A Market for Accuracy: Classification under Competition
This addresses the problem of service providers in consumer markets by introducing a novel competitive learning approach, though it is incremental in extending traditional methods to market contexts.
The paper tackles the problem of machine learning models in competitive markets, showing that accuracy alone is insufficient and proposing a method for classification under competition to maximize market share, with results indicating benefits for providers and consumers and quick convergence to market equilibrium.
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.