Achieving Fairness through Adversarial Learning: an Application to Recidivism Prediction

2018/06/30 by Christina Wadsworth, Wadsworth, Christina, Francesca Vera +3 · 9 citations
Computer Science · Mathematics · Social Sciences · #Adversarial Robustness in Machine Learning #Criminal Justice and Corrections Analysis #Ethics and Social Impacts of AI #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.1807.00199

To be published in FAT/ML, 2018, Stockholm, Sweden

arxiv created 2018/06/30 · openalex publication_date 2018/06/30 · arxiv updated 2018/07/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Recidivism prediction scores are used across the USA to determine sentencing and supervision for hundreds of thousands of inmates. One such generator of recidivism prediction scores is Northpointe's Correctional Offender Management Profiling for Alternative Sanctions (COMPAS) score, used in states like California and Florida, which past research has shown to be biased against black inmates according to certain measures of fairness. To counteract this racial bias, we present an adversarially-trained neural network that predicts recidivism and is trained to remove racial bias. When comparing the results of our model to COMPAS, we gain predictive accuracy and get closer to achieving two out of three measures of fairness: parity and equality of odds. Our model can be generalized to any prediction and demographic. This piece of research contributes an example of scientific replication and simplification in a high-stakes real-world application like recidivism prediction.

Citations

• A statistical framework for fair predictive algorithms
• Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations

Cited by

• Personalized Pricing in Social Networks with Individual and Group Fairness Considerations
• Machine Learning with Multitype Protected Attributes: Intersectional Fairness through Regularisation
• Explaining How Quantization Disparately Skews a Model
• FairDRL-ST: Disentangled Representation Learning for Fair Spatio-Temporal Mobility Prediction
• End-To-End Bias Mitigation: Removing Gender Bias in Deep Learning
• AI Fairness via Domain Adaptation
• A Tale of Fairness Revisited: Beyond Adversarial Learning for Deep Neural Network Fairness
• Fairness Score and Process Standardization: Framework for Fairness Certification in Artificial Intelligence Systems
• General Post-Processing Framework for Fairness Adjustment of Machine Learning Models

Related

• Evaluating the Tradeoff Between Predictive Accuracy and Racial Fairness in Machine Learning-Based Recidivism Models
• Algorithmic Bias in Recidivism Prediction: A Causal Perspective
• Detecting Statistically Significant Fairness Violations in Recidivism Forecasting Algorithms
• An algorithm for removing sensitive information: application to race-independent recidivism prediction
• Accuracy, Fairness, and Interpretability of Machine Learning Criminal Recidivism Models