InterpretML: A Unified Framework for Machine Learning Interpretability

TLDR

InterpretML is an open‑source Python package that provides both glassbox models (e.g., linear models, rule lists, GAMs) and black‑box explainability techniques (e.g., Partial Dependence, LIME) to practitioners and researchers. The package offers a unified API and extensible visualization platform that lets users easily compare multiple interpretability algorithms. It includes the first implementation of the Explainable Boosting Machine, an interpretable glassbox model that matches the accuracy of many black‑box models. MIT‑licensed source code is available on GitHub at github.com/microsoft/interpret.

Abstract

InterpretML is an open-source Python package which exposes machine learning interpretability algorithms to practitioners and researchers. InterpretML exposes two types of interpretability - glassbox models, which are machine learning models designed for interpretability (ex: linear models, rule lists, generalized additive models), and blackbox explainability techniques for explaining existing systems (ex: Partial Dependence, LIME). The package enables practitioners to easily compare interpretability algorithms by exposing multiple methods under a unified API, and by having a built-in, extensible visualization platform. InterpretML also includes the first implementation of the Explainable Boosting Machine, a powerful, interpretable, glassbox model that can be as accurate as many blackbox models. The MIT licensed source code can be downloaded from github.com/microsoft/interpret.