Prediction without Preclusion: Recourse Verification with Reachable Sets

arXiv:2308.12820v2 Announce Type: replace
Abstract: Machine learning models are often used to decide who receives a loan, a job interview, or a public benefit. Models in such settings use features without considering their actionability. As a result, they can assign predictions that are fixed $-$ meaning that individuals who are denied loans and interviews are, in fact, precluded from access to credit and employment. In this work, we introduce a procedure called recourse verification to test if a model assigns …

abstract arxiv benefit cs.cy cs.lg features interview job loans machine machine learning machine learning models meaning prediction predictions public stat.ml type verification