From Micro to Macro : Understanding User Preferences from Different Perspectives for Personalized Recommendation

In recent years, recommender systems have become widely utilized by businesses across industries. Given a set of users, items, and observed user-item interactions, these systems learn user preferences by collective intelligence, and deliver proper items under various contexts to improve user engagements and merchant profits. Collaborative Filtering is the most popular method for recommender systems. The principal idea of Collaborative Filtering is that users might be interested in the items that are preferred by users with similar preferences. Therefore, learning user preferences is the core technique of Collaborative Filtering. In this report, we first present an overview of several state-of-the-art Collaborative Filtering models. Afterwards, we discuss three perspectives to rethink the recommendation problem and some related work that attempts to improve recommender systems from these perspectives. Finally, we point out some potential opportunities for the future work.