Study Of Collaborative Filtering Algorithms Based On Layered Strategy

Traditional Top-N strategy for movie recommendation takes only users’ratings into account when mining users’needs or interests. But watching movie is a special behavior, in which users’ interests should not just be represented by their ratings. We think that the decision to watch a movie also reflects the target users’needs, even though he or she may give it a low rating. In this paper, we introduce two factors, i.e. Users’ Tastes and Users’Choices to describe users’needs.The analysis of relationships between them gives us a new explanation for the lay-ered structure of users’ratings. Then, inspired by Maslow’s Hierarchy of Needs theory, we present a layered perspective of users’interests and design an efficient and effec-tive recommendation strategy based on collaborative filtering models to meet users’ layered needs.The main contributions of this paper include:(1)we present a new perspective of user’s needs. Inspired by Maslow’s Hierarchy of Needs theory, we interpret users’lay-ered ratings as users’layered needs. (2) We propose a novel recommendation strategy to meet user’s layered needs. In our work, traditional CF models are extended with three layering methods to improve the influence of User’s Choices on recommendation results.Experimental results based on two real world data sets demonstrate that our model can produce better accuracy and performance.