Dynamic Bayesian Network-Based Product Recommendation Considering Consumers' Multistage Shopping Journeys: A Marketing Funnel Perspective

Qiang Wei, Yao Mu, Xunhua Guo, Weijie Jiang, Guoqing Chen

Abstract: Recommender systems are widely used by online merchants to find the products that are likely to interest consumers, but existing dynamic methods still face challenges regarding diverse behaviors, variability in interest shifts, and the identification of psychological dynamics. Premised on the marketing funnel perspective to analyze consumer shopping journeys, this study proposes a novel machine learning approach for product recommendation, namely, multistage dynamic Bayesian network (MS-DBN), to model the generative processes of consumers’ interactive behaviors with products in light of stage transitions and interest shifts. This approach features a dynamic Bayesian network model to overcome the problem of diverse behaviors and extract generalizable regularity of consumers’ psychological dynamics, two latent layers to depict variability in consumers’ interest shifts across multiple stages, and the identification strategies that dynamically detect the invisible stages and interests of consumers. Extensive experiments on large-scale real-world data and comprehensive robustness checks manifest the superior performance of the proposed MS-DBN approach over baseline methods. History: Olivia Liu Sheng, Senior Editor; Huimin Zhao, Associate Editor. Funding: This work was supported by the National Natural Science Foundation of China [Grants 72172070, 72302153, 72293561, and 92246001]. Supplemental Material: The online appendices are available at https://doi.org/10.1287/isre.2020.0277.

External IDs:dblp:journals/isr/WeiMGJC24