Inherent Trade-Offs in the Fair Determination of Risk Scores

Abstract

Recent discussion in the public sphere about algorithmic classification has involved tension between competing notions of what it means for a probabilistic classification to be fair to different groups. We formalize three fairness conditions that lie at the heart of these debates, and we prove that except in highly constrained special cases, there is no method that can satisfy these three conditions simultaneously. Moreover, even satisfying all three conditions approximately requires that the data lie in an approximate version of one of the constrained special cases identified by our theorem. These results suggest some of the ways in which key notions of fairness are incompatible with each other, and hence provide a framework for thinking about the trade-offs between them.

To appear in Proceedings of Innovations in Theoretical Computer Science (ITCS), 2017

Cited by in corpus (21)

• Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment
• Fairness in Machine Learning: A Survey
• A Clarification of the Nuances in the Fairness Metrics Landscape
• Fairness in Credit Scoring: Assessment, Implementation and Profit Implications
• An Empirical Characterization of Fair Machine Learning For Clinical Risk Prediction
• Representation Bias in Data: A Survey on Identification and Resolution Techniques
• Towards Guidelines for Assessing Qualities of Machine Learning Systems
• Fairness Score and Process Standardization: Framework for Fairness Certification in Artificial Intelligence Systems
• Fairness in machine learning: against false positive rate equality as a measure of fairness
• Philosophy within Data Science Ethics Courses
• Algorithmic decision making methods for fair credit scoring
• Integrating Psychometrics and Computing Perspectives on Bias and Fairness in Affective Computing: A Case Study of Automated Video Interviews
• Impossibility Results in AI: A Survey
• BeFair: Addressing Fairness in the Banking Sector
• Group Fairness in Prediction-Based Decision Making: From Moral Assessment to Implementation
• Fair-SSL: Building fair ML Software with less data
• From the Fair Distribution of Predictions to the Fair Distribution of Social Goods: Evaluating the Impact of Fair Machine Learning on Long-Term Unemployment
• Ensuring Fairness with Transparent Auditing of Quantitative Bias in AI Systems
• Fairness in Forecasting of Observations of Linear Dynamical Systems
• FairGridSearch: A Framework to Compare Fairness-Enhancing Models
• A Canonical Data Transformation for Achieving Inter- and Within-group Fairness