Bad side of eCommerce recommendation systems: Overemphasis on hits and blockbusters

Recommender systems like those at Amazon, Netflix, and Apple's iTune Store work against niche products and tend to direct customers to blockbuster hits, according to the Management Insights feature in the current issue of Management Science, the flagship journal of the Institute for Operations Research and the Management Sciences (INFORMS®). Management Insights, a regular feature of the journal, is a digest of important research in business, management, operations research, and management science. It appears in every issue of the monthly journal.

"Blockbuster Culture's Next Rise or Fall: The Impact of Recommender Systems on Sales Diversity" is by Daniel Fleder and Kartik Hosanagar of the Wharton School.

The last ten years have seen an extraordinary increase in the number of products available. This trend is part of the "long tail" phenomenon, and many believe that it could amount to a cultural shift from hit to niche goods.

A difficulty that arises, however, is how consumers will find their ideal, niche products among myriad choices. Recommender systems are one solution. These systems use data on purchases and user profiles to identify which products are best suited to each user.

Although recommenders have been assumed to diversify choice, the authors show why some systems may do the opposite. Recommenders can create self-reinforcing cycles in which popular items are recommended more, recommended items are purchased more, purchased items are recommended even more, and so on. These cycles reduce diversity. Consequently, consumers and niche producers may be underserved if there exist better product matches outside of the hits, and retailers may find that they offer the right assortment but their recommender system may be promoting a narrow range of products.

The authors recommend that managers consider design modifications to ensure that their recommender system limits these popularity effects and promotes exploration.

Source: Institute for Operations Research and the Management Sciences