Congratulations to Dr. Li Yang, Associate Professor of Marketing and Academic Advisor for the Integrated MBA Program at CKGSB, whose research article, “Modeling Dynamic Heterogeneity Using Gaussian Processes” has been selected as one of four finalists for the Journal of Marketing Research’s 2021 Paul E. Green Award. Dr. Li’s paper offers a new modeling and computational methodology for big data in marketing to more precisely understand the changing individual’s behaviors and preferences.
This paper introduces a new model that can flexibly capture the changing individual’s preferences over time. Modelling of people’s preferences is fundamental to marketing, given its role in helping firms segment and target the market. Yet limited attention has been paid towards understanding the dynamics or changes within an individual’s preferences over time, despite its relevance in many contexts. Professor Li’s paper demonstrates how a common assumption in the literature that the population mean of the heterogeneity distribution evolves over time, but that an individual’s parameter trajectory remains at a fixed distance from this evolving mean can lead to biased model estimates, including for fundamental factors, like price elasticity.
This paper is among the first in marketing to build on the gaussian process (GP) methodology, while the hierarchical GP specification that Professor Li’s paper develops is new to the literature, more broadly. These innovations allow the analysing of statistical information both across people and time simultaneously. This novel framework offers greater flexibility, generality and precision, as illustrated in the paper.
Professor Li shares this recognition with Ryan Dew, Assistant Professor of Marketing at The Wharton School, University of Pennsylvania and Asim Ansari, William T. Dillard Professor of Marketing at Columbia Business School, Columbia University.
The Paul E. Green Award recognizes the best article in the Journal of Marketing Research within the last calendar year that demonstrates the most potential to contribute significantly to the theory, methods and practice of marketing research.
The Cheung Kong Graduate School of Business is China’s first privately-funded and research-focused business school with over 40 full-time faculty members dedicated to gaining a deeper understanding of the various areas in business management from a global perspective. After receiving the news, Dr. Li says, “Thank you to CKGSB for providing flexible working environment and generous financial support to conduct my research.”
Publication: Journal of Marketing Research, Vol. 57, Issue 1, Page(s): 55-77, February 2020
Authors: Ryan Dew, Asim Ansari, Yang Li
Marketing research relies on individual-level estimates to understand the rich heterogeneity of consumers, firms, and products. While much of the literature focuses on capturing static cross-sectional heterogeneity, little research has been done on modeling dynamic heterogeneity, or the heterogeneous evolution of individual-level model parameters. In this work, the authors propose a novel framework for capturing the dynamics of heterogeneity, using individual-level, latent, Bayesian nonparametric Gaussian processes. Similar to standard heterogeneity specifications, this Gaussian process dynamic heterogeneity (GPDH) specification models individual-level parameters as flexible variations around population-level trends, allowing for sharing of statistical information both across individuals and within individuals over time. This hierarchical structure provides precise individual-level insights regarding parameter dynamics. The authors show that GPDH nests existing heterogeneity specifications and that not flexibly capturing individual-level dynamics may result in biased parameter estimates. Substantively, they apply GPDH to understand preference dynamics and to model the evolution of online reviews. Across both applications, they find robust evidence of dynamic heterogeneity and illustrate GPDH’s rich managerial insights, with implications for targeting, pricing, and market structure analysis.