# Algorithmic Bias in Recidivism Prediction: A Causal Perspective

arXiv: https://arxiv.org/abs/1911.10640 · HTML: https://mlsanity.com/paper/1911.10640/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2019.

## Built on by (most cited first, 7 of 7)

- [The Political Preferences of LLMs](https://mlsanity.com/paper/2402.01789/) (2024)
- [AcceleratedLiNGAM: Learning Causal DAGs at the speed of GPUs](https://mlsanity.com/paper/2403.03772/) (2024)
- [Machine Learning with Multitype Protected Attributes: Intersectional Fairness through Regularisation](https://mlsanity.com/paper/2509.08163/) (2025)
- [Argumentative Debates for Transparent Bias Detection [Technical Report]](https://mlsanity.com/paper/2508.04511/) (2025)
- [Counterfactual Fairness in Mortgage Lending via Matching and Randomization](https://mlsanity.com/paper/2112.02170/) (2021)
- [Recovering Fairness Directly from Modularity: a New Way for Fair Community Partitioning](https://mlsanity.com/paper/2505.22684/) (2025)
- [A Blended Likelihood Approach for Achieving Fairness Using Naive Bayes](https://mlsanity.com/paper/2605.25228/) (2026)

## Abstract (arXiv)

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.