ing-bank/probatus

🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models

Source code/webpage/demos for the What-If Tool

⚓ Eurybia monitors model drift over time and securizes model deployment with data validation

A game theoretic approach to explain the output of any machine learning model.

Track your Data Science. Skore's open-source Python library accelerates ML model development with automated evaluation reports, smart methodological guidance, and comprehensive cross-validation analysis.

Interpretability and explainability of data and machine learning models

Shapley Interactions and Shapley Values for Machine Learning

Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling (sklearn-compatible).

Library for exploring and validating machine learning data