Saved in:
Bibliographic Details
Main Authors: Sommer, Yonatan, Hikri, Ivri, Amit, Lotan, Rosenfeld, Nir
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.20012
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916897272889344
author Sommer, Yonatan
Hikri, Ivri
Amit, Lotan
Rosenfeld, Nir
author_facet Sommer, Yonatan
Hikri, Ivri
Amit, Lotan
Rosenfeld, Nir
contents 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 can 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_20012
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Classifiers That Induce Markets
Sommer, Yonatan
Hikri, Ivri
Amit, Lotan
Rosenfeld, Nir
Machine Learning
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 can 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.
title Learning Classifiers That Induce Markets
topic Machine Learning
url https://arxiv.org/abs/2502.20012