Fiche du document
16 février 2024
- doi: 10.58079/vuwh
Ce document est lié à :
info:eu-repo/semantics/reference/issn/2262-6891
info:eu-repo/semantics/openAccess
Sujets proches
Impartiality BiasCiter ce document
Arthur Charpentier, « Fairness and discrimination, PhD Course, #7 Sensitive attributes and proxies », Freakonometrics, ID : 10.58079/vuwh
Métriques
Partage / Export
Résumé
In our previous post, we discussed "group fairness". I might have gone a bit fast, and I decided to add some material about sensistive attributes, and proxies. Sensitive attributes ? Almost everywhere, we can find a list of variables that are considered, by law, as sensitive, since they will lead to discrimination. As mentioned earlier, sensitive variable might change with time, and accross regions... Another issue with black boxes is that it might be hard to assess if they are related to s...