Intersectional Fairness via Mixed-Integer Optimization

TL;DR

This paper introduces a novel mixed-integer optimization framework to train interpretable classifiers that effectively address intersectional bias, ensuring fairness in high-stakes AI applications like healthcare and finance.

Contribution

It presents a unified MIO-based approach for intersectional fairness, proving measure equivalence and improving bias detection in interpretable classifiers.

Findings

MIO-based algorithm enhances bias detection accuracy.

Interpretable classifiers bound intersectional bias below thresholds.

Proven measure equivalence for fairness detection.

Abstract

The deployment of Artificial Intelligence in high-risk domains, such as finance and healthcare, necessitates models that are both fair and transparent. While regulatory frameworks, including the EU's AI Act, mandate bias mitigation, they are deliberately vague about the definition of bias. In line with existing research, we argue that true fairness requires addressing bias at the intersections of protected groups. We propose a unified framework that leverages Mixed-Integer Optimization (MIO) to train intersectionally fair and intrinsically interpretable classifiers. We prove the equivalence of two measures of intersectional fairness (MSD and SPSF) in detecting the most unfair subgroup and empirically demonstrate that our MIO-based algorithm improves performance in finding bias. We train high-performing, interpretable classifiers that bound intersectional bias below an acceptable threshold, offering a robust solution for regulated industries and beyond.