Skip to content

A modular stock prediction framework combining time series models and modern ML techniques. Supports custom pipelines for feature engineering (lag features, technical indicators), model training (ARIMA, XGBoost, LSTM), and walk-forward backtesting with performance metrics like Sharpe ratio, MSE, and cumulative return. Currently under development.

Notifications You must be signed in to change notification settings

divagr18/quantcast

About

A modular stock prediction framework combining time series models and modern ML techniques. Supports custom pipelines for feature engineering (lag features, technical indicators), model training (ARIMA, XGBoost, LSTM), and walk-forward backtesting with performance metrics like Sharpe ratio, MSE, and cumulative return. Currently under development.

Topics

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages