# Auditing Predictive Models for Intersectional Biases

arXiv: https://arxiv.org/abs/2306.13064 · HTML: https://mlsanity.com/paper/2306.13064/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 47 references that are in the map.
- First posted on arXiv 22 Jun 2023.

## Builds on (most cited first, 13 of 13)

- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness](https://mlsanity.com/paper/1711.05144/) (2017)
- [Multiaccuracy: Black-Box Post-Processing for Fairness in Classification](https://mlsanity.com/paper/1805.12317/) (2018)
- [An Intersectional Definition of Fairness](https://mlsanity.com/paper/1807.08362/) (2018)
- [Compositional Fairness Constraints for Graph Embeddings](https://mlsanity.com/paper/1905.10674/) (2019)
- [The age of secrecy and unfairness in recidivism prediction](https://mlsanity.com/paper/1811.00731/) (2018)
- [Algorithmic Fairness Datasets: the Story so Far](https://mlsanity.com/paper/2202.01711/) (2022)
- [Evaluating Debiasing Techniques for Intersectional Biases](https://mlsanity.com/paper/2109.10441/) (2021)
- [Identifying Significant Predictive Bias in Classifiers](https://mlsanity.com/paper/1611.08292/) (2016)
- [Fairer and more accurate, but for whom?](https://mlsanity.com/paper/1707.00046/) (2017)
- [Flipping the Script on Criminal Justice Risk Assessment: An actuarial model for assessing the risk the federal sentencing system poses to defendants](https://mlsanity.com/paper/2205.13505/) (2022)
- [Efficient Discovery of Heterogeneous Quantile Treatment Effects in Randomized Experiments via Anomalous Pattern Detection](https://mlsanity.com/paper/1803.09159/) (2018)

## Abstract (arXiv)

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), a flexible auditing framework for detecting intersectional biases in classification models. CBS identifies the subgroup for which there is the most significant bias against the protected class, as 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 previously unidentified intersectional and contextual biases in the COMPAS pre-trial risk assessment tool and has higher bias detection power compared to similar methods that audit for subgroup fairness.