The Impact of Equal Opportunity on Statistical Discrimination

I modify the canonical statistical discrimination model of Coate and Loury (1993) by assuming the firm's belief about an individual's unobserved class is machine learning-generated and, therefore, contractible. This expands the toolkit of a regulator beyond belief-free regulations like affirmative action. Contractible beliefs make it feasible to require the firm to select a decision policy that equalizes true positive rates across groups -- what the algorithmic fairness literature calls equal opportunity. While affirmative action does not necessarily end statistical discrimination, I show that imposing equal opportunity does.