Auditing Predictive Models for Intersectional Biases

Kate Boxer, Edward McFowland III, Daniel B. Neill

Keywords: predictive bias detection, fairness auditing, intersectional bias, contextual bias, group fairness definitions, subgroup bias, predictive bias

TL;DR: Conditional Bias Scan is an auditing framework for detecting intersectional and subgroup biases in classifiers' predictions.

Abstract: Predictive models that satisfy group fairness criteria in aggregate for members of a protected class, but do not guarantee subgroup fairness, could produce biased predictions for individuals at the intersection of two or more protected classes. To address this risk, we propose Conditional Bias Scan (CBS), an auditing framework for detecting intersectional biases in classification models. CBS identifies the subgroup with the most significant bias against the protected class, compared to the equivalent subgroup in the non-protected class, and can incorporate multiple commonly used fairness definitions for both probabilistic and binarized predictions. We show that this methodology can detect subgroup biases in the COMPAS pre-trial risk assessment tool and in German Credit Data, and has higher bias detection power compared to similar methods that audit for subgroup fairness.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 7474