Recommender System Rethink: Implications for an Electronic Marketplace with Competing Manufacturers

Posted: 14 May 2018

See all articles by lusi li

lusi li

University of Texas at Dallas - Department of Information Systems & Operations Management

Jianqing Chen

The University of Texas at Dallas, Jindal School of Management

Srinivasan Raghunathan

University of Texas at Dallas - Naveen Jindal School of Management

Date Written: March 18, 2015

Abstract

Abstract Recommender systems that inform consumers about their likely ideal product have become the cornerstone of eCommerce platforms that sell products from competing manufacturers. Using a model of an electronic marketplace in which two competing manufacturers sell their products through a common retail platform, we study the effect of recommender systems on the retail platform, manufacturers, consumer surplus, and social welfare. In our setting, consumers are differentiated with respect to their preference for the two products (locational differentiation) and awareness about the two products (informational differentiation). A recommender system selects the recommendation based on a recommendation score which is a weighted sum of expected retailer profit and expected consumer value. We find that the recommender system may benefit or hurt the retailer and the manufacturers, depending on the signs and magnitudes of substitution effect and demand effect of the recommender system. The substitution effect of the recommender system either intensifies or softens the price competition between two manufacturers through two forces—its direct influence alters the informational differentiation of consumers (which affects the markup that manufacturers can charge) and its strategic influence motivates the manufacturers to use price as a lever to attract more recommendations in their favor. The demand effect of the recommender system increases overall consumer awareness, but, depending on the substitution effect, may increase or decrease the demand. The recommendation strategy, viz., the relative weight assigned to retailer profit vis-a-vis consumer value in computing the recommendation score, along with recommender system precision and relative sizes of consumers with different awareness level, determines whether the retailer benefits from the recommender system and by how much. We find that the retailer's optimal recommendation strategy is mildly profit oriented in the sense that it assigns a larger but not too-large a weight to retailer profit than consumer value, and that under the optimal strategy, the price competition is less intense and the retailer profit is higher compared to when there is no recommender system. Furthermore, an increase in either the recommender system precision or the fraction of consumers that are aware of at least one product induces the retailer to adopt a more profit oriented recommendation strategy.

Suggested Citation

li, lusi and Chen, Jianqing and Raghunathan, Srinivasan, Recommender System Rethink: Implications for an Electronic Marketplace with Competing Manufacturers (March 18, 2015). Available at SSRN: https://ssrn.com/abstract=3170609

Lusi Li

University of Texas at Dallas - Department of Information Systems & Operations Management ( email )

P.O. Box 830688
Richardson, TX 75083-0688
United States

Jianqing Chen (Contact Author)

The University of Texas at Dallas, Jindal School of Management ( email )

800 West Campbell Road
Richardson, TX 75080
United States

Srinivasan Raghunathan

University of Texas at Dallas - Naveen Jindal School of Management ( email )

P.O. Box 830688
Richardson, TX 75083-0688
United States

Here is the Coronavirus
related research on SSRN

Paper statistics

Abstract Views
488
PlumX Metrics