Certifying and removing disparate impact

Michael Feldman, Sorelle A. Friedler, John Moeller, Carlos Scheidegger, Suresh Venkatasubramanian

Research output: Chapter in Book/Report/Conference proceedingConference contribution

569 Scopus citations

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) and an explicit description of the process. When computers are involved, 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 process, we propose making inferences based on the data it uses. We present four contributions. First, we link disparate impact to a measure of classification accuracy that while known, has received relatively little attention. Second, we propose a test for disparate impact based on how well the protected class can be predicted from the other attributes. Third, we describe methods by which data might be made unbiased. Finally, we present empirical evidence supporting the effectiveness of our test for disparate impact and our approach for both masking bias and preserving relevant information in the data. Interestingly, our approach resembles some actual selection practices that have recently received legal scrutiny.

Original languageEnglish (US)
Title of host publicationKDD 2015 - Proceedings of the 21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining
PublisherAssociation for Computing Machinery
Pages259-268
Number of pages10
ISBN (Electronic)9781450336642
DOIs
StatePublished - Aug 10 2015
Event21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2015 - Sydney, Australia
Duration: Aug 10 2015Aug 13 2015

Publication series

NameProceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Volume2015-August

Other

Other21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2015
CountryAustralia
CitySydney
Period8/10/158/13/15

Keywords

  • Disparate impact
  • Fairness
  • Machine learning

ASJC Scopus subject areas

  • Software
  • Information Systems

Fingerprint Dive into the research topics of 'Certifying and removing disparate impact'. Together they form a unique fingerprint.

Cite this