Strategic Classification with Unforeseeable Outcomes

Tian Xie, Zhiqun Zuo, Xueru Zhang

Primary Area: societal considerations including fairness, safety, privacy

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Strategic Classification

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We propose a comprehensive probabilistic framework to model unforeseeable outcomes of both manipulation and improvement behaviors of strategic agents

Abstract: Machine learning systems are often used to make decisions about individuals, where individuals may best respond and behave strategically to receive favorable outcomes, e.g., they may genuinely *improve* the true labels or *manipulate* observable features directly to game the system without changing labels. Although both behaviors have been studied (often as two separate problems) in the literature, most works assume individuals can (i) perfectly foresee the outcomes of their behaviors when they best respond; (ii) change their features arbitrarily as long as it's affordable, and the costs they need to pay are deterministic functions of feature changes. In this paper, we consider a different setting and focus on *imitative* strategic behaviors with *unforeseeable* outcomes, i.e., individuals manipulate/improve by imitating the features of those with positive labels, but the induced feature changes are unforeseeable. We first propose a novel probabilistic model to capture both behaviors and establish a Stackelberg game between individuals and the decision-maker. Under this model, we examine how the decision-maker's ability to anticipate individual behavior affects its objective function and the individual's best response. We show that the objective difference between the two can be decomposed into three interpretable terms, with each representing the decision-maker's preference for a certain behavior. By exploring the roles of each term, we further illustrate how a decision-maker with adjusted preferences can simultaneously disincentivize manipulation, incentivize improvement, and promote fairness.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 4325