Dynamic Pricing through Data Sampling

• 成果类型: Article
• 署名作者: Cohen, Maxime C.; Lobel, Ruben; Perakis, Georgia
• 署名单位: New York University; Airbnb; Massachusetts Institute of Technology (MIT)
• 刊物名称: PRODUCTION AND OPERATIONS MANAGEMENT
• ISSN/ISSBN: 1059-1478
• DOI: 10.1111/poms.12854
• 发表日期: 2018
• 页码: 1074-1088
• 关键词: multistage robust optimization; average approximation method; uncertain convex-programs; randomized solutions; revenue management

摘要

We study a dynamic pricing problem, where a firm offers a product to be sold over a fixed time horizon. The firm has a given initial inventory level, but there is uncertainty about the demand for the product in each time period. The objective of the firm is to determine a dynamic pricing strategy that maximizes revenue throughout the entire selling season. We develop a tractable optimization model that directly uses demand data, therefore creating a practical decision tool. We show computationally that regret-based objectives can perform well when compared to average revenue maximization and to a Bayesian approach. The modeling approach proposed in this study could be particularly useful for risk-averse managers with limited access to historical data or information about the true demand distribution. Finally, we provide theoretical performance guarantees for this sampling-based solution.