Explaining contributions of features towards unfairness in classifiers: A novel threshold-dependent Shapley value-based approach

Pelegrina, G.D., Siraj, S. orcid.org/0000-0002-7962-9930, Duarte, L.T. et al. (1 more author) (2024) Explaining contributions of features towards unfairness in classifiers: A novel threshold-dependent Shapley value-based approach. Engineering Applications of Artificial Intelligence, 138 (Part B). 109427. ISSN 0952-1976

Abstract

Metadata

Item Type: Article
Authors/Creators:
Copyright, Publisher and Additional Information:

© 2024, Elsevier. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/. This is an author produced version of an article published in Engineering Applications of Artificial Intelligence. Uploaded in accordance with the publisher's self-archiving policy.

Keywords: Interpretable machine learning; Shapley value; Fairness; Feature contribution
Dates:
  • Published: December 2024
  • Published (online): 5 October 2024
  • Accepted: 1 October 2024
Institution: The University of Leeds
Academic Units: The University of Leeds > Faculty of Business (Leeds) > Analytics, Technology & Ops Department
Depositing User: Symplectic Publications
Date Deposited: 07 Oct 2024 15:54
Last Modified: 18 Oct 2024 14:59
Published Version: https://www.sciencedirect.com/science/article/pii/...
Status: Published
Publisher: Elsevier
Identification Number: 10.1016/j.engappai.2024.109427
Open Archives Initiative ID (OAI ID):

Download

Accepted Version


Embargoed until: 5 October 2025

Filename: 2024 FairSHAP EAAI.pdf

Licence: CC-BY-NC-ND 4.0

Request a copy

file not available

Export

Statistics