paper-with-me

Papers

Achieving Fairness through Adversarial Learning: an Application to Recidivism Prediction

2018-06-30 · Christina Wadsworth, Francesca Vera, Chris Piech

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.

📄 PDF Abstract BibTeX arXiv:1807.00199

Code (2)

dns43/fairness tf
istaustria-cvml/flea jax

Tasks

FairnessManagementPrediction

Similar Papers 제목 키워드 기반

Counterfactual Fairness for Predictions using Generative Adversarial Networks

2023-10-26 · Yuchen Ma, Dennis Frauen, Valentyn Melnychuk, Stefan Feuerriegel

Fairness in predictions is of direct importance in practice due to legal, ethical, and societal reasons. It is often achieved through counterfactual fairness, which ensures that the prediction for an individual is the sa…

AttributecounterfactualFairnessGenerative Adversarial Network

Multi-Differential Fairness Auditor for Black Box Classifiers

2019-03-18 · Xavier Gitiaux, Huzefa Rangwala

Machine learning algorithms are increasingly involved in sensitive decision-making process with adversarial implications on individuals. This paper presents mdfa, an approach that identifies the characteristics of the vi…

Decision MakingFairness

Accuracy, Fairness, and Interpretability of Machine Learning Criminal Recidivism Models

2022-09-14 · Eric Ingram, Furkan Gursoy, Ioannis A. Kakadiaris

Criminal recidivism models are tools that have gained widespread adoption by parole boards across the United States to assist with parole decisions. These models take in large amounts of data about an individual and then…

Fairness

Fair prediction with disparate impact: A study of bias in recidivism prediction instruments

2017-02-28 · Alexandra Chouldechova

Recidivism prediction instruments (RPI's) provide decision makers with an assessment of the likelihood that a criminal defendant will reoffend at a future point in time. While such instruments are gaining increasing popu…

FairnessPrediction

Fair prediction with disparate impact: A study of bias in recidivism prediction instruments

2016-10-24 · Alexandra Chouldechova

Recidivism prediction instruments provide decision makers with an assessment of the likelihood that a criminal defendant will reoffend at a future point in time. While such instruments are gaining increasing popularity a…

FairnessPrediction