An Efficient Collaborative Filtering using New User Similarity Measure for Recommendation

Collaborative filtering has become one of the most used approaches to provide personalize services for users. The key of this approach is to find similar users or items using user-item rating matrix so that the system can show recommendations for user. However, most approaches related to this approach are based on similarity algorithms and this algorithm focus on only user item rating similarity calculation. These methods are not much effective, especially when the user rating data is extremely sparse and when only few ratings are available. To solve this problem research, propose an approach to compute the user similarity with the type of user-rating item. Research improved collaborative filtering algorithm based on user similarity combination, which combines the user similarity based on user-rating item and the user similarity based on the types of user-rating items. Research has also enhanced user-rating item similarity with new hybrid similarity. Experiments on classic MovieLens datasets are implemented. The result shows the superiority of the collaborative filtering approach in recommended performance.