Timezone: »

Counterfactual Fairness
Matt Kusner · Joshua Loftus · Chris Russell · Ricardo Silva

Wed Dec 06 04:50 PM -- 05:05 PM (PST) @ Hall C

Machine learning can impact people with legal or ethical consequences when it is used to automate decisions in areas such as insurance, lending, hiring, and predictive policing. In many of these scenarios, previous decisions have been made that are unfairly biased against certain subpopulations, for example those of a particular race, gender, or sexual orientation. Since this past data may be biased, machine learning predictors must account for this to avoid perpetuating or creating discriminatory practices. In this paper, we develop a framework for modeling fairness using tools from causal inference. Our definition of counterfactual fairness captures the intuition that a decision is fair towards an individual if it the same in (a) the actual world and (b) a counterfactual world where the individual belonged to a different demographic group. We demonstrate our framework on a real-world problem of fair prediction of success in law school.

Author Information

Matt Kusner (University of Oxford)
Joshua Loftus (The Alan Turing Institute)
Chris Russell (The Alan Turing Institute/ The University of Surrey)
Ricardo Silva (University College London)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors