Advertising as Information for Ranking E-Commerce Search Listings

Abstract

Search engines and e-commerce platforms have substantial difficulty exposing new products to their users on account of an information problem: new products typically do not have enough sales or other user-engagement that enables platforms to reliably assess product quality. This paper evaluates the role of advertising in providing information to the platform regarding new product quality so as to solve this cold-start problem and engineer higher quality organic listings. If sellers' advertising decisions predict the quality of new products, incorporating the advertising propensity of sellers into the search ranking algorithm can help obtain higher quality listings. Using a large-scale experiment implemented at JD.com---a large e-commerce platform in China---we show that using ad propensity information for ranking new products benefits both the platform and consumers, in the short run. Our findings showcase a new channel by which advertising can potentially improve outcomes for consumers and platforms in e-commerce, through its ability to reveal information that can be used by platforms to improve search ranking algorithms.