Recommender Systems---Beyond Matrix Completion
Communications of the ACM, 59 (11):
94--102 (November 2016)DOI: 10.1145/2891406
Abstract
The future success of these systems depends on more than a Netflix challenge. Recommender systems have become a ubiquitous part of our daily online user experience and support users in a variety of domains. Today, the scientific community operationalizes the research problem mainly on principles from information retrieval and machine learning, leading to a well-defined but narrow problem characterization. We briefly review the history of the field, report on the recent advances, and propose a more comprehensive research approach that considers both the consumer's and the provider's perspective.
