Detection de blanchiment d'argent (AML/LCB-FT) : ML calibre vs rule-based, XAI compliance (SHAP), audit-friendly
-
Updated
Jun 8, 2026 - Jupyter Notebook
Detection de blanchiment d'argent (AML/LCB-FT) : ML calibre vs rule-based, XAI compliance (SHAP), audit-friendly
Production-style anti-money-laundering detection on the SAML-D dataset (9.5M txns, 17 typologies). XGBoost + LightGBM ensemble · 96% fewer alerts than the $5K rule at 85% recall · per-alert SHAP narratives · Streamlit triage dashboard · model card.
Add a description, image, and links to the saml-d topic page so that developers can more easily learn about it.
To associate your repository with the saml-d topic, visit your repo's landing page and select "manage topics."