【Academic Seminar】Distribution-free Contextual Dynamic Pricing
Topic: Distribution-free Contextual Dynamic Pricing
Time & Date: 10:30am-11:30am, Jun 10 (Beijing Time), 2021
Speaker: Prof. Wei SUN, Purdue University
Venue: Zoom, Meeting ID: 997 8595 4421, (Password: 800316)
Contextual dynamic pricing aims to set personalized prices based on sequential interactions with customers. At each time period, a customer who is interested in purchasing a product comes to the platform. The customer’s valuation for the product is a linear function of contexts, including product and customer features, plus some random market noise. The seller does not observe the customer’s true valuation, but instead needs to learn the valuation by leveraging contextual information and historical binary purchase feedbacks. Existing models typically assume full or partial knowledge of the random noise distribution. In this talk, I will consider a contextual dynamic pricing with unknown random noise. Our distribution-free pricing policy learns both the contextual function and the market noise simultaneously. A key ingredient of our method is a novel perturbed linear bandit framework, where a modified linear upper confidence bound algorithm is proposed to balance the exploration of market noise and the exploitation of the current knowledge for better pricing. We establish the regret upper bound and a matching lower bound of our policy in the perturbed linear bandit framework and prove a sub-linear regret bound in the considered pricing problem. Finally, we demonstrate the superior performance of our policy on simulations and a real-life auto-loan dataset. This talk is based on a joint work with Yiyun Luo and Yufeng Liu from UNC.
Will Wei Sun is currently an assistant professor at Krannert School of Management, Purdue University. Before that, he was an assistant professor at Miami Business School and a research scientist in the advertising science team at Yahoo labs. He obtained his PhD in Statistics from Purdue University in 2015. Dr. Sun’s research focuses reinforcement learning and tensor learning, with applications in computational advertising, dynamic pricing, recommender systems, and Neuroimaging analysis.