Skip to Main Content
This is a study of the long tail problem of recommender systems when many items in the long tail have only a few ratings, thus making it hard to use them in recommender systems. The approach presented in this paper clusters items according to their popularities, so that the recommendations for tail items are based on the ratings in more intensively clustered groups and for the head items are based on the ratings of individual items or groups, clustered to a lesser extent. We apply this method to two real-life data sets and compare the results with those of the nongrouping and fully grouped methods in terms of recommendation accuracy and scalability. The results show that if such adaptive clustering is done properly, this method reduces the recommendation error rates for the tail items, while maintaining reasonable computational performance.