Back to Portfolio
Quantitative Finance

Advanced ML Trading System

Implementation of methods from Lopez de Prado's Advances in Financial Machine Learning. CUSUM filters for event detection, triple barrier labeling, meta-labeling for signal confidence, purged K-fold cross-validation, and Kelly criterion for position sizing. Built in Python with XGBoost.

Full case study coming soon.

The interactive write-up for this project is in progress. Check back shortly.

Key Highlights

Triple barrier labeling and meta-labeling
Sequential bootstrap and purged K-fold CV
Kelly criterion dynamic bet sizing
Deflated Sharpe ratio metrics

Technologies

Quantitative FinanceMLPythonXGBoost