Multi-Level Strategic Classification: Incentivizing Improvement through Promotion and Relegation Dynamics

Ziyuan Huang, Lina Alkarmi, Mingyan Liu
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:46269-46308, 2026.

Abstract

Strategic classification studies the problem where self-interested individuals or agents manipulate their response to obtain favorable decision outcomes made by classifiers, typically turning to dishonest actions when they are less costly than genuine efforts. While existing studies on sequential strategic classification primarily focus on optimizing dynamic classifier weights, we depart from these weight-centric approaches by analyzing the design of classifier thresholds and difficulty progression within a multi-level promotion-relegation framework. Our model captures the critical inter-temporal incentives driven by an agent’s farsightedness, skill retention, and a "leg-up" effect where qualification and attainment can be self-reinforcing. We characterize the agent’s optimal long-term strategy and demonstrate that a principal can design a sequence of thresholds to effectively incentivize honest effort. Crucially, we prove that under mild conditions, this mechanism enables agents to reach arbitrarily high levels solely through genuine improvement efforts.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-huang26a, title = {Multi-Level Strategic Classification: Incentivizing Improvement through Promotion and Relegation Dynamics}, author = {Huang, Ziyuan and Alkarmi, Lina and Liu, Mingyan}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {46269--46308}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/huang26a/huang26a.pdf}, url = {https://proceedings.mlr.press/v306/huang26a.html}, abstract = {Strategic classification studies the problem where self-interested individuals or agents manipulate their response to obtain favorable decision outcomes made by classifiers, typically turning to dishonest actions when they are less costly than genuine efforts. While existing studies on sequential strategic classification primarily focus on optimizing dynamic classifier weights, we depart from these weight-centric approaches by analyzing the design of classifier thresholds and difficulty progression within a multi-level promotion-relegation framework. Our model captures the critical inter-temporal incentives driven by an agent’s farsightedness, skill retention, and a "leg-up" effect where qualification and attainment can be self-reinforcing. We characterize the agent’s optimal long-term strategy and demonstrate that a principal can design a sequence of thresholds to effectively incentivize honest effort. Crucially, we prove that under mild conditions, this mechanism enables agents to reach arbitrarily high levels solely through genuine improvement efforts.} }
Endnote
%0 Conference Paper %T Multi-Level Strategic Classification: Incentivizing Improvement through Promotion and Relegation Dynamics %A Ziyuan Huang %A Lina Alkarmi %A Mingyan Liu %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-huang26a %I PMLR %P 46269--46308 %U https://proceedings.mlr.press/v306/huang26a.html %V 306 %X Strategic classification studies the problem where self-interested individuals or agents manipulate their response to obtain favorable decision outcomes made by classifiers, typically turning to dishonest actions when they are less costly than genuine efforts. While existing studies on sequential strategic classification primarily focus on optimizing dynamic classifier weights, we depart from these weight-centric approaches by analyzing the design of classifier thresholds and difficulty progression within a multi-level promotion-relegation framework. Our model captures the critical inter-temporal incentives driven by an agent’s farsightedness, skill retention, and a "leg-up" effect where qualification and attainment can be self-reinforcing. We characterize the agent’s optimal long-term strategy and demonstrate that a principal can design a sequence of thresholds to effectively incentivize honest effort. Crucially, we prove that under mild conditions, this mechanism enables agents to reach arbitrarily high levels solely through genuine improvement efforts.
APA
Huang, Z., Alkarmi, L. & Liu, M.. (2026). Multi-Level Strategic Classification: Incentivizing Improvement through Promotion and Relegation Dynamics. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:46269-46308 Available from https://proceedings.mlr.press/v306/huang26a.html.

Related Material