Is Calibration a Fairness Requirement?: An Argument from the Point of View of Moral Philosophy and Decision Theory

Michele Loi, Christoph Heitz

Abstract: This paper evaluates whether calibration between groups is morally required for fair machine-learning systems. It compares calibration with equality of false positive and false negative rates, treating fairness as a question of wrongful discrimination. The paper clarifies when calibration has moral force and when other fairness criteria may better capture the relevant discriminatory harm.