Consumer Search and Dynamic Preference: A Deep Structural Econometric Model

Posted: 13 Dec 2023

See all articles by Yicheng Song

Yicheng Song

University of Minnesota - Twin Cities - Carlson School of Management

Tianshu Sun

Cheung Kong Graduate School of Business; University of Southern California - Marshall School of Business

Date Written: December 9, 2023

Abstract

Modeling and exploiting consumers' dynamic preferences could lead to significant business opportunities. Deep learning methods empirically promise us advantageous capabilities in dealing with manifold consumer data to predict their future actions, but these data-driven opaque predictive approaches don't explicitly model consumer's decision-making processes, making them difficult to interpret. On the other hand, the economic theory of sequential search suggests that consumers adopt a sequential search strategy when looking for the best product to purchase, which involves searching through a series of alternatives until they find the best option that meets their preferences. Based on these two pillars, we propose a theory-driven deep learning model called consumer Preference Transformer (CPT), which leverages the deep learning model to learn dynamic consumer preferences and sequential search theory to model consumers' search and purchase decisions. CPT integrates these two building blocks into a unified model that can be estimated via end-to-end learning. Unlike regular deep learning methods, we incorporate economic theory that explicitly models the consumer's decision, opening up the black box of the model and providing reasonable interpretations of the formation process of dynamic consumer preferences. Our empirical evaluation results show the proposed CPT method outperforms state-of-the-art deep learning and structural econometric models in predicting consumer click and purchase actions. The deep structural econometric model also allows for the evaluation of different recommendation policies. The policy evaluation could help improve product recommendation strategies, such as which product and what attributes to show to improve user experience and revenues.

Keywords: Structural Econometric Model, Deep Learning, Transformer, Theory Driven Machine Learning

Suggested Citation

Song, Yicheng and Sun, Tianshu, Consumer Search and Dynamic Preference: A Deep Structural Econometric Model (December 9, 2023). Available at SSRN: https://ssrn.com/abstract=4659329

Yicheng Song (Contact Author)

University of Minnesota - Twin Cities - Carlson School of Management ( email )

19th Avenue South
Minneapolis, MN 55455
United States

HOME PAGE: http://https://www.yichengsong.com/

Tianshu Sun

Cheung Kong Graduate School of Business ( email )

1017, Oriental Plaza 1
No.1 Dong Chang'an Street
Beijing
China

University of Southern California - Marshall School of Business ( email )

3670 Trousdale Parkway
Bridge Hall 310B
Los Angeles, CA 90089
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Abstract Views
218
PlumX Metrics