Beyond Rational Illusion: Behaviorally Realistic Strategic Classification

TL;DR

This paper introduces a new framework for strategic classification that incorporates behavioral economics principles, specifically prospect theory, to model agents' non-rational strategic manipulations.

Contribution

It formalizes a behaviorally realistic setting for strategic classification and proposes the Prospect-Guided Strategic Framework (Pro-SF) based on prospect theory.

Findings

Pro-SF outperforms traditional models on synthetic datasets.

Pro-SF demonstrates improved robustness in real-world scenarios.

Incorporating behavioral biases leads to more reliable strategic classification.

Abstract

Strategic classification(SC) studies the interaction between decision models and agents who strategically manipulate their features for favorable outcomes. Existing SC frameworks typically rely on the idealized assumption that agents are strictly rational. However, evidence from behavioral economics and psychology consistently shows that real-world decision-making is often shaped by cognitive biases, deviating from pure rationality. To formalize this limitation, we identify and define a new problem setting, termed the behaviorally realistic strategic classification problem, where agents' strategic manipulations deviate from full rationality due to psychological biases. Motivated by the identified limitation, we propose the Prospect-Guided Strategic Framework (Pro-SF) to address the problem, a principled framework grounded in prospect theory to model and learn under behaviorally realistic strategic responses. Specifically, to capture behaviorally realistic strategic manipulations, our framework reformulates the Stackelberg-style interaction between agents and the decision-maker by incorporating three key mechanisms inspired by prospect theory, including the asymmetry between benefits and costs, different subjective reference points, and non-rational probability distortion. Experiments on synthetic and real-world datasets establish Pro-SF as a behaviorally grounded approach to strategic classification, bridging machine learning and behavioral economics for more reliable deployment in the real world.