Achieving Fairness through Adversarial Learning: an Application to Recidivism Prediction

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.

arXiv commentTo be published in FAT/ML, 2018, Stockholm, Sweden

References in corpus (4)

• Equality of Opportunity in Supervised Learning
• Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations
• A statistical framework for fair predictive algorithms
• Fairer and more accurate, but for whom?

Cited by in corpus (30)

• Fairness in Machine Learning: A Survey
• Towards Equity and Algorithmic Fairness in Student Grade Prediction
• Fairness Score and Process Standardization: Framework for Fairness Certification in Artificial Intelligence Systems
• Fairness via Representation Neutralization
• Improved Adversarial Learning for Fair Classification
• DVR: Micro-Video Recommendation Optimizing Watch-Time-Gain under Duration Bias
• Fairness without the sensitive attribute via Causal Variational Autoencoder
• End-To-End Bias Mitigation: Removing Gender Bias in Deep Learning
• FairRec: Fairness-aware News Recommendation with Decomposed Adversarial Learning
• Adversarial training approach for local data debiasing
• Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning
• Removing the influence of a group variable in high-dimensional predictive modelling
• Towards Accuracy-Fairness Paradox: Adversarial Example-based Data Augmentation for Visual Debiasing
• Removing biased data to improve fairness and accuracy
• Modeling Techniques for Machine Learning Fairness: A Survey
• AI Fairness via Domain Adaptation
• Fair-by-design explainable models for prediction of recidivism
• Fairness-Aware Neural Réyni Minimization for Continuous Features
• The Fairness-Accuracy Pareto Front
• Fairness in Missing Data Imputation
• Towards a Measure of Individual Fairness for Deep Learning
• Additive Adversarial Learning for Unbiased Authentication
• Equality of opportunity in travel behavior prediction with deep neural networks and discrete choice models
• Using Adversarial Debiasing to Remove Bias from Word Embeddings
• Adaptation and Generalization for Unknown Sensitive Factors of Variations
• Fairness-aware Summarization for Justified Decision-Making
• Debiasing Convolutional Neural Networks via Meta Orthogonalization
• Towards Auditability for Fairness in Deep Learning
• Stochastic Projective Splitting: Solving Saddle-Point Problems with Multiple Regularizers
• A Tale of Fairness Revisited: Beyond Adversarial Learning for Deep Neural Network Fairness