Differential Privacy in Personalized Pricing with Nonparametric Demand Models
成果类型：
Article
署名作者：
Chen, Xi; Miao, Sentao; Wang, Yining
署名单位：
New York University; McGill University; University of Texas System; University of Texas Dallas
刊物名称：
OPERATIONS RESEARCH
ISSN/ISSBN：
0030-364X
DOI：
10.1287/opre.2022.2347
发表日期：
2023
页码：
581-602
关键词：
摘要：
In recent decades, the advance of information technology and abundant personal data facilitate the application of algorithmic personalized pricing. However, this leads to the growing concern of potential violation of privacy because of adversarial attack. To address the privacy issue, this paper studies a dynamic personalized pricing problem with unknown nonparametric demand models under data privacy protection. Two concepts of data privacy, which have been widely applied in practices, are introduced: central differential privacy (CDP) and local differential privacy (LDP), which is proved to be stronger than CDP inmany cases. We develop two algorithms thatmake pricing decisions and learn the unknown demand on the fly while satisfying the CDP and LDP guarantee, respectively. In particular, for the algorithm with CDP guarantee, the regret is proved to be at most (O) over tilde (T(d+2)/(d+4) + epsilon T--1(d/(d+4))). Here, the parameter T denotes the length of the time horizon, d is the dimension of the personalized information vector, and the key parameter epsilon > 0 measures the strength of privacy (smaller e indicates a stronger privacy protection). Conversely, for the algorithm with LDP guarantee, its regret is proved to be at most (O) over tilde(epsilon T--2/(d+2)((d+1)/(d+2))), which is near optimal as we prove a lower bound of Omega(epsilon(-2/(d+2)) T(d+1)/(d+2)/d(7/3)) for any algorithmwith LDP guarantee.