Dynamic Pricing with Limited Competitor Information in a Multi-Agent Economy

We study the price dynamics in a multi-agent economy consisting of buyers and competing sellers, where each seller has limited information about its competitors’ prices. In this economy, buyers use shopbots while the sellers employ automated pricing agents or pricebots. A pricebot resets its seller’s price at regular intervals with the objective of maximizing revenue in each time period. Derivative following provides a simple, albeit naive, strategy for dynamic pricing in such a scenario. In this paper, we refine the derivative following algorithm and introduce a model-optimizer algorithm that re-estimates the priceprofit relationship for a seller in each period more efficiently. Simulations using the model-optimizer algorithm indicate that it outperforms derivative following even though it does not have any additional information about the market. Our results underscore the role machine learning and optimization can play in fostering competition (or cooperation) in a multi-agent economy where the agents have limited information about their environment.