Hunting for Discriminatory Proxies in Linear Regression Models
This work addresses the issue of discriminatory outcomes in AI decision-making for affected populations, offering a method to analyze and mitigate bias, though it is incremental by extending proxy detection from classification to regression.
The paper tackles the problem of discrimination in machine learning models by defining and detecting statistical proxies for protected attributes in linear regression, presenting algorithms that efficiently identify such proxies via second-order cone programming and demonstrating their utility on law enforcement datasets with racial disparities.
A machine learning model may exhibit discrimination when used to make decisions involving people. One potential cause for such outcomes is that the model uses a statistical proxy for a protected demographic attribute. In this paper we formulate a definition of proxy use for the setting of linear regression and present algorithms for detecting proxies. Our definition follows recent work on proxies in classification models, and characterizes a model's constituent behavior that: 1) correlates closely with a protected random variable, and 2) is causally influential in the overall behavior of the model. We show that proxies in linear regression models can be efficiently identified by solving a second-order cone program, and further extend this result to account for situations where the use of a certain input variable is justified as a `business necessity'. Finally, we present empirical results on two law enforcement datasets that exhibit varying degrees of racial disparity in prediction outcomes, demonstrating that proxies shed useful light on the causes of discriminatory behavior in models.