Date:
Location:
Our upcoming event for the Statistics Department Colloquium Series is scheduled for Monday, November 20 from 12:00 – 1:00pm (ET) and will be an in-person presentation Science Center Rm. 316. Lunch will be provided to guests following the talk. This week's speaker will be Linda Zhao of the Statistics Department at the University of Pennsylvania.
Doubly High-Dimensional Contextual Bandits: An Interpretable Model for Joint Assortment-Pricing
Abstract:
Key challenges in running a retail business include how to select products to present to consumers (the assortment problem), and how to price products (the pricing problem) to maximize revenue or profit. Instead of considering these problems in isolation, we propose a joint approach to assortment-pricing based on contextual bandits. Our model is doubly high-dimensional, in that both context vectors and actions are allowed to take values in high-dimensional spaces. In order to circumvent the curse of dimensionality, we propose a simple yet flexible model that captures the interactions between covariates and actions via a (near) low-rank representation matrix. The resulting class of models is reasonably expressive while remaining interpretable through latent factors, and includes various structured linear bandit and pricing models as particular cases. We propose a computationally tractable procedure that combines an exploration/exploitation protocol with an efficient low-rank matrix estimator, and we prove bounds on its regret. Simulation results show that this method has lower regret than state-of-the-art methods applied to various standard bandit and pricing models. Real-world case studies on the assortment-pricing problem, from an industry-leading instant noodles company to an emerging beauty start-up, underscore the gains achievable using our method. In each case, we show at least three-fold gains in revenue or profit by our bandit method, as well as the interpretability of the latent factor models that are learned.
Joint work with Cai, J., Chen, R. and Wainwright, M.
About: Linda Zhao is a full professor of statistics at the Wharton School. She received her Ph.D. from Cornell in 1993 and has been with the University of Pennsylvania since 1994. A fellow of the Institute of Mathematical Statistics (IMS), Linda has been actively engaged in her academic career. Her specialty falls in modern machine learning methods, replicability in science, network and high-dimensional data, housing price prediction, and Bayesian methods. Her current projects include data-driven decision-making via RL; equity ownership networks and their relationship to firm performance and innovation activities; identifying signals from noisy data using a non-parametric Bayesian scheme; and conducting model-free data analysis. Her work has won NSF support for over 20 years. For the past seven years, she has been developing and teaching a modern data mining course to undergraduate, MBA, Master's, and Ph.D. students across the entire Penn campus. She is also an avid ballroom dancer and loves to travel around the world.