Important Dates

Abstract: Automated decision-making in morally sensitive domains is spreading rapidly throughout different sectors of society. By using massive amounts of data, machine learning algorithms train a model to optimally predict a decision variable as a function of observed features. This outsourcing of our decision-making to an artificial agent opens up a significant challenge: how do we ensure that AI decisions are fair? Recently this challenge has been addressed by defining various notions of causal fairness, which improve upon purely statistical measures of fairness by explicitly incorporating the causal structure of the prediction model. In this talk I will focus on a form of discrimination that is not yet covered by existing causal fairness measures: unintentional proxy discrimination. Such discrimination is particularly pernicious in the context of AI, due to the fact that the very design of AI systems creates an incentive to discriminate in this manner. [Poster]