Optimal Policies for Dynamic Pricing and Inventory Control with Nonparametric Censored Demands

• 成果类型: Article
• 署名作者: Chen, Boxiao; Wang, Yining; Zhou, Yuan
• 署名单位: University of Illinois System; University of Illinois Chicago; University of Illinois Chicago Hospital; University of Texas System; University of Texas Dallas; Tsinghua University; Tsinghua University
• 刊物名称: MANAGEMENT SCIENCE
• ISSN/ISSBN: 0025-1909
• DOI: 10.1287/mnsc.2023.4859
• 发表日期: 2024
• 关键词: Dynamic pricing; inventory replenishment; censored demand; lost sales; Regret minimization; bandit learning; nonconcavity

摘要

We study the classic model of joint pricing and inventory control with lost sales over T consecutive review periods. The firm does not know the demand distribution a priori and needs to learn it from historical censored demand data. We develop nonparametric online learning algorithms that converge to the clairvoyant optimal policy at the fastest possible speed. The fundamental challenges rely on that neither zeroth-order nor first-order feedbacks are accessible to the firm and reward at any single price is not observable due to demand censoring. We propose a novel inversion method based on empirical measures to consistently estimate the difference of the instantaneous reward functions at two prices, directly tackling the fundamental challenge brought by censored demands. Based on this technical innovation, we design bisection and trisection search methods that attain an (O) over tilde(root T) regret for the case with concave reward functions, and we design an active tournament elimination method that attains (O) over tilde (T-3/5) regret when the reward functions are non concave. We complement the (O) over tilde (T-3/5) regret upper bound with a matching (Omega) over tilde (T-3/5) regret lower bound. The lower bound is established by a novel information-theoretical argument based on generalized squared Hellinger distance, which is significantly different from conventional arguments that are based on Kullback-Leibler divergence. Both the upper bound technique based on the difference estimator and the lower bound technique based on generalized Hellinger distance are new in the literature, and can be potentially applied to solve other inventory or censored demand type problems that involve learning.