Explainable AI for Trees: From Local Explanations to Global Understanding

TL;DR

This paper enhances the interpretability of tree-based machine learning models by introducing a polynomial time algorithm for optimal explanations, new local interaction explanations, and tools for understanding global structure, demonstrated on medical datasets.

Contribution

It presents the first polynomial time algorithm for optimal explanations, introduces local interaction explanations, and offers tools for global understanding of tree models, improving interpretability in practice.

Findings

Identified high-impact, low-frequency risk factors for mortality.

Highlighted population sub-groups with shared risk characteristics.

Uncovered non-linear interaction effects among risk factors.

Abstract

Tree-based machine learning models such as random forests, decision trees, and gradient boosted trees are the most popular non-linear predictive models used in practice today, yet comparatively little attention has been paid to explaining their predictions. Here we significantly improve the interpretability of tree-based models through three main contributions: 1) The first polynomial time algorithm to compute optimal explanations based on game theory. 2) A new type of explanation that directly measures local feature interaction effects. 3) A new set of tools for understanding global model structure based on combining many local explanations of each prediction. We apply these tools to three medical machine learning problems and show how combining many high-quality local explanations allows us to represent global structure while retaining local faithfulness to the original model. These tools enable us to i) identify high magnitude but low frequency non-linear mortality risk factors in the general US population, ii) highlight distinct population sub-groups with shared risk characteristics, iii) identify non-linear interaction effects among risk factors for chronic kidney disease, and iv) monitor a machine learning model deployed in a hospital by identifying which features are degrading the model's performance over time. Given the popularity of tree-based machine learning models, these improvements to their interpretability have implications across a broad set of domains.