The demand for transparency and fairness in AI-based decision-making systems is constantly growing. Organisations need to be assured that their applications, based on these technologies, behave fairly, without introducing negative social implications in relation to sensitive attributes such as gender or race. Since the notion of fairness is context dependent and not uniquely defined, studies in the literature have proposed various formalisation. In this work, we propose a novel, flexible, discrimination-aware decision-tree that allows the user to employ different fairness criteria depending on the application domain. Our approach enhances decision-tree classifiers to provide transparent and fair rules to final users.

Castelnovo, A., Cosentini, A., Malandri, L., Mercorio, F., Mezzanzanica, M. (2022). FFTree: A flexible tree to handle multiple fairness criteria. INFORMATION PROCESSING & MANAGEMENT, 59(6 (November 2022)) [10.1016/j.ipm.2022.103099].

FFTree: A flexible tree to handle multiple fairness criteria

Castelnovo, Alessandro
;
Malandri, Lorenzo;Mercorio, Fabio;Mezzanzanica, Mario
2022

Abstract

The demand for transparency and fairness in AI-based decision-making systems is constantly growing. Organisations need to be assured that their applications, based on these technologies, behave fairly, without introducing negative social implications in relation to sensitive attributes such as gender or race. Since the notion of fairness is context dependent and not uniquely defined, studies in the literature have proposed various formalisation. In this work, we propose a novel, flexible, discrimination-aware decision-tree that allows the user to employ different fairness criteria depending on the application domain. Our approach enhances decision-tree classifiers to provide transparent and fair rules to final users.
Articolo in rivista - Articolo scientifico
Discrimination-aware decision tree; Explainable AI; Fairness; Machine learning;
English
7-ott-2022
2022
59
6 (November 2022)
103099
none
Castelnovo, A., Cosentini, A., Malandri, L., Mercorio, F., Mezzanzanica, M. (2022). FFTree: A flexible tree to handle multiple fairness criteria. INFORMATION PROCESSING & MANAGEMENT, 59(6 (November 2022)) [10.1016/j.ipm.2022.103099].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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/10281/393552
Citazioni
  • Scopus 8
  • ???jsp.display-item.citation.isi??? 4
Social impact