A Survey of Collaborative Filtering Algorithms for Social Recommender Systems

Abstract

This paper introduces the status of social recommender system research in general and collaborative filtering in particular. For the collaborative filtering, the paper shows the basic principles and formulas of two basic approaches, the user-based collaborative filtering and the item-based collaborative filtering. For the user or item similarity calculation, the paper compares the differences between the cosine-based similarity, the revised cosine-based similarity and the Pearson-based similarity. The paper also analyzes the three main challenges of the collaborative filtering algorithm and shows the related works facing the challenges. To solve the Cold Start problem and reduce the cost of best neighborhood calculation, the paper provides several solutions. At last it discusses the future of the collaborative filtering algorithm in social recommender system.