Generalized Strategic Classification and the Case of Aligned Incentives
About
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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Strategic Label Improvement Evaluation | HELOC (test) | Manipulated Agents1.05e+3 | 4 | |
| Strategic Label Improvement Evaluation | Adult (test) | Manipulated Agents775 | 4 | |
| Strategic Label Improvement Evaluation | Law School (test) | Manipulated Agents22 | 4 | |
| Strategic Label Improvement Evaluation | ACS Income (test) | Number of Manipulated Agents1.73e+4 | 4 | |
| Strategic Label Improvement Evaluation | Synthetic (test) | Manipulated Agents Count2.23e+3 | 4 |