Bad Side of eCommerce Recommendation Systems: Overemphasis on Hits and Blockbusters

HANOVER, MD, May 14, 2009 – Recommender systems like those at Amazon, Netflix, and Apple’s iTune Store may work against niche products by directing 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.

The current issue of Management Insights is available here. The full papers associated with the Insights are available to Management Science subscribers. Individual papers can be purchased at http://institutions.informs.org. Additional issues of Management Insights can be accessed here.

The other Insights in the current issue are:

• On the Value of Commitment and Availability Guarantees When Selling to Strategic Consumers by Xuanming Su, Fuqiang Zhang
• An Optimal Contact Model for Maximizing Online Panel Response Rates by Scott A. Neslin, Thomas P. Novak, Kenneth R. Baker, Donna L. Hoffman
• Contagion of Wishful Thinking in Markets by Nicholas Seybert, Robert Bloomfield
• Quasi-Robust Multiagent Contracts by Anil Arya, Joel Demski, Jonathan Glover, Pierre Liang
• Multiple Sourcing and Procurement Process Selection with Bidding Events by Tunay I. Tunca, Qiong Wu
• Information Sharing and Order Variability Control Under a Generalized Demand Model by Li Chen, Hau L. Lee
• A Generalized Approach to Portfolio Optimization: Improving Performance by Constraining Portfolio Norms by Victor DeMiguel, Lorenzo Garlappi, Francisco J. Nogales, Raman Uppal
• Optimal Policies and Approximations for a Bayesian Linear Regression Inventory Model by Katy S. Azoury, Julia Miyaoka
• Information Market-Based Decision Fusion by Johan Perols, Kaushal Chari, Manish Agrawal
• Private Network EDI vs. Internet Electronic Markets: A Direct Comparison of Fulfillment Performance by Yuliang Yao, Martin Dresner, Jonathan Palmer
• Loss Functions in Option Valuation: A Framework for Selection by Dennis Bams, Thorsten Lehnert, Christian C. P. Wolff
• Additive Utility in Prospect Theory by Han Bleichrodt, Ulrich Schmidt, Horst Zank

INFORMS journals are strongly cited in Journal Citation Reports, an industry source. In the JCR subject category “operations research and management science,” Management Science ranked in the top 10 along with two other INFORMS journals.

The special MBA issue published by BusinessWeek includes Management Science and three other INFORMS journals in its list of 20 top academic journals that are used to evaluate business school programs. Financial Times includes Management Science and four other INFORMS journals in its list of academic journals used to evaluate MBA programs.

About INFORMS

The Institute for Operations Research and the Management Sciences (INFORMS®) is an international scientific society with 10,000 members, including Nobel Prize laureates, dedicated to applying scientific methods to help improve decision-making, management, and operations. Members of INFORMS work in business, government, and academia. They are represented in fields as diverse as airlines, health care, law enforcement, the military, financial engineering, and telecommunications. The INFORMS website is www.informs.org. More information about operations research is at www.scienceofbetter.org.

###