A Bayesian learning and pricing model with multiple unknown demand parameters

This article presents a Bayesian learning model for demand estimation in revenue management. Different from most existing models in the literature, our discussion centers on demand functions with an arbitrary number of unknown and correlated parameters, and estimating them simultaneously. We formulate the problem as a Dirichlet learning model and show the search process converges to the true parameter values. As the observed data does not unambiguously reveal the underlying demand curve, the exploration scheme is notably different from conventional Dirichlet sampling process. We apply a partially observable Markov decision process to ensure the true demand curve surfaces as a favorite. Our pricing policy during the learning phase also differs from myopic heuristics by taking both the remaining time and unsold items into consideration. As incomplete learning remains a concern for all existing learning models, we show that the occurrence of uninformative prices is rooted in the dynamics of pricing, and prove that the proposed model is immune from incomplete learning. For revenue performance, the regret bounds established are comparable to the benchmark in the literature under similar conditions. Overall, the proposed model integrates the learning process with earning goals and offers a promising tool to achieve both targets.