Group fairness in prediction-based decision making : from moral assessment to implementation

Baumann, Joachim; Heitz, Christoph

doi:10.1109/SDS54800.2022.00011

Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-25910

Full metadata record

DC Field	Value	Language
dc.contributor.author	Baumann, Joachim	-
dc.contributor.author	Heitz, Christoph	-
dc.date.accessioned	2022-11-03T15:39:42Z	-
dc.date.available	2022-11-03T15:39:42Z	-
dc.date.issued	2022	-
dc.identifier.isbn	978-1-6654-6847-3	de_CH
dc.identifier.uri	https://digitalcollection.zhaw.ch/handle/11475/25910	-
dc.description.abstract	Ensuring fairness of prediction-based decision making is based on statistical group fairness criteria. Which one of these criteria is the morally most appropriate one depends on the context, and its choice requires an ethical analysis. In this paper, we present a step-by-step procedure integrating three elements: (a) a framework for the moral assessment of what fairness means in a given context, based on the recently proposed general principle of “Fair equality of chances” (FEC) (b) a mapping of the assessment's results to established statistical group fairness criteria, and (c) a method for integrating the thus-defined fairness into optimal decision making. As a second contribution, we show new applications of the FEC principle and show that, with this extension, the FEC framework covers all types of group fairness criteria: independence, separation, and sufficiency. Third, we introduce an extended version of the FEC principle, which additionally allows accounting for morally irrelevant elements of the fairness assessment and links to well-known relaxations of the fairness criteria. This paper presents a framework to develop fair decision systems in a conceptually sound way, combining the moral and the computational elements of fair prediction-based decision-making in an integrated approach. Data and code to reproduce our results are available at https://github.com/joebaumann/fair-prediction-based-decision-making.	de_CH
dc.language.iso	en	de_CH
dc.publisher	IEEE	de_CH
dc.rights	Licence according to publishing contract	de_CH
dc.subject	Algorithmic fairness	de_CH
dc.subject	Prediction-based decision making	de_CH
dc.subject	Ethical fairness principle	de_CH
dc.subject	Group fairness criteria	de_CH
dc.subject	Philosophy	de_CH
dc.subject	Distributive justice	de_CH
dc.subject.ddc	005: Computerprogrammierung, Programme und Daten	de_CH
dc.subject.ddc	658.403: Entscheidungsfindung, Informationsmanagement	de_CH
dc.title	Group fairness in prediction-based decision making : from moral assessment to implementation	de_CH
dc.type	Konferenz: Paper	de_CH
dcterms.type	Text	de_CH
zhaw.departement	School of Engineering	de_CH
zhaw.organisationalunit	Institut für Datenanalyse und Prozessdesign (IDP)	de_CH
dc.identifier.doi	10.1109/SDS54800.2022.00011	de_CH
dc.identifier.doi	10.21256/zhaw-25910	-
zhaw.conference.details	9th Swiss Conference on Data Science (SDS), Lucerne, Switzerland, 22-23 June 2022	de_CH
zhaw.funding.eu	No	de_CH
zhaw.originated.zhaw	Yes	de_CH
zhaw.pages.end	25	de_CH
zhaw.pages.start	19	de_CH
zhaw.publication.status	acceptedVersion	de_CH
zhaw.publication.review	Peer review (Publikation)	de_CH
zhaw.title.proceedings	Proceedings 2022 9th Swiss Conference on Data Science (SDS)	de_CH
zhaw.funding.snf	187473	de_CH
zhaw.funding.zhaw	Algorithmic Fairness in data-based decision making: Combining ethics and technology	de_CH
zhaw.author.additional	No	de_CH
zhaw.display.portrait	Yes	de_CH
Appears in collections:	Publikationen School of Engineering

Files in This Item:

File	Description	Size	Format
2022_Baumann_Heitz_Group-fairness-prediction-based-decision-making_IEEE.pdf	Accepted Version	242.6 kB	Adobe PDF	View/Open

Show simple item record

Baumann, J., & Heitz, C. (2022). Group fairness in prediction-based decision making : from moral assessment to implementation [Conference paper]. Proceedings 2022 9th Swiss Conference on Data Science (SDS), 19–25. https://doi.org/10.1109/SDS54800.2022.00011

Baumann, J. and Heitz, C. (2022) ‘Group fairness in prediction-based decision making : from moral assessment to implementation’, in Proceedings 2022 9th Swiss Conference on Data Science (SDS). IEEE, pp. 19–25. Available at: https://doi.org/10.1109/SDS54800.2022.00011.

J. Baumann and C. Heitz, “Group fairness in prediction-based decision making : from moral assessment to implementation,” in Proceedings 2022 9th Swiss Conference on Data Science (SDS), 2022, pp. 19–25. doi: 10.1109/SDS54800.2022.00011.

BAUMANN, Joachim und Christoph HEITZ, 2022. Group fairness in prediction-based decision making : from moral assessment to implementation. In: Proceedings 2022 9th Swiss Conference on Data Science (SDS). Conference paper. IEEE. 2022. S. 19–25. ISBN 978-1-6654-6847-3

Baumann, Joachim, and Christoph Heitz. 2022. “Group Fairness in Prediction-Based Decision Making : From Moral Assessment to Implementation.” Conference paper. In Proceedings 2022 9th Swiss Conference on Data Science (SDS), 19–25. IEEE. https://doi.org/10.1109/SDS54800.2022.00011.

Baumann, Joachim, and Christoph Heitz. “Group Fairness in Prediction-Based Decision Making : From Moral Assessment to Implementation.” Proceedings 2022 9th Swiss Conference on Data Science (SDS), IEEE, 2022, pp. 19–25, https://doi.org/10.1109/SDS54800.2022.00011.