Header

UZH-Logo

Maintenance Infos

A Systematic Approach to Group Fairness in Automated Decision Making


Hertweck, Corinna; Heitz, Christoph (2021). A Systematic Approach to Group Fairness in Automated Decision Making. In: 2021 8th Swiss Conference on Data Science (SDS), Lucerne, 9 June 2021. IEEE, 1-6.

Abstract

While the field of algorithmic fairness has brought forth many ways to measure and improve the fairness of machine learning models, these findings are still not widely used in practice. We suspect that one reason for this is that the field of algorithmic fairness came up with a lot of definitions of fairness, which are difficult to navigate. The goal of this paper is to provide data scientists with an accessible introduction to group fairness metrics and to give some insight into the philosophical reasoning for caring about these metrics. We will do this by considering in which sense socio-demographic groups are compared for making a statement on fairness.

Abstract

While the field of algorithmic fairness has brought forth many ways to measure and improve the fairness of machine learning models, these findings are still not widely used in practice. We suspect that one reason for this is that the field of algorithmic fairness came up with a lot of definitions of fairness, which are difficult to navigate. The goal of this paper is to provide data scientists with an accessible introduction to group fairness metrics and to give some insight into the philosophical reasoning for caring about these metrics. We will do this by considering in which sense socio-demographic groups are compared for making a statement on fairness.

Statistics

Citations

Dimensions.ai Metrics

Altmetrics

Downloads

14 downloads since deposited on 31 Jan 2022
6 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Informatics
Dewey Decimal Classification:000 Computer science, knowledge & systems
Scopus Subject Areas:Physical Sciences > Artificial Intelligence
Physical Sciences > Computer Science Applications
Physical Sciences > Information Systems
Social Sciences & Humanities > Decision Sciences (miscellaneous)
Social Sciences & Humanities > Information Systems and Management
Uncontrolled Keywords:algorithmic fairness, group fairness, statistical parity, independence, separation, sufficiency
Language:English
Event End Date:9 June 2021
Deposited On:31 Jan 2022 06:33
Last Modified:01 Aug 2022 00:01
Publisher:IEEE
ISBN:978-1-6654-4610-5
OA Status:Green
Publisher DOI:https://doi.org/10.1109/sds51136.2021.00008
Project Information:
  • : FunderSNSF
  • : Grant ID407740_187473
  • : Project TitleSocially acceptable AI and fairness trade-offs in predictive analytics
  • : Project Websitehttps://fair-ai.ch/
  • Content: Accepted Version