Contextual Offline Demand Learning and Pricing with Separable Models

TitleContextual Offline Demand Learning and Pricing with Separable Models
Publication TypeJournal Article
Year of Publication2024
AuthorsLi M, Simchi-Levi D, Tan R, Wang C, Wu MXiao
JournalUnder revision
KeywordsCurrent Research

This paper, inspired by a collaboration with a leading consumer electronics retailer in the Middle East, explores the challenge of demand learning and pricing using separable demand models. The intrinsic sparsity within the dataset, characterized by limited price changes and low sales volumes, renders traditional models ineffective in deriving reasonable price elasticity. To address this issue, we advocate the adoption of a separable model that leverages two submodels to distinctly capture the effects of price and contextual information. The separable structure enables us to invest special emphasis on the role of price and impose specific structural assumptions on the submodel for pricing effects, such as the incorporation of the monotone decreasing property. Theoretical analysis sheds light on the statistical complexity of demand learning with the separable structure, highlighting its capacity to reduce the necessary sample size to achieve a desired level of accuracy. We also introduce a computationally efficient iterative algorithm for deriving submodels from offline datasets, complete with convergence guarantees. In an empirical context, we present compelling demonstrations of how our method can yield meaningful price elasticity estimations based on real sales data from the retailer.