Context-Aware Recommender Systems: From Foundations to Recent Developments

Gediminas Adomavicius, Konstantin Bauman, Alexander Tuzhilin, Moshe Unger

Abstract: The importance of contextual information has been recognized by researchers and practitioners in many disciplines, including e-commerce, personalization, information retrieval, ubiquitous and mobile computing, data mining, marketing, and management. Prior work has extensively demonstrated that relevant contextual information does matter in recommender systems and that it is important to take this information into account when providing recommendations. We discuss the general notion of context and major approaches to modeling it in recommender systems, including explicit vs. latent and static vs. dynamic approaches. We also discuss three popular algorithmic paradigms—contextual pre-filtering, post-filtering, and modeling—for incorporating contextual information into the recommendation process, and survey the recent advances in contextual modeling that include tensor factorization, deep learning, and reinforcement learning techniques. We also discuss important directions for future research.