Algorithmic Bias in Recidivism Prediction: A Causal Perspective
This addresses algorithmic fairness in criminal justice for policymakers and researchers, though it is incremental as it applies an existing causal method to a known dataset.
The authors tackled the problem of racial bias in COMPAS recidivism predictions by applying a causal fairness measure (FACT) using the Neyman-Rubin framework, finding strong evidence of bias against African American defendants with robustness to unmeasured confounding.
ProPublica's analysis of recidivism predictions produced by Correctional Offender Management Profiling for Alternative Sanctions (COMPAS) software tool for the task, has shown that the predictions were racially biased against African American defendants. We analyze the COMPAS data using a causal reformulation of the underlying algorithmic fairness problem. Specifically, we assess whether COMPAS exhibits racial bias against African American defendants using FACT, a recently introduced causality grounded measure of algorithmic fairness. We use the Neyman-Rubin potential outcomes framework for causal inference from observational data to estimate FACT from COMPAS data. Our analysis offers strong evidence that COMPAS exhibits racial bias against African American defendants. We further show that the FACT estimates from COMPAS data are robust in the presence of unmeasured confounding.