Generalized Strategic Classification and the Case of Aligned Incentives

TL;DR

This paper broadens the scope of strategic classification to include diverse user motivations, introduces a flexible model, and develops a novel max-margin learning framework that is both practical and theoretically sound.

Contribution

It proposes a generalized model of strategic classification, identifies a new aligned-incentives subclass, and introduces a new max-margin approach suitable for strategic inputs.

Findings

Standard max-margin losses are ineffective for strategic data.

The proposed max-margin framework outperforms existing methods.

Experimental results validate the approach's practical utility.

Abstract

Strategic classification studies learning in settings where self-interested users can strategically modify their features to obtain favorable predictive outcomes. A key working assumption, however, is that "favorable" always means "positive"; this may be appropriate in some applications (e.g., loan approval), but reduces to a fairly narrow view of what user interests can be. In this work we argue for a broader perspective on what accounts for strategic user behavior, and propose and study a flexible model of generalized strategic classification. Our generalized model subsumes most current models but includes other novel settings; among these, we identify and target one intriguing sub-class of problems in which the interests of users and the system are aligned. This setting reveals a surprising fact: that standard max-margin losses are ill-suited for strategic inputs. Returning to our fully generalized model, we propose a novel max-margin framework for strategic learning that is practical and effective, and which we analyze theoretically. We conclude with a set of experiments that empirically demonstrate the utility of our approach.