Recommender systems employ the popular K-nearest neighbor collaborative filtering (K-CF) methodology and its variations for recommending the products. In K-CF approach, recommendation for a given user is computed based on the ratings of K-nearest neighbors. In K-CF approach, it can be noted that, the system identifies K neighbors for each user irrespective of the number of products he/she has rated. As a result, the user who have rated few products may get the less-similar neighbors and the user who have rated more products may miss the genuine neighbors. In the literature, the notion of lower-bound similarity has been proposed to improve the clustering performance in which the clusters are extracted by fixing the similarity threshold. In this paper, we have extended the notion of lower-bound similarity to recommender systems to improve the performance of K-CF approach. In the proposed approach, instead of fixing K for finding the neighborhood, the similarity threshold value is fixed to extract the neighbors for each user. As a result, each user gets appropriate number of neighbors based on the number of products rated by him/her in a dynamic manner. The experimental results, on MovieLens dataset, show that the proposed lower bound similarity CF approach improves the performance of recommender systems over K-CF approach.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.