Algorithmic Fairness: Choices, Assumptions, and Definitions

A recent wave of research has attempted to define fairness quantitatively. In particular, this work has explored what fairness might mean in the context of decisions based on the predictions of statistical and machine learning models. The rapid growth of this new field has led to wildly inconsistent motivations, terminology, and notation, presenting a serious challenge for cataloging and comparing definitions. This article attempts to bring much-needed order. First, we explicate the various choices and assumptions made-often implicitly-to justify the use of prediction-based decision-making. Next, we show how such choices and assumptions can raise fairness concerns and we present a notationally consistent catalog of fairness definitions from the literature. In doing so, we offer a concise reference for thinking through the choices, assumptions, and fairness considerations of prediction-based decision-making.

Automated summary

Recent research has aimed to quantify fairness, particularly in the context of decisions based on statistical and machine learning model predictions. The inconsistency in motivations, terminology, and notation in this new field poses a challenge for cataloging and comparing definitions. This article attempts to bring order by providing a consistent catalog of fairness definitions and exploring the choices, assumptions, and fairness considerations in prediction-based decision-making.