Recommender Systems Build Commonality, not Factions

Wharton Professors  Kartik Hosanagar, Andreas Buja and Daniel M. Fleder have conducted a fascinating new study regarding recommender systems (in this case, iTunes recommendations). The authors chose to examine the arguments being made by various folks that, "Increased personalization is creating fragmentation throughout society."   For example, Cass Sunstein,law professor and head of the Obama administration's regulatory policy, has made such an argument.   The scholars examined how recommendation systems on the Internet affect consumer behavior.  They focused on iTunes for their study.   Here is what they found, according to the Knowledge@Wharton website:

"An increase in the volume of purchases was anticipated, the authors write, but the increase of roughly 50% was larger than expected. By comparison, the number of purchases made by the control group actually declined by a small amount. "The personalization system exposes you to a lot more items you like, so you consume more than you used to before," says Hosanagar. "As each consumer buys more, it increases the likelihood they have something in common." For the taste effect, the study results also show that once volume is controlled for, consumers buy a more similar mix of products after receiving recommendations.  In addition to purchasing more songs, the research showed that consumers who used the service became part of networks that intensified as a result of receiving suggestions about songs. The researchers, who plotted relationships between thousands of users and millions of songs, found a 23% increase in the percent of listeners with an artist in common compared to the control group.  The researchers also plotted combinations exploring the "distance" between pairs of users, or the number of people in the network between them. They wanted to determine whether those who initially were close on the network become closer, while others who were farther removed grew farther away, indicating fragmentation. The authors found that all kinds of users -- close as well as far -- became closer to one another on their networks in the treated group relative to the control group. The group that received recommendations showed more user-pairs becoming closer (36%), while fewer pairs (9.2%) moved farther apart. "The increase in similarity appears uniform: All types of users become closer to one another," the paper states. "Users who were close became closer, and users who were initially far became closer, too."

In sum, music recommendation systems tend to broaden consumer interests, rather than narrowing the individual's focus on a particular niche.  Hopefully, future studies will examine whether the same result occurs with other types of recommendation engines.  For more on the importance of recommendation systems in many markets, I highly recommend reading Chris Anderson's excellent book, The Long Tail.  In that book, he explains how companies such as NetFlix and Amazon have a much higher percentage of their sales coming from non-blockbuster hits than brick-and-mortar retailers.  They accomplish this through the digital nature of their business, and they drive those sales of less well-known products through things such as their recommendation engines.