2019/05/25 by Omer Ben-Porat, Fedor Sandomirskiy, Ben-Porat, Omer +3 · 1 citation
Computer Science · Social Sciences · #Blockchain Technology Applications and Security #Computer Science and Game Theory (cs.GT) #Ethics and Social Impacts of AI #FOS: Computer and information sciences #Machine Learning (cs.LG) #cs.GT #cs.LG
paper · pdf · doi:10.48550/arxiv.1905.10546
Published in AAAI 2021
openalex publication_date 2019/05/25 · arxiv created 2021/01/04 · arxiv updated 2021/01/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Machine Learning (ML) algorithms shape our lives. Banks use them to determine if we are good borrowers; IT companies delegate them recruitment decisions; police apply ML for crime-prediction, and judges base their verdicts on ML. However, real-world examples show that such automated decisions tend to discriminate against protected groups. This potential discrimination generated a huge hype both in media and in the research community. Quite a few formal notions of fairness were proposed, which take a form of constraints a "fair" algorithm must satisfy. We focus on scenarios where fairness is imposed on a self-interested party (e.g., a bank that maximizes its revenue). We find that the disadvantaged protected group can be worse off after imposing a fairness constraint. We introduce a family of Welfare-Equalizing fairness constraints that equalize per-capita welfare of protected groups, and include Demographic Parity and Equal Opportunity as particular cases. In this family, we characterize conditions under which the fairness constraint helps the disadvantaged group. We also characterize the structure of the optimal Welfare-Equalizing classifier for the self-interested party, and provide an algorithm to compute it. Overall, our Welfare-Equalizing fairness approach provides a unified framework for discussing fairness in classification in the presence of a self-interested party.