Beyond Rational Illusion: Behaviorally Realistic Strategic Classification
Xinpeng Lv, Yunxin Mao, Renzhe Xu, Chunyuan Zheng, Yikai Chen, Haoxuan Li, Yang Shi, Jinxuan Yang, Zhouchen Lin, Yuanlong Chen, Yuanxing Zhang, Shaowu Yang, Wenjing Yang, Haotian Wang

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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
