Algorithmic Fairness and Base Rate Tracking.
Fourth, note that as well as requiring that the average risk scores be equal when the base rates are, base rate tracking also requires the converse, i.e., that when the risk scores are equal, the base rates should be too. For instance, if an algorithm assigns radically different average risk scores...
| Publicado en: | Philosophy & Public Affairs Vol. 50; no. 2; pp. 239 - 267 |
|---|---|
| Formato: | Artículo |
| Publicado: |
Wiley-Blackwell
Spring2022
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=156113739&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 156113739 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 00483915 PPA jtl: Philosophy & Public Affairs issn: 00483915 maglogo: Y pubinfo: dt: Spring2022 vid: 50 iid: 2 pid: 480 pub: Wiley-Blackwell artinfo: ui: 156113739 10.1111/papa.12211 ppf: 239 ppct: 28 formats: fmt: – @attributes: type: T – @attributes: type: P size: 150KB tig: atl: Algorithmic Fairness and Base Rate Tracking. aug: su: Fairness Disease risk factors Intuition Classification algorithms sug: subj: Fairness Disease risk factors Intuition Classification algorithms ab: Fourth, note that as well as requiring that the average risk scores be equal when the base rates are, base rate tracking also requires the converse, i.e., that when the risk scores are equal, the base rates should be too. For instance, if an algorithm assigns radically different average risk scores to two groups with the same long run expected base rates, then there is something intrinsically unfair about the way that the algorithm makes its judgments, in the sense that no algorithm with this property can be perfectly fair, regardless of the details of its social/historical context etc. Since the base rates for the two rooms in Hedden's coin flip example are equal to the average risk scores assigned to the people in those rooms, base rate tracking is trivially satisfied by the optimal predictive algorithm. In contrast, when the algorithm in Redlining 1 assigned black applicants a risk score that was higher than their white counterparts in a manner that could not be justified by a comparable disparity in their base rates, that was a case in which the algorithm's predictions were themselves intrinsically unfair, and could be identified as such on the basis of purely statistical criteria. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y custom: Copyright of Philosophy & Public Affairs is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. item: Philosophy & Public Affairs holder: Wiley-Blackwell dt: @attributes: year: 2022 holdings: @attributes: islocal: N |
|---|