Making Sense of Recommendations

Citation:

Yeomans, Mike, Anuj K. Shah, Sendhil Mullainathan, and Jon Kleinberg. Working Paper. “Making Sense of Recommendations”.
recommenders55.pdf428 KB

Date Published:

2016

Abstract:

Algorithms are increasingly being used to make recommendations about matters of taste, expanding their scope into domains that are primarily subjective. This raises two important questions. How accurately can algorithms predict subjective preferences, compared to human recommenders? And how much do people trust them? Recommender systems face several disadvantages: They have no preferences of their own and they do not model their recommendations after the way people make recommendations. In a series of experiments, however, we find that recommender systems outperform human recommenders, even in a domain where people have a lot of experience and well-developed tastes: Predicting what people will find funny. Moreover, these recommender systems outperform friends, family members, and significant others. But people do not trust these recommender systems. They do not use them to make recommendations for others, and they prefer to receive recommendations from other people instead. We find that this lack of trust partly stems from the fact that machine recommendations seem harder to understand than human recommendations. But, simple explanations of recommender systems can alleviate this distrust.

Last updated on 02/21/2017