Summary of Kleinberg, Mullainathan, and Raghavan (2016), "Inherent Trade-Offs in the Fair Determination of Risk Scores"

I’m at Econ-ML talking about Kleinberg, Mullainathan, and Raghavan (2016), “Inherent Trade-Offs in the Fair Determination of Risk Scores.” They demonstrate that it is generally impossible for an algorithm to satisfy each of three seemingly-reasonable criteria for fairness to different groups.