Testing the Fairness-Improvability of Algorithms
arxiv(2024)
摘要
Many algorithms have a disparate impact in that their benefits or harms fall
disproportionately on certain social groups. Addressing an algorithm's
disparate impact can be challenging, however, because it is not always clear
whether there exists an alternative more-fair algorithm that does not
compromise on other key objectives such as accuracy or profit. Establishing the
improvability of algorithms with respect to multiple criteria is of both
conceptual and practical interest: in many settings, disparate impact that
would otherwise be prohibited under US federal law is permissible if it is
necessary to achieve a legitimate business interest. The question is how a
policy maker can formally substantiate, or refute, this necessity defense. In
this paper, we provide an econometric framework for testing the hypothesis that
it is possible to improve on the fairness of an algorithm without compromising
on other pre-specified objectives. Our proposed test is simple to implement and
can incorporate any exogenous constraint on the algorithm space. We establish
the large-sample validity and consistency of our test, and demonstrate its use
empirically by evaluating a healthcare algorithm originally considered by
Obermeyer et al. (2019). In this demonstration, we find strong statistically
significant evidence that it is possible to reduce the algorithm's disparate
impact without compromising on the accuracy of its predictions.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要