Inherent Trade-Offs in the Fair Determination of Risk Scores
This work addresses the problem of reconciling competing fairness definitions in algorithmic classification for policymakers and researchers, showing that trade-offs are unavoidable.
The paper formalizes three fairness conditions for algorithmic risk scores and proves that they cannot be simultaneously satisfied except in highly constrained cases, highlighting inherent trade-offs between different notions of fairness.
Recent discussion in the public sphere about algorithmic classification has involved tension between competing notions of what it means for a probabilistic classification to be fair to different groups. We formalize three fairness conditions that lie at the heart of these debates, and we prove that except in highly constrained special cases, there is no method that can satisfy these three conditions simultaneously. Moreover, even satisfying all three conditions approximately requires that the data lie in an approximate version of one of the constrained special cases identified by our theorem. These results suggest some of the ways in which key notions of fairness are incompatible with each other, and hence provide a framework for thinking about the trade-offs between them.