The Illusion of Fairness: Auditing Fairness Interventions with Audit Studies

TL;DR

This paper demonstrates that audit study data can reveal hidden biases in fairness interventions for AI hiring systems and proposes new methods to reduce discrimination more effectively.

Contribution

It introduces a novel approach using audit study data to evaluate and improve fairness interventions in AI hiring algorithms, revealing limitations of traditional metrics.

Findings

Traditional fairness measures can be misleading without audit data

Audit data uncovers approximately 10% residual disparity in fairness interventions

New treatment effect estimation methods further reduce algorithmic discrimination

Abstract

Artificial intelligence systems, especially those using machine learning, are being deployed in domains from hiring to loan issuance in order to automate these complex decisions. Judging both the effectiveness and fairness of these AI systems, and their human decision making counterpart, is a complex and important topic studied across both computational and social sciences. Within machine learning, a common way to address bias in downstream classifiers is to resample the training data to offset disparities. For example, if hiring rates vary by some protected class, then one may equalize the rate within the training set to alleviate bias in the resulting classifier. While simple and seemingly effective, these methods have typically only been evaluated using data obtained through convenience samples, introducing selection bias and label bias into metrics. Within the social sciences, psychology, public health, and medicine, audit studies, in which fictitious ``testers'' (e.g., resumes, emails, patient actors) are sent to subjects (e.g., job openings, businesses, doctors) in randomized control trials, provide high quality data that support rigorous estimates of discrimination. In this paper, we investigate how data from audit studies can be used to improve our ability to both train and evaluate automated hiring algorithms. We find that such data reveals cases where the common fairness intervention method of equalizing base rates across classes appears to achieve parity using traditional measures, but in fact has roughly 10% disparity when measured appropriately. We additionally introduce interventions based on individual treatment effect estimation methods that further reduce algorithmic discrimination using this data.