A Market for Accuracy: Classification under Competition

TL;DR

This paper studies how machine learning models compete in markets, proposing a method to maximize market share that considers competition, and demonstrating its effectiveness and market stability across various domains.

Contribution

It introduces a novel classification approach for competitive markets, accounting for competitors and market dynamics, which improves provider and consumer outcomes.

Findings

Market share can be maximized through strategic classification.

Timing of market entry and updates impacts success.

Market equilibrium is achieved quickly and remains stable.

Abstract

Machine learning models play a key role for service providers looking to gain market share in consumer markets. However, traditional learning approaches do not take into account the existence of additional providers, who compete with each other for consumers. Our work aims to study learning in this market setting, as it affects providers, consumers, and the market itself. We begin by analyzing such markets through the lens of the learning objective, and show that accuracy cannot be the only consideration. We then propose a method for classification under competition, so that a learner can maximize market share in the presence of competitors. We show that our approach benefits the providers as well as the consumers, and find that the timing of market entry and model updates can be crucial. We display the effectiveness of our approach across a range of domains, from simple distributions to noisy datasets, and show that the market as a whole remains stable by converging quickly to an equilibrium.