Fairness in Algorithmic Decision Making: An Excursion Through the Lens of Causality
This work addresses fairness in AI for society, but it is incremental as it builds on existing causal frameworks to propose new definitions without major breakthroughs.
The paper tackles the problem of detecting unfair discrimination in algorithmic decision-making by introducing two causality-based fairness definitions, FACE and FACT, and applies them to synthetic and real-world datasets like Adult income and NYC Stop and Frisk, showing agreement with other studies and nuanced differences between the definitions.
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.