Fairness Behind a Veil of Ignorance: A Welfare Analysis for Automated Decision Making

Abstract

We draw attention to an important, yet largely overlooked aspect of evaluating fairness for automated decision making systems---namely risk and welfare considerations. Our proposed family of measures corresponds to the long-established formulations of cardinal social welfare in economics, and is justified by the Rawlsian conception of fairness behind a veil of ignorance. The convex formulation of our welfare-based measures of fairness allows us to integrate them as a constraint into any convex loss minimization pipeline. Our empirical analysis reveals interesting trade-offs between our proposal and (a) prediction accuracy, (b) group discrimination, and (c) Dwork et al.'s notion of individual fairness. Furthermore and perhaps most importantly, our work provides both heuristic justification and empirical evidence suggesting that a lower-bound on our measures often leads to bounded inequality in algorithmic outcomes; hence presenting the first computationally feasible mechanism for bounding individual-level inequality.

arXiv commentConference: Thirty-second Conference on Neural Information Processing Systems (NIPS 2018)

References in corpus (1)

• Equality of Opportunity in Supervised Learning

Cited by in corpus (8)

• Fairness in Machine Learning: A Survey
• A survey on datasets for fairness-aware machine learning
• Noise-tolerant fair classification
• Regulatory Instruments for Fair Personalized Pricing
• Disaggregated Interventions to Reduce Inequality
• An Axiomatic Theory of Provably-Fair Welfare-Centric Machine Learning
• Fair Classification and Social Welfare
• Fairness Through Counterfactual Utilities