License: Creative Commons Attribution 3.0 Unported license (CC BY 3.0)
When quoting this document, please refer to the following
DOI: 10.4230/LIPIcs.ITCS.2017.43
URN: urn:nbn:de:0030-drops-81560
URL: http://dagstuhl.sunsite.rwth-aachen.de/volltexte/2017/8156/
Go to the corresponding LIPIcs Volume Portal

Kleinberg, Jon ; Mullainathan, Sendhil ; Raghavan, Manish

Inherent Trade-Offs in the Fair Determination of Risk Scores

pdf-format:
LIPIcs-ITCS-2017-43.pdf (0.5 MB)

Abstract

Recent discussion in the public sphere about algorithmic classification has involved tension between competing notions of what it means for a probabilistic classification to be fair to different groups. We formalize three fairness conditions that lie at the heart of these debates, and we prove that except in highly constrained special cases, there is no method that can satisfy these three conditions simultaneously. Moreover, even satisfying all three conditions approximately requires that the data lie in an approximate version of one of the constrained special cases identified by our theorem. These results suggest some of the ways in which key notions of fairness are incompatible with each other, and hence provide a framework for thinking about the trade-offs between them.

BibTeX - Entry

@InProceedings{kleinberg_et_al:LIPIcs:2017:8156,
  author =	{Jon Kleinberg and Sendhil Mullainathan and Manish Raghavan},
  title =	{{Inherent Trade-Offs in the Fair Determination of Risk Scores}},
  booktitle =	{8th Innovations in Theoretical Computer Science Conference (ITCS 2017)},
  pages =	{43:1--43:23},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-029-3},
  ISSN =	{1868-8969},
  year =	{2017},
  volume =	{67},
  editor =	{Christos H. Papadimitriou},
  publisher =	{Schloss Dagstuhl--Leibniz-Zentrum fuer Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{http://drops.dagstuhl.de/opus/volltexte/2017/8156},
  URN =		{urn:nbn:de:0030-drops-81560},
  doi =		{10.4230/LIPIcs.ITCS.2017.43},
  annote =	{Keywords: algorithmic fairness, risk tools, calibration}
}

Keywords: algorithmic fairness, risk tools, calibration
Collection: 8th Innovations in Theoretical Computer Science Conference (ITCS 2017)
Issue Date: 2017
Date of publication: 28.11.2017

DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI