A Philosophical Theory of Fairness for Prediction-Based Decisions.

Abstract

This paper presents a fairness principle that can be used to evaluate decision-making based on predictions. We propose that a decision rule for decision-making based on predictions is fair when the individuals directly subjected to the implications of the decision enjoy fair equality of chances. We define fair equality of chances as obtaining if and only if the individuals who are equal with respect to the features that justify inequalities in outcomes have the same statistical prospects of being benefited or harmed, irrespective of their morally irrelevant traits. The paper characterizes – in a formal way – the way in which luck is allowed to impact outcome in order for its influence to be fair. This fairness principle can be used to evaluate decision-making based on predictions, a kind of decision-making that is becoming increasingly important to theorize around in light of the growing prevalence of algorithmic decision-making in healthcare, the criminal justice system and the insurance industry, among other areas. It can be used to evaluate decision-making rules based on different normative theories, and is compatible with the broadest range of normative views according to which inequalities due to brute luck can be fair.

Keywords: Fairness, bias, statistical decision-making, statistical discrimination