Learning Models for Actionable Recourse

Part of Advances in Neural Information Processing Systems 34 (NeurIPS 2021)

Bibtex Paper Reviews And Public Comment » Supplemental

Authors

Alexis Ross, Himabindu Lakkaraju, Osbert Bastani

Abstract

As machine learning models are increasingly deployed in high-stakes domains such as legal and financial decision-making, there has been growing interest in post-hoc methods for generating counterfactual explanations. Such explanations provide individuals adversely impacted by predicted outcomes (e.g., an applicant denied a loan) with recourse---i.e., a description of how they can change their features to obtain a positive outcome. We propose a novel algorithm that leverages adversarial training and PAC confidence sets to learn models that theoretically guarantee recourse to affected individuals with high probability without sacrificing accuracy. We demonstrate the efficacy of our approach via extensive experiments on real data.