Auditing ML Models for Individual Bias and Unfairness

Abstract

We consider the task of auditing ML models for individual bias/unfairness. We formalize the task in an optimization problem and develop a suite of inferential tools for the optimal value. Our tools permit us to obtain asymptotic confidence intervals and hypothesis tests that cover the target/control the Type I error rate exactly. To demonstrate the utility of our tools, we use them to reveal the gender and racial biases in Northpointe’s COMPAS recidivism prediction instrument.

Cite

Text

Xue et al. "Auditing ML Models for Individual Bias and Unfairness." Artificial Intelligence and Statistics, 2020.

Markdown

[Xue et al. "Auditing ML Models for Individual Bias and Unfairness." Artificial Intelligence and Statistics, 2020.](https://mlanthology.org/aistats/2020/xue2020aistats-auditing/)

BibTeX

@inproceedings{xue2020aistats-auditing,
  title     = {{Auditing ML Models for Individual Bias and Unfairness}},
  author    = {Xue, Songkai and Yurochkin, Mikhail and Sun, Yuekai},
  booktitle = {Artificial Intelligence and Statistics},
  year      = {2020},
  pages     = {4552-4562},
  volume    = {108},
  url       = {https://mlanthology.org/aistats/2020/xue2020aistats-auditing/}
}