This paper proposes a robust, reliable, and reproducible methodology for evaluating group fairness in classification algorithms. Building upon established theoretical definitions of non-discrimination criteria -Independence, Separation, and Sufficiency- we present a comprehensive approach to quantifying fairness. Notably, our methodology extends beyond binary group comparisons to accommodate scenarios with multiple sensitive groups. Furthermore, we provide a methodological approach for assessing fairness within the Sufficiency criterion by operationalizing Calibration, elucidating critical issues and conceptual subtleties that appear to have been overlooked in existing literature. We assess the reliability and robustness of our model through applications to one real dataset.

Multi-Group Fairness Measures for Classification / M. Mancini, D. Merlini, M. C. Verri. - ELETTRONICO. - (2026), pp. 1155-1162. [10.5220/0015183800004091]

Multi-Group Fairness Measures for Classification

M. Mancini
;
D. Merlini;M. C. Verri
2026

Abstract

This paper proposes a robust, reliable, and reproducible methodology for evaluating group fairness in classification algorithms. Building upon established theoretical definitions of non-discrimination criteria -Independence, Separation, and Sufficiency- we present a comprehensive approach to quantifying fairness. Notably, our methodology extends beyond binary group comparisons to accommodate scenarios with multiple sensitive groups. Furthermore, we provide a methodological approach for assessing fairness within the Sufficiency criterion by operationalizing Calibration, elucidating critical issues and conceptual subtleties that appear to have been overlooked in existing literature. We assess the reliability and robustness of our model through applications to one real dataset.
2026
Proceedings of the 15th International Conference on Data Science,Technology and Applications, {DATA} 2026, Porto, Portugal, July 16-18,2026, Volume 2
1155
1162
M. Mancini; D. Merlini; M. C. Verri
File in questo prodotto:
File Dimensione Formato  
multigroup.pdf

accesso aperto

Descrizione: Multi-group Fairness Measures for Classification
Tipologia: Pdf editoriale (Version of record)
Licenza: Open Access
Dimensione 316.49 kB
Formato Adobe PDF
316.49 kB Adobe PDF

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

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1500542
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact