Certifying and removing disparate impact
Michael Feldman, Sorelle Friedler, John Moeller, Carlos, Scheidegger, Suresh Venkatasubramanian

TL;DR
This paper introduces a method to detect and mitigate algorithmic bias related to disparate impact by analyzing data attributes, providing a legal-aligned, data-driven approach that does not require access to the algorithm itself.
Contribution
It links legal concepts of bias to classification accuracy, proposes a test based on information leakage, and offers methods to make data unbiased, supported by empirical evidence.
Findings
The proposed test effectively detects disparate impact.
Methods can mask bias while preserving data utility.
Empirical results validate the approach's effectiveness.
Abstract
What does it mean for an algorithm to be biased? In U.S. law, unintentional bias is encoded via disparate impact, which occurs when a selection process has widely different outcomes for different groups, even as it appears to be neutral. This legal determination hinges on a definition of a protected class (ethnicity, gender, religious practice) and an explicit description of the process. When the process is implemented using computers, determining disparate impact (and hence bias) is harder. It might not be possible to disclose the process. In addition, even if the process is open, it might be hard to elucidate in a legal setting how the algorithm makes its decisions. Instead of requiring access to the algorithm, we propose making inferences based on the data the algorithm uses. We make four contributions to this problem. First, we link the legal notion of disparate impact to a…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsEthics and Social Impacts of AI · Law, Economics, and Judicial Systems · Judicial and Constitutional Studies
