Sequential Strategic Screening
This addresses vulnerabilities in sequential screening systems for applications like hiring or admissions, though it is incremental by combining strategic classification with screening processes.
The paper tackles the problem of strategic behavior in multi-classifier screening processes, showing that individuals can exploit sequential ordering to achieve positive outcomes with limited manipulation budgets, even when far from satisfying all classifiers simultaneously.
We initiate the study of strategic behavior in screening processes with multiple classifiers. We focus on two contrasting settings: a conjunctive setting in which an individual must satisfy all classifiers simultaneously, and a sequential setting in which an individual to succeed must satisfy classifiers one at a time. In other words, we introduce the combination of strategic classification with screening processes. We show that sequential screening pipelines exhibit new and surprising behavior where individuals can exploit the sequential ordering of the tests to zig-zag between classifiers without having to simultaneously satisfy all of them. We demonstrate an individual can obtain a positive outcome using a limited manipulation budget even when far from the intersection of the positive regions of every classifier. Finally, we consider a learner whose goal is to design a sequential screening process that is robust to such manipulations, and provide a construction for the learner that optimizes a natural objective.