Skip to yearly menu bar Skip to main content


Equality of Opportunity in Supervised Learning

Moritz Hardt · Eric Price · Eric Price · Nati Srebro

Area 5+6+7+8 #47

Keywords: [ (Application) Privacy, Anonymity, and Security ] [ Game Theory and Econometrics ] [ (Other) Machine Learning Topics ] [ (Other) Classification ] [ Learning Theory ]


We propose a criterion for discrimination against a specified sensitive attribute in supervised learning, where the goal is to predict some target based on available features. Assuming data about the predictor, target, and membership in the protected group are available, we show how to optimally adjust any learned predictor so as to remove discrimination according to our definition. Our framework also improves incentives by shifting the cost of poor classification from disadvantaged groups to the decision maker, who can respond by improving the classification accuracy.

Live content is unavailable. Log in and register to view live content