Fair Prediction with Endogenous Behavior
Theoretical Economics
2020-02-19 v1 Artificial Intelligence
Computer Science and Game Theory
Machine Learning
Econometrics
Abstract
There is increasing regulatory interest in whether machine learning algorithms deployed in consequential domains (e.g. in criminal justice) treat different demographic groups "fairly." However, there are several proposed notions of fairness, typically mutually incompatible. Using criminal justice as an example, we study a model in which society chooses an incarceration rule. Agents of different demographic groups differ in their outside options (e.g. opportunity for legal employment) and decide whether to commit crimes. We show that equalizing type I and type II errors across groups is consistent with the goal of minimizing the overall crime rate; other popular notions of fairness are not.
Cite
@article{arxiv.2002.07147,
title = {Fair Prediction with Endogenous Behavior},
author = {Christopher Jung and Sampath Kannan and Changhwa Lee and Mallesh M. Pai and Aaron Roth and Rakesh Vohra},
journal= {arXiv preprint arXiv:2002.07147},
year = {2020}
}