Fairness in Algorithmic Decision Making: An Excursion Through the Lens of Causality

Abstract

As virtually all aspects of our lives are increasingly impacted by algorithmic decision making systems, it is incumbent upon us as a society to ensure such systems do not become instruments of unfair discrimination on the basis of gender, race, ethnicity, religion, etc. We consider the problem of determining whether the decisions made by such systems are discriminatory, through the lens of causal models. We introduce two definitions of group fairness grounded in causality: fair on average causal effect (FACE), and fair on average causal effect on the treated (FACT). We use the Rubin-Neyman potential outcomes framework for the analysis of cause-effect relationships to robustly estimate FACE and FACT. We demonstrate the effectiveness of our proposed approach on synthetic data. Our analyses of two real-world data sets, the Adult income data set from the UCI repository (with gender as the protected attribute), and the NYC Stop and Frisk data set (with race as the protected attribute), show that the evidence of discrimination obtained by FACE and FACT, or lack thereof, is often in agreement with the findings from other studies. We further show that FACT, being somewhat more nuanced compared to FACE, can yield findings of discrimination that differ from those obtained using FACE.

7 pages, 2 figures, 2 tables.To appear in Proceedings of the International Conference on World Wide Web (WWW), 2019

References in corpus (13)

• Matching Methods for Causal Inference: A Review and a Look Forward
• Equality of Opportunity in Supervised Learning
• Counterfactual Fairness
• Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment
• Fairness Constraints: Mechanisms for Fair Classification
• Avoiding Discrimination through Causal Reasoning
• The Variational Fair Autoencoder
• A survey on measuring indirect discrimination in machine learning
• Exposing the Probabilistic Causal Structure of Discrimination
• Causal Reasoning for Algorithmic Fairness
• Fairness in Criminal Justice Risk Assessments: The State of the Art
• Causal Interventions for Fairness
• Big Data, Data Science, and Civil Rights

Cited by in corpus (15)

• Personalized Counterfactual Fairness in Recommendation
• Machine learning fairness notions: Bridging the gap with real-world applications
• Outcome-Explorer: A Causality Guided Interactive Visual Interface for Interpretable Algorithmic Decision Making
• Survey on Causal-based Machine Learning Fairness Notions
• FairBatch: Batch Selection for Model Fairness
• On Consequentialism and Fairness
• What-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspective
• FR-Train: A Mutual Information-Based Approach to Fair and Robust Training
• Path-Specific Counterfactual Fairness for Recommender Systems
• The Fairness-Accuracy Pareto Front
• A Causal Lens for Peeking into Black Box Predictive Models: Predictive Model Interpretation via Causal Attribution
• The Danger of Reverse-Engineering of Automated Judicial Decision-Making Systems
• Algorithmic Bias in Recidivism Prediction: A Causal Perspective
• Locating disparities in machine learning
• Learning Fair Representations for Recommendation: A Graph-based Perspective