interpretml

Fit interpretable models. Explain blackbox machine learning.

The code of AAAI 2020 paper "Transparent Classification with Multilayer Logical Perceptrons and Random Binarization".

counterfactual explanations for ML hyperparameters

Microsoft Ignite - Getting started on your health-tech journey using responsible AI

Example/Code for the article on KDNuggets

Demo's of FairLearn and InterpretML as described in my article on responsible AI.

Démonstration Azure InterpretML

Insurance workflow wrapper for interpretML's Explainable Boosting Machine — relativities, diagnostics, monotonicity editing, GLM comparison

EBM-based sports analytics system for evaluating run-up speed, stride mechanics, flying techniques, body measurements and within-athlete long jump performance variation.

Comparing XAI methods (EBM shape functions vs. post-hoc SHAP on XGBoost) and handover formats (JSON, PNG, tool-use) for LLM-generated natural-language explanations of ML predictions. Studienarbeit, TU Dresden.

A demonstration of detecting and mitigating bias in AI.

This project applies Microsoft's InterpretML library to analyze Titanic survival data using two ML models: the Explainable Boosting Machine (EBM), a fully transparent glassbox model, and Random Forest, a blackbox model. The EBM allows each prediction to be traced back to specific features such as gender, age, and passenger class.

Print Markdown to a single A4 page with auto-fit font sizing, live preview, and one-click PDF export