license: mit
language:
- en
metrics:
- mae
- r_squared
- mape
- mse
pipeline_tag: time-series-forecasting
datasets:
- Captain-Slow/Financial_datasets
Welcome to this repository of time series analysis and forecasting Notebooks, with applications to financial datasets, the goal of this collection is to explore patterns, trends, and predictive modeling techniques using both statistical and machine learning methods.
What’s Inside
This repository includes the following:
Exploratory Data Analysis (EDA)
Techniques for visualizing, decomposing, and understanding temporal structures in financial time series.Classical Forecasting Methods
Models such as:- ARIMA / SARIMA
- Facebook Prophet
- Vector Auto Regression
- Arch/Garch for volatility modeling
Machine Learning Approaches
Implementation of:- Random Forests
- XGBoost
- Long Short Term Memory
Feature Engineering for Time Series
Lag features, rolling statistics, seasonal indicators, and date-based encodings.Model Optimization and Evaluation
Grid-search-cv , Randomized-search-cv, cross-validation for time series, and performance metrics (MAE, RMSE, MAPE).
Datasets
The notebooks primarily work with financial datasets, such as:
- Stock price data.
- Commodity Prices.
- Foreign Exchnage rates.
- Inflation rates.
- Cryptocurrency price histories.
- Sales datasets