Generating Counterfactual and Contrastive Explanations using SHAP

TL;DR

This paper introduces a model-agnostic method leveraging SHAP to generate contrastive and counterfactual explanations, enhancing interpretability and compliance with legal requirements in AI decision-making.

Contribution

It presents a novel systemic pipeline for generating contrastive and counterfactual explanations using SHAP, applicable across different models and datasets.

Findings

Effective generation of explanations demonstrated on IRIS, Wine Quality, and Mobile Features datasets.

The pipeline provides insights into model decision boundaries and feature importance.

Enhances transparency and legal compliance in AI systems.

Abstract

With the advent of GDPR, the domain of explainable AI and model interpretability has gained added impetus. Methods to extract and communicate visibility into decision-making models have become legal requirement. Two specific types of explanations, contrastive and counterfactual have been identified as suitable for human understanding. In this paper, we propose a model agnostic method and its systemic implementation to generate these explanations using shapely additive explanations (SHAP). We discuss a generative pipeline to create contrastive explanations and use it to further to generate counterfactual datapoints. This pipeline is tested and discussed on the IRIS, Wine Quality & Mobile Features dataset. Analysis of the results obtained follows.