Ordered Counterfactual Explanation by Mixed-Integer Linear Optimization

TL;DR

This paper introduces Ordered Counterfactual Explanation (OrdCE), a novel framework that incorporates feature interaction and ordering into counterfactual explanations using mixed-integer linear optimization, improving interpretability.

Contribution

It proposes a new objective function and optimization method for ordered counterfactual explanations considering feature interactions and causality.

Findings

Effective in real datasets compared to unordered methods

Incorporates feature interaction into counterfactual explanations

Provides an optimal feature change order for better interpretability

Abstract

Post-hoc explanation methods for machine learning models have been widely used to support decision-making. One of the popular methods is Counterfactual Explanation (CE), also known as Actionable Recourse, which provides a user with a perturbation vector of features that alters the prediction result. Given a perturbation vector, a user can interpret it as an "action" for obtaining one's desired decision result. In practice, however, showing only a perturbation vector is often insufficient for users to execute the action. The reason is that if there is an asymmetric interaction among features, such as causality, the total cost of the action is expected to depend on the order of changing features. Therefore, practical CE methods are required to provide an appropriate order of changing features in addition to a perturbation vector. For this purpose, we propose a new framework called Ordered Counterfactual Explanation (OrdCE). We introduce a new objective function that evaluates a pair of an action and an order based on feature interaction. To extract an optimal pair, we propose a mixed-integer linear optimization approach with our objective function. Numerical experiments on real datasets demonstrated the effectiveness of our OrdCE in comparison with unordered CE methods.