Open Source Projects
Advanced machine learning libraries for risk management and interpretable AI.
Incremental learning framework for CatBoost with Ray integration for distributed training
Fast Weight of Evidence (WOE) encoding with statistical inference and confidence intervals
Efficient implementation of Fisher's scoring algorithm for maximum likelihood estimation
Interpretability tools for Random Forest models with feature importance analysis
Interpretable gradient boosting with WOE-based scoring for high-stakes domains
Scorecard framework for XGBoost and CatBoost with SQL deployment capabilities
Contribute to xRiskLab
Our projects are open source and community-driven. We welcome contributions from developers, data scientists, and researchers who share our vision of interpretable machine learning.