How Recommendation Affects Customer Search: A Field Experiment

Speaker：YUAN Zhe（Researcher, School of Economics, Zhejiang University）

Host：HAO Tongtong, Associate Professor, Lingnan College

Time and Date：14:30, Mar. 3, 2023

Venue：Wang Daohan Meeting room, Lingnan hall 

Language: English + Chinese

Abstract：

Product recommendation and search are two technology-mediated channels through which E-commerce platforms can help customers find products: Customers are passive in the former and proactive in the latter. However, the relationship between the two channels, and the underlying mechanisms and implications for platform design are not well understood. We use a randomized field experiment with 555,800 customers on a large E-commerce platform to investigate how product recommendation affects customer search. We vary the quality of the recommendation that users experience upon arriving at the homepage of the platform and find that a decrease in the recommendation relevance leads to a significant increase in the consumer’s use of search channel, indicating a (partial) substitution effect between the two at the aggregate level. We propose a conceptual framework and theorize how different states of customer demand—demand fulfillment and demand formation—may drive such a relationship. We further exploit the rich heterogeneity across user groups and product categories and use computational linguistic methods to examine customers’ search queries in detail. The results are aligned with our framework and provide evidence that both demand formation and demand fulfillment are at work in the channel interactions between recommendation and search: demand formation is associated with channel complementarity and demand fulfillment is associated with channel substitution. Specifically, when customers receive more product recommendation in a category, they search more in that category and search with generic query words, which indicates a complementarity between recommendation and search. But when customers receive less product recommendation in a category that they are interested in, they compensate for this reduction by searching more in that category and search with long-tail query words, which indicates a substitution between recommendation and search. However, we do not find substitution or complementarity when customers receive less product recommendation in categories that they are not interested in. This experimental study is among the first to examine the causal relationship between the recommendation channel and search channel and offers implications on the design of E-commerce platforms.

Profile of the speaker:

Zhe Yuan is an assistant professor at Zhejiang University. Zhe graduated from University of Toronto (Ph.D.), UBC (M.A.) and Peking University (B.A.). Before joining Zhejiang University, he worked at Alibaba Group as an economist. Zhe's specialty is Industrial Organization and Digital Economy with research interest in network economy (airline network and telecommunication network), platform growth (search engine and recommendation systems design, AI adoption), platform governance (data value/privacy information design/platform mechanism design).