": "2023/02/01",
"position": 70,
"query": "machine learning workforce"
},
{
"date": "2023/07/10",
"position": 4,
"query": "machine learning workforce"
},
{
"date": "2023/08/01",
"position": 66,
"query": "machine learning workforce"
},
{
"date": "2023/09/01",
"position": 72,
"query": "machine learning workforce"
},
{
"date": "2023/10/01",
"position": 72,
"query": "machine learning workforce"
},
{
"date": "2024/03/01",
"position": 72,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 69,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 70,
"query": "machine learning workforce"
},
{
"date": "2024/10/01",
"position": 68,
"query": "machine learning workforce"
},
{
"date": "2024/12/01",
"position": 69,
"query": "machine learning workforce"
},
{
"date": "2025/01/01",
"position": 66,
"query": "machine learning workforce"
},
{
"date": "2025/02/01",
"position": 81,
"query": "machine learning workforce"
},
{
"date": "2025/03/01",
"position": 80,
"query": "machine learning workforce"
},
{
"date": "2025/04/01",
"position": 80,
"query": "machine learning workforce"
}
] |
Leveraging Machine Learning for Workforce Optimization - Infosys
|
Leveraging Machine Learning for Workforce Optimization
|
https://www.infosys.com
|
[
"Infosys Limited"
] |
Machine learning is a catalyst for workforce optimization in our audit engagements. Our solution identifies and integrates diverse data tenors.
|
Overview
In the conventional method of audit services, a multi-disciplinary team of accountants, forensic professionals, and bankruptcy evaluators analyzes data from diverse sources and performs an audit. This people-intensive methodology requires a significant investment of time and effort to manage audit and assurance activities on an industrial scale.
Infosys partners with professional services organizations to undertake audit and assurance projects by leveraging machine learning algorithms and tools. Machine learning is a catalyst for workforce optimization in our audit engagements. Our solution identifies and integrates diverse data tenors using open source and proprietary machine learning frameworks to uncover knowledge from diverse sources across the enterprise.
Our machine learning solutions learn from common elements across value streams of audit and assurance. Past decisions guide the machine to make informed decisions about audit and assurance workforce optimization strategies. Our solution mines past effort, metrics and knowledge to undertake audit activities such as proposals for similar engagements.
| 2023-01-01T00:00:00 |
https://www.infosys.com/industries/professional-services/offerings/workforce-optimization.html
|
[
{
"date": "2023/01/01",
"position": 73,
"query": "machine learning workforce"
},
{
"date": "2023/02/01",
"position": 72,
"query": "machine learning workforce"
},
{
"date": "2023/08/01",
"position": 68,
"query": "machine learning workforce"
},
{
"date": "2023/09/01",
"position": 76,
"query": "machine learning workforce"
},
{
"date": "2023/10/01",
"position": 76,
"query": "machine learning workforce"
},
{
"date": "2024/03/01",
"position": 76,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 71,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 71,
"query": "machine learning workforce"
},
{
"date": "2024/10/01",
"position": 70,
"query": "machine learning workforce"
},
{
"date": "2024/12/01",
"position": 71,
"query": "machine learning workforce"
},
{
"date": "2025/01/01",
"position": 68,
"query": "machine learning workforce"
},
{
"date": "2025/02/01",
"position": 72,
"query": "machine learning workforce"
},
{
"date": "2025/03/01",
"position": 69,
"query": "machine learning workforce"
},
{
"date": "2025/04/01",
"position": 72,
"query": "machine learning workforce"
}
] |
|
AI in the workplace. Why machine learning is not coming after your job.
|
AI in the workplace. Why machine learning is not coming after your job.
|
https://www.blog.refocusai.com
|
[] |
Fiction through the effort of researchers and the stampede of scientific development has a tendency lately to become real. Artificial Intelligence is not ...
|
Fiction through the effort of researchers and the stampede of scientific development has a tendency lately to become real. Artificial Intelligence is not one of those things.
Editorial Note: This article was updated in March 2022 to reflect the latest AI and workforce trends.
Back when this article was originally written, 2020 was the year that cars would fly, time travel would be possible, and life could be extended indefinitely. Endeavors that may have started off as purely science fiction were starting to bear fruit. As the stampede scientific development marches on, one technology that has not lived up to the hype is Artificial Intelligence (AI).
While true AI does not yet exist, machines can learn, which we explore in this article on 'How computers learn'. Let's start by breaking down what artificial intelligence is.
What actually is Artificial Intelligence?
AI means a lot of different things to a lot of different people, so let's break it down. According to Merriam-Webster, it is:
a branch of computer science dealing with the simulation of intelligent behavior in computers; the capability of a machine to imitate intelligent human behavior.
Put into practical application, AI is the ability for a machine to react to a situation it has never experienced or learned about
Think about dropping a Los Angeles alley cat into the Kruger National park in front of an elephant. How would the cat react? It has never seen an elephant in LA, nor been on one of the plains of Africa. Now compare this to dropping a human into a similar situation: the human could generalize that because they once saw an elephant in a zoo, the human knows that the elephant is not interested in eating them.
