Skip to content

Latest commit

 

History

2 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Forecasting Models

Time series forecasting library for volatility and price prediction.

Features

  • GARCH volatility forecasting
  • EWMA volatility forecasting
  • XGBoost and LightGBM ML models
  • LSTM neural network forecasting
  • Prophet time series forecasting
  • ARIMA price forecasting
  • Ensemble forecasting

Key finding

Walk-forward validation revealed that every point-forecast model in this library was systematically overconfident when evaluated on calibration rather than accuracy alone. Refitting on expanding windows and checking calibration against held-out volatility regimes consistently exposed overconfidence that accuracy metrics masked.

Installation

pip install forecasting-models

License

MIT License

About

Time series forecasting library for volatility and price prediction using GARCH, EWMA, XGBoost, LightGBM, LSTM, Prophet, and ARIMA models with ensemble methods.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages