Accurate Shapley Values for explaining tree-based models

TL;DR

This paper introduces two new, more accurate estimators for computing Shapley Values in tree-based models, addressing issues of encoding sensitivity and efficiency, with practical benefits demonstrated through simulations.

Contribution

The paper presents novel estimators for Shapley Values that leverage tree structures for improved accuracy and efficiency in model explanations.

Findings

New estimators outperform existing methods in accuracy

Simulations show practical gains over state-of-the-art algorithms

Methods are implemented in a Python package for accessibility

Abstract

Shapley Values (SV) are widely used in explainable AI, but their estimation and interpretation can be challenging, leading to inaccurate inferences and explanations. As a starting point, we remind an invariance principle for SV and derive the correct approach for computing the SV of categorical variables that are particularly sensitive to the encoding used. In the case of tree-based models, we introduce two estimators of Shapley Values that exploit the tree structure efficiently and are more accurate than state-of-the-art methods. Simulations and comparisons are performed with state-of-the-art algorithms and show the practical gain of our approach. Finally, we discuss the limitations of Shapley Values as a local explanation. These methods are available as a Python package.