Generalizing is not yet possible for a computer. Computers ‘learn’ by ingesting massive amounts of data about a specific situation. Algorithms that allow computers to generalize across unrelated topics are just starting to emerge and are the first step in a long process that may eventually end in computers being self-aware. What has gained prominence in the workplace is machine learning (ML).
So what is Machine Learning?
The Brookings Institute does an excellent job of delineating ML from AI: “The core insight of machine learning is that much of what we recognize as intelligence hinges on probability rather than reason or logic.” In application, ML is the use of statistical, actuarial, and other mathematical models to identify trends at scale in large datasets.
AI, ML, and your job
It is impossible to know how the workforce will change if computers become rational-thinking beings. For now, rest assured fellow humans, ML is not coming for your job. There are three main reasons for this:
ML relies heavily on manual (code for human) data gathering and preparation in order to ‘learn’; Computers require humans to build the algorithms that power ML; ML allows computers to react to well-defined problem sets (such as immediately determining if a credit card transaction is fraudulent) but requires humans for quality control and to resolve the outcome of the inference.
Machine Learning in the workplace
Imagine a world where you have the ability to predict an events’ likely outcome. This ability exists and is already being applied equally across the financial, retail, manufacturing, logistics, and agricultural sectors for well-understood subject areas. Let’s look at one of the practical and proven uses of ML, driving sales. Here is the situation: an insurance agent answers a client's question. Seems simple right? In an article on Sales and Insurance, we dive into this topic even more.
During a routine interaction, the insurance agent casually the client ten potential coverages which they do not already have. The individual is only interested however in one of the nine offered policies. As a result, the client comes away from the encounter with a feeling of being overwhelmed, and 'sold to.' For any insurance professional, this is the least desired outcome as it can damage the trust between the two parties. And in most situations where a client feels sold to, their instinct is just to say “NO” to everything - even the policy they would have otherwise been interested in. What a lost opportunity!
With machine learning insights, the conversation would have gone differently. In the near future, insurance agents will regularly use ML to provide context about their client's buying behavior. If they now can know that their client has a 92% chance of needing a commercial property policy, does the agent still waste time offering the client the other nine policies that there is zero chance they’ll purchase? Of course not. Within this context, the ML informed the agent that their client would need additional coverage. The agent only presents additional lines that would benefit the client who can then easily review these coverages. Both parties win.
The statistical analysis at scale made possible by ML will enable companies to serve their clients and provide valuable insight during interactions with customers.
The statistical analysis at scale made possible by ML will enable companies to serve their clients and provide valuable insight during interactions with customers. We think of this as an 'AI Buddy System,' which we explain in this article. So while an individual’s job may see some change as the result of ML insights, machine learning will not be replacing them.
Future of Work à la ML
Technology is leading to changes in how the workforce spends eight hours a day for their career spanning 30+ years. Naturally, this change has led to uncertainty about the role of technology, specifically machine learning (or AI), in replacing workers. Understanding the capabilities of ML is a starting point to understanding how this technology is enabling workers, not causing job loss. A couple ways ML is changing the way businesses operate:
Increasing retention by targeting clients with customized loyalty initiatives. Personalizing customer service to maximize every client encounter. Identify fraud early in the underwriting process, reducing costly claims. Smoother supply chains for just-in-time logistics.
Far more likely to contribute to systemic job-loss is new consumer preferences, technological advancements (like using nuclear fusion for power generation rather than coal), and the practice of offshoring jobs.
I've had the pleasure of speaking with many seasoned insurance professionals resistant to our ML because they feel threatened; they think this advancement will lead to job losses. This could not be further from reality. Ultimately, the promise of machine learning is efficiency. The average workday will contain far less mundane tasks, and create more enriching work experiences.
Because no one enjoys crunching numbers in an Excel sheet - wouldn’t you rather engage in meaningful conversations with customers you have a greater than 51% chance of making the sale to?
Originally published on HackerNoon
| 2020-10-26T00:00:00 |
2020/10/26
|
https://www.blog.refocusai.com/machine-learning-workplace/
|
[
{
"date": "2023/01/01",
"position": 74,
"query": "machine learning workforce"
},
{
"date": "2023/08/01",
"position": 67,
"query": "machine learning workforce"
},
{
"date": "2023/09/01",
"position": 75,
"query": "machine learning workforce"
},
{
"date": "2023/10/01",
"position": 75,
"query": "machine learning workforce"
},
{
"date": "2024/03/01",
"position": 75,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 73,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 73,
"query": "machine learning workforce"
},
{
"date": "2024/10/01",
"position": 71,
"query": "machine learning workforce"
},
{
"date": "2024/12/01",
"position": 73,
"query": "machine learning workforce"
},
{
"date": "2025/01/01",
"position": 67,
"query": "machine learning workforce"
},
{
"date": "2025/02/01",
"position": 79,
"query": "machine learning workforce"
},
{
"date": "2025/03/01",
"position": 76,
"query": "machine learning workforce"
},
{
"date": "2025/04/01",
"position": 78,
"query": "machine learning workforce"
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.