Learning Classifiers That Induce Markets

Yonatan Sommer, Ivri Hikri, Lotan Amit, Nir Rosenfeld
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56148-56172, 2025.

Abstract

When learning is used to inform decisions about humans, such as for loans, hiring, or admissions, this can incentivize users to strategically modify their features, at a cost, to obtain positive predictions. The common assumption is that the function governing costs is exogenous, fixed, and predetermined. We challenge this assumption, and assert that costs emerge as a result of deploying a classifier. Our idea is simple: when users seek positive predictions, this creates demand for important features; and if features are available for purchase, then a market will form, and competition will give rise to prices. We extend the strategic classification framework to support this notion, and study learning in a setting where a classifier can induce a market for features. We present an analysis of the learning task, devise an algorithm for computing market prices, propose a differentiable learning framework, and conduct experiments to explore our novel setting and approach.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-sommer25a, title = {Learning Classifiers That Induce Markets}, author = {Sommer, Yonatan and Hikri, Ivri and Amit, Lotan and Rosenfeld, Nir}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {56148--56172}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/sommer25a/sommer25a.pdf}, url = {https://proceedings.mlr.press/v267/sommer25a.html}, abstract = {When learning is used to inform decisions about humans, such as for loans, hiring, or admissions, this can incentivize users to strategically modify their features, at a cost, to obtain positive predictions. The common assumption is that the function governing costs is exogenous, fixed, and predetermined. We challenge this assumption, and assert that costs emerge as a result of deploying a classifier. Our idea is simple: when users seek positive predictions, this creates demand for important features; and if features are available for purchase, then a market will form, and competition will give rise to prices. We extend the strategic classification framework to support this notion, and study learning in a setting where a classifier can induce a market for features. We present an analysis of the learning task, devise an algorithm for computing market prices, propose a differentiable learning framework, and conduct experiments to explore our novel setting and approach.} }
Endnote
%0 Conference Paper %T Learning Classifiers That Induce Markets %A Yonatan Sommer %A Ivri Hikri %A Lotan Amit %A Nir Rosenfeld %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-sommer25a %I PMLR %P 56148--56172 %U https://proceedings.mlr.press/v267/sommer25a.html %V 267 %X When learning is used to inform decisions about humans, such as for loans, hiring, or admissions, this can incentivize users to strategically modify their features, at a cost, to obtain positive predictions. The common assumption is that the function governing costs is exogenous, fixed, and predetermined. We challenge this assumption, and assert that costs emerge as a result of deploying a classifier. Our idea is simple: when users seek positive predictions, this creates demand for important features; and if features are available for purchase, then a market will form, and competition will give rise to prices. We extend the strategic classification framework to support this notion, and study learning in a setting where a classifier can induce a market for features. We present an analysis of the learning task, devise an algorithm for computing market prices, propose a differentiable learning framework, and conduct experiments to explore our novel setting and approach.
APA
Sommer, Y., Hikri, I., Amit, L. & Rosenfeld, N.. (2025). Learning Classifiers That Induce Markets. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:56148-56172 Available from https://proceedings.mlr.press/v267/sommer25a.html.

Related Material