Group fairness requires equal predicted outcomes across protected groups

Evidence

Our first definition of fairness is “group fairness.” We can say that a classifier satisfies this definition if both protected (e.g., Black defendants) and unprotected (White defendants) groups have equal probabilities of being assigned to the positive predicted class (Verma & Rubin, 2018). This is intuitively fair. Since positive prediction means a good risk score, then all defendants, regardless of group, should have an equivalent opportunity of receiving a good score. — Joseph Avery, Jim Sidanius, Joel Cooper, Gregory Davis, Amanda N., Bias in the Law, 1157

Categorization

• DEFINE: Defines group fairness as equality of predicted positive classification across protected classes.