Product Recommendation and Consumer Search

ABSTRACT

We study an online environment where a firm provides strategic product recommendations to consumers. We develop an analytical framework to integrate recommendations into the consumer search process. The firm sells two imperfectly substitutable products with different profit margins and makes a personalized product recommendation to each consumer based on its uncertainty (lack of knowledge) of his preferences. We define recommendation bias as the firm’s deliberate decision to recommend a product to a consumer that does not minimize expected misfit cost of the consumer. Consumers can accept the product recommendation, search for the nonrecommended product, or leave the website. We identify five consumer segments based on consumers’ responses to the firm’s recommendations. We show that the recommendation bias, profit, and consumer surplus depend on the interaction between the firm’s uncertainty regarding consumer preferences and consumer search costs. A reduction in its uncertainty about consumers leads to a corresponding increase in the firm’s profit but does not necessarily result in a reduction in consumer surplus. An increase in search costs can lead to nonmonotonic changes in the firm’s recommendation strategy, causing an increase or decrease in recommendation bias when the firm’s uncertainty about consumers is low. Furthermore, the firm’s profit can behave non-monotonically with respect to search costs: the firm benefits from an increase in search costs when these costs are small and uncertainty about consumers is low, but it can be adversely affected when search costs are moderate. Interestingly, consumer surplus may increase when search costs increase.

KEYWORDS:

• Recommendation bias
• consumer search
• digital commerce
• firm uncertainty
• product recommendation
• recommendation strategy
• search cost
• online recommenders
• online commerce

Acknowledgments

We thank the Guest Editors, Rob Kauffman and Atanu Lahiri, for their constructive comments and guidance throughout the review process.

Supplemental data

Supplemental data for this article can be accessed online at https://doi.org/10.1080/07421222.2023.2229123.

Notes

¹ For example, products may be sourced from different suppliers. In the case of online media streaming, Netflix and Spotify pay different royalties to content production studios. It has been reported that Netflix pays a large amount of royalties to third-party content providers. In contrast, Netflix pays smaller royalties to studios for its own original programming. In addition, providers such as Netflix pay for the Internet bandwidth and server capacity that support streaming services on their platforms. For example, Netflix may incur a higher cost to support the streaming of high definition (HD) content of a longer duration than that of non-HD content of a shorter duration. Moreover, YouTube and USA Today generate revenue from advertisements that are displayed on their platforms, and the advertising revenue depends on the rating and number of views.

² For example, customers of Netflix often receive emails from Netflix which include recommendations for content that they have not viewed yet. This saves time and effort for customers. Furthermore, consumers would still need to assess the product location (e.g., examining the product information, regardless of the product being recommended or not recommended by the firm before consumption).

³ Consumers incur both costs if they search for the non-recommended product. This is consistent with Fleder and Hosanagar [13, p. 706], who argue that recommendation systems facilitate “the ease of clicking a recommended item versus continuing to search through a firm’s website.”

⁴ The non-zero cost of assessing both products would increase the relative attractiveness of the outside option without affecting the relative attractiveness of recommendation versus search. Since we already define V as the relative attractiveness of the product for the outside option, this assumption does not change our results.

Additional information

Notes on contributors

Vidyanand Choudhary

Vidyanand Choudhary ([email protected]) is a professor at the Paul Merage School of Business, University of California, Irvine and a Senior Editor of Production and Operations Management. Previously, he served as the Associate Dean for Undergraduate programs and Senior Associate Dean at the Merage School. He conducts research in the area of Economics of Information Systems. His research has been published in various journals such as Management Science and Information Systems Research.

Zhe (James) Zhang

Zhe (James) Zhang ([email protected]; corresponding author) is an associate professor of Information Systems in the Naveen Jindal School of Management at the University of Texas at Dallas. He studies how IT and the Internet have digitally transformed products and markets, and how firms should respond to this paradigm shift. His papers have been published in various journals such as Information Systems Research, MIS Quarterly, and Production and Operations Management.