Complements and substitutes in online product recommendations: The differential effects on consumers’ willingness to pay

Online product recommendations have been shown to influence consumers’ preferences and purchasing behaviors for recommended products. However, it remains an open empirical question whether and how recommendations of other products affect a consumer’s economic behavior for a focal product. In many e-...

Full description

Saved in:
Bibliographic Details
Published inInformation & management Vol. 57; no. 6; p. 103341
Main Authors Zhang, Mingyue, Bockstedt, Jesse
Format Journal Article
LanguageEnglish
Published Elsevier B.V 01.09.2020
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:Online product recommendations have been shown to influence consumers’ preferences and purchasing behaviors for recommended products. However, it remains an open empirical question whether and how recommendations of other products affect a consumer’s economic behavior for a focal product. In many e-commerce websites, a product is presented with co-purchase and co-view recommendations, which potentially contain complementary and substitutable products, respectively. Very little research has explored differential effects of recommending complementary and substitutable products. In this study, we explore how types of other recommended products impact consumers’ willingness to pay for a focal product through interactions with prices of recommended products and consumers’ decision stages. We conducted a 23 randomized factorial experiment as well as two 2 × 2 experiments to examine these issues. Experimental results provide evidence that there is a significant interaction effect between the recommendation type and decision stage, which highlights the importance of recommendation timing on e-commerce platforms. Furthermore, it also illustrates that the effect of recommending complementary vs. substitutable products is subject to contextual factors such as consumers’ decision stages. Results of our study have significant implications for the design and application of online recommender systems.
ISSN:0378-7206
1872-7530
DOI:10.1016/j.im.2020.103341