Learning Classifiers That Induce Markets
This addresses the challenge of strategic manipulation in decision-making systems for applications like finance and employment, offering a novel perspective on cost dynamics.
The paper tackles the problem of strategic user behavior in classification tasks like loans or hiring, where users can modify features at a cost, by proposing that classifiers can induce markets for features, leading to emergent costs. It extends strategic classification to include market formation, analyzes the learning task, devises algorithms for price computation, and presents experimental results.
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.