Robust Strategic Classification under Decision-Dependent Cost Uncertainty

2026-06-29

AI Summary

This work addresses a critical limitation in existing strategic classification methods, which typically assume that users’ manipulation costs are fixed and independent of the algorithm’s decisions, thereby overlooking the dynamic nature of these costs in real-world settings. To bridge this gap, the paper proposes a novel two-stage robust optimization framework that explicitly incorporates decision-dependent cost uncertainty. By constructing an uncertainty set that adapts to the classifier’s historical decisions, the approach captures the evolving nature of manipulation costs over time. This formulation not only effectively mitigates long-term strategic gaming by users but also substantially enhances the classifier’s robustness and cumulative utility in dynamic environments. Theoretical analysis substantiates the superiority of the proposed method over conventional approaches.

Abstract

Humans facing algorithmic decision systems have been found to ``game'' them by altering their input data (at a cost to them) in order to favorably change the algorithmic outcomes they receive (at a cost to the algorithm). The growing literature on strategic classification seeks to develop robust machine learning algorithms that account for, and reduce, unwanted strategic behavior. A limitation of these existing works is that they assume the cost of strategic behavior to be fixed and independent of the classifier's decision. In practice, however, manipulation costs evolve and depend on past algorithmic decisions: today's decisions influence tomorrow's costs. This paper proposes and analyzes a two-stage robust optimization framework with a decision-dependent uncertainty set to capture such dependencies. We highlight that awareness of policy-dependent costs not only reduces uncertainty, but also better curtails gaming of the algorithmic system over time.

Problem

• strategic classification
• decision-dependent uncertainty
• cost uncertainty
• algorithmic decision systems
• gaming behavior

Innovation

• strategic classification
• decision-dependent uncertainty
• robust optimization
• gaming behavior
• algorithmic decision systems