Algorithmic bias mitigation has been one of the most difficult conundrums for the data science community and Machine Learning (ML) experts. Over several years, there have appeared enormous efforts in the field of fairness in ML. Despite the progress toward identifying biases and designing fair algorithms, translating them into the industry remains a major challenge. In this paper, we present the initial results of an industrial open innovation project in the banking sector: we propose a general roadmap for fairness in ML and the implementation of a toolkit called BeFair that helps to identify and mitigate bias. Results show that training a model without explicit constraints may lead to bias exacerbation in the predictions.
Castelnovo, A., Crupi, R., Gamba, G., Greco, G., Naseer, A., Regoli, D., et al. (2020). BeFair: Addressing Fairness in the Banking Sector. In Proceedings - 2020 IEEE International Conference on Big Data, Big Data 2020 (pp.3652-3661). New York : Institute of Electrical and Electronics Engineers Inc. [10.1109/BigData50022.2020.9377894].
BeFair: Addressing Fairness in the Banking Sector
Castelnovo A.;Greco G.;
2020
Abstract
Algorithmic bias mitigation has been one of the most difficult conundrums for the data science community and Machine Learning (ML) experts. Over several years, there have appeared enormous efforts in the field of fairness in ML. Despite the progress toward identifying biases and designing fair algorithms, translating them into the industry remains a major challenge. In this paper, we present the initial results of an industrial open innovation project in the banking sector: we propose a general roadmap for fairness in ML and the implementation of a toolkit called BeFair that helps to identify and mitigate bias. Results show that training a model without explicit constraints may lead to bias exacerbation in the predictions.File | Dimensione | Formato | |
---|---|---|---|
BeFair_Addressing_Fairness_in_the_Banking_Sector.pdf
accesso aperto
Tipologia di allegato:
Publisher’s Version (Version of Record, VoR)
Dimensione
1.51 MB
Formato
Adobe PDF
|
1.51 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.