ShapShift: Explaining Model Prediction Shifts with Subgroup Conditional Shapley Values

TL;DR

ShapShift is a method that explains prediction shifts in machine learning models by attributing changes to subgroups defined by decision tree structures, applicable to various model types.

Contribution

It introduces a Shapley value-based approach for explaining prediction shifts using decision tree subgroups, including a model-agnostic surrogate variant.

Findings

Provides exact explanations for single decision trees.

Extends to tree ensembles and neural networks.

Offers practical approximation techniques for real-world use.

Abstract

Changes in input distribution can induce shifts in the average predictions of machine learning models. Such prediction shifts may impact downstream business outcomes (e.g. a bank's loan approval rate), so understanding their causes can be crucial. We propose \ours{}: a Shapley value method for attributing prediction shifts to changes in the conditional probabilities of interpretable subgroups of data, where these subgroups are defined by the structure of decision trees. We initially apply this method to single decision trees, providing exact explanations based on conditional probability changes at split nodes. Next, we extend it to tree ensembles by selecting the most explanatory tree and accounting for residual effects. Finally, we propose a model-agnostic variant using surrogate trees grown with a novel objective function, allowing application to models like neural networks. While exact computation can be intensive, approximation techniques enable practical application. We show that \ours{} provides simple, faithful, and near-complete explanations of prediction shifts across model classes, aiding model monitoring in dynamic environments.