Clustering Technique for Collaborative Filtering and the Application to Venue Recommendation

Collaborative Filtering(CF) is a well-known technique in recommender systems. CF exploits the relationships between users and recommends the items to the active user according to the ratings of his/her neighbors. CF suffers from the data sparsity problem, where users only rate a small set of items. That makes the computation of similarity between users imprecise and consequently reduces the accuracy of CF algorithms. In this paper, we propose to use clustering techniques on the social network of users to derive the recommendations. We study the application of this approach to academic venue recommendation. Our interest is to support researchers, especially young PhD students, to find the right venues or the right communities. Using the data from DBLP digital library, the evaluation shows that our clustering technique based CF performs better than the traditional CF algorithms.