Fairness-Aware Contextual Dynamic Pricing with Strategic Buyers

• 成果类型: Article; Early Access
• 署名作者: Liu, Pangpang; Sun, Will Wei
• 署名单位: Yale University; Purdue University System; Purdue University
• 刊物名称: JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
• ISSN/ISSBN: 0162-1459; 1537-274X
• DOI: 10.1080/01621459.2026.2648862
• 发表日期: 2026-06-10
• 关键词: contextual bandit; Dynamic pricing; fairness; Regret Bounds; Reinforcement Learning; DISCRIMINATION

摘要

Contextual pricing strategies are prevalent in online retailing, where the seller adjusts prices based on products' attributes and buyers' characteristics. Although such strategies can enhance seller's profits, they raise concerns about fairness when significant price disparities emerge among specific groups, such as gender or race. These disparities can lead to adverse perceptions of fairness among buyers and may even violate the law and regulation. In contrast, price differences can incentivize disadvantaged buyers to strategically manipulate their group identity to obtain a lower price. In this article, we investigate contextual dynamic pricing with fairness constraints, taking into account buyers' strategic behaviors when their group status is private and unobservable from the seller. We propose a dynamic pricing policy that simultaneously achieves price fairness and discourages strategic behaviors. Our policy achieves an upper bound of O(root T+H(T)) regret over T time horizons, where the term H(T) captures the effect of buyers' perceived price difference. When buyers are able to learn the fairness of the price policy, this upper bound reduces to O(root T). We also prove an Omega(root T) regret lower bound of any pricing policy under our problem setting. We support our findings with extensive experimental evidence, showcasing our policy's effectiveness. In our real data analysis, we observe the existence of price discrimination against race in the loan application even after accounting for other contextual information. Our proposed pricing policy demonstrates a significant improvement, achieving an average reduction of 30.71% in regret compared to the benchmark policy. Supplementary materials for this article are available online, including a standardized description of the materials available for reproducing the work.