Equalizing Recourse across Groups

Abstract

The rise in machine learning-assisted decision-making has led to concerns about the fairness of the decisions and techniques to mitigate problems of discrimination. If a negative decision is made about an individual (denying a loan, rejecting an application for housing, and so on) justice dictates that we be able to ask how we might change circumstances to get a favorable decision the next time. Moreover, the ability to change circumstances (a better education, improved credentials) should not be limited to only those with access to expensive resources. In other words, \emph{recourse} for negative decisions should be considered a desirable value that can be equalized across (demographically defined) groups. This paper describes how to build models that make accurate predictions while still ensuring that the penalties for a negative outcome do not disadvantage different groups disproportionately. We measure recourse as the distance of an individual from the decision boundary of a classifier. We then introduce a regularized objective to minimize the difference in recourse across groups. We explore linear settings and further extend recourse to non-linear settings as well as model-agnostic settings where the exact distance from boundary cannot be calculated. Our results show that we can successfully decrease the unfairness in recourse while maintaining classifier performance.

arXiv comment13 pages, 4 figures, 2 tables

References in corpus (6)

• Scikit-learn: Machine Learning in Python
• Actionable Recourse in Linear Classification
• On Fairness and Calibration
• Learning Non-Discriminatory Predictors
• The Disparate Effects of Strategic Manipulation
• Satisfying Real-world Goals with Dataset Constraints

Cited by in corpus (10)

• Algorithmic recourse under imperfect causal knowledge: a probabilistic approach
• Algorithmic Recourse: from Counterfactual Explanations to Interventions
• A survey of algorithmic recourse: definitions, formulations, solutions, and prospects
• CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms
• Information Discrepancy in Strategic Learning
• Counterfactual Explanations Can Be Manipulated
• Linear Classifiers that Encourage Constructive Adaptation
• Strategic Classification Made Practical
• Algorithmic Recourse in Partially and Fully Confounded Settings Through Bounding Counterfactual Effects
• Everything is Relative: Understanding Fairness with Optimal Transport