Inherent Trade-Offs in the Fair Determination of Risk ScoresEI

摘要

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 ...更多
个人信息

 

您的评分 :

ITCS, 2016.

被引用次数206|引用|6
标签
作者
评论