Model Explainability Tools

Ranking methodology

In development — no version effective yet.

Decision archetype: ai · Scores are category-relative (P-01) and commercial relationships never affect rank (P-04).

Tools (3)

InterpretMLMicrosoft Research

Open source

Open-source toolkit for training interpretable glassbox models and explaining blackbox models.

LIMEMarco Tulio Ribeiro

Open source

Open-source library that explains classifiers using locally faithful surrogate models.

SHAPScott Lundberg

Open source

Open-source library that explains model predictions using Shapley additive values.