A Systematic Approach to Group Fairness in Automated Decision Making
This work aims to help data scientists navigate fairness definitions, but it is incremental as it synthesizes existing concepts without new empirical results.
The paper addresses the challenge of applying algorithmic fairness in practice by providing an accessible introduction to group fairness metrics and explaining the philosophical reasoning behind them, focusing on how socio-demographic groups are compared.
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.