With the support of the legally-grounded methodology of situation testing, we tackle the problems of discrimination discovery and prevention from a dataset of historical decisions by adopting a variant of k-NN classification. A tuple is labeled as discriminated if we can observe a significant difference of treatment among its neighbors belonging to a protected-by-law group and its neighbors not belonging to it. Discrimination discovery boils down to extracting a classification model from the labeled tuples. Discrimination prevention is tackled by changing the decision value for tuples labeled as discriminated before training a classifier. The approach of this paper overcomes legal weaknesses and technical limitations of existing proposals.

k-NN as an Implementation of Situation Testing for Discrimination Discovery and Prevention

RUGGIERI, SALVATORE;TURINI, FRANCO
2011-01-01

Abstract

With the support of the legally-grounded methodology of situation testing, we tackle the problems of discrimination discovery and prevention from a dataset of historical decisions by adopting a variant of k-NN classification. A tuple is labeled as discriminated if we can observe a significant difference of treatment among its neighbors belonging to a protected-by-law group and its neighbors not belonging to it. Discrimination discovery boils down to extracting a classification model from the labeled tuples. Discrimination prevention is tackled by changing the decision value for tuples labeled as discriminated before training a classifier. The approach of this paper overcomes legal weaknesses and technical limitations of existing proposals.
2011
9781450308137
File in questo prodotto:
File Dimensione Formato  
kdd2011.pdf

non disponibili

Tipologia: Documento in Post-print
Licenza: Importato da Ugov Ricerca - Accesso privato/ristretto
Dimensione 747.85 kB
Formato Adobe PDF
747.85 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11568/194066
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 174
  • ???jsp.display-item.citation.isi??? ND
social impact