Real-time dynamic pricing in a non-stationary environment using model-free reinforcement learning

This paper examines the problem of establishing a pricing policy that maximizes the revenue for selling a given inventory by a fixed deadline. This problem is faced by a variety of industries, including airlines, hotels and fashion. Reinforcement learning algorithms are used to analyze how firms can both learn and optimize their pricing strategies while interacting with their customers. We show that by using reinforcement learning we can model the problem with inter-dependent demands. This type of model can be useful in producing a more accurate pricing scheme of services or products when important events affect consumer preferences. This paper proposes a methodology to optimize revenue in a model-free environment in which demand is learned and pricing decisions are updated in real-time. We compare the performance of the learning algorithms using Monte-Carlo simulation. Crown Copyright (C) 2013 Published by Elsevier Ltd. All rights reserved.