Multiple Content Items Based On The User's Personal Characteristics, Collaborative Filtering Recommendation

Recently, personalized recommender systems, especially collaborative filtering recommender systems, have achieved widespread successes on the Web. The tremendous growth in the amount of available information and the kinds of commodities to Web sites poses some key challenges for recommender systems, so the problems of cold-start and sparsity in collaborative filtering recommendation and Multiple-content problem of Item-based collaborative filtering algorithm are in dire need to be solved.By analyzing Multiple-content problem of Item-based collaborative filtering algorithm, an improved Item-based collaborative filtering algorithm was proposed. This new algorithm takes synthetically into account the influence of item attribute and user rating. In the nearest neighbors query, firstly compute similarity of item by the characteristics of attributes matrix of items to find out neighbor item candidate set, and then compute the similarity between the target item and item of candidate set by user rating matrix to find out the nearest neighbor item set. So the Multiple-content problem of Item-based collaborative filtering resolved. Experimental results indicate that the algorithm can solve Multiple-content problem and provide better recommendation results even though the user ratings are very sparsely.Individual user character determines users' consume in a certain extent. To address the problem of extreme sparseness of user rating data and new-user recommendation, a novel collaborative filtering algorithm based on user character is proposed. This method predicts item ratings that users have not rated by the similarity based on user character and adjusts the user rating matrix, then uses a new similarity measure to find the target users' neighbors.Then, experiments are designed. The results of the experiment are analyzed. The improved algorithm, the collaborative filtering recommendation algorithm and the content-based recommendation algorithm are compared, so that the accuracy of the improved algorithm is showed.Finally, the structure of the personalized recommender systems with the collaborative filtering algorithm based on user character that is proposed is illuminated, and the application of the personalized recommender systems with this algorithm in the industry of videos sale on web is introduced.