Learning Models for Actionable Recourse

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.

References in corpus (8)

• Equality of Opportunity in Supervised Learning
• Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations
• Actionable Recourse in Linear Classification
• Interpreting Blackbox Models via Model Extraction
• Algorithmic recourse under imperfect causal knowledge: a probabilistic approach
• Generating Counterfactual Explanations with Natural Language
• Interpreting Neural Network Judgments via Minimal, Stable, and Symbolic Corrections
• PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction