Learning Classifiers That Induce Markets

TL;DR

This paper explores how classifiers can induce markets for features by creating demand and prices, challenging the assumption that costs are fixed, and develops methods to learn in this dynamic setting.

Contribution

It introduces a framework where classifiers can generate markets for features, integrating market dynamics into the learning process for strategic classification.

Findings

Market prices can be computed efficiently within the learning framework.

Classifiers can influence feature demand and pricing through strategic decisions.

The proposed approach effectively models and learns in markets induced by classifiers.

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 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.