GitHub - divagr18/quantcast: 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.

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 5 Commits
src		src
.gitignore		.gitignore
check.py		check.py
dashboard.py		dashboard.py
factor_cache.py		factor_cache.py
import requests.py		import requests.py
market_data.db		market_data.db
portfolio_history.csv		portfolio_history.csv
simulated_trades.csv		simulated_trades.csv
test_factors.py		test_factors.py
test_fetcher.py		test_fetcher.py
test_strategy.py		test_strategy.py

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.