Collaborative Filtering Algorithm Based on Item Attribute and Time Weight
Qian Chen, Wanggen Li, Jiao Liu · 2016
Collaborative filtering is a recommendation algorithm which is used in personalized system.To solve the problem of low accuracy caused by sparse data in the user-item matrix of traditional collaborative filtering algorithm, this paper presents a hybrid algorithm.Firstly, it uses the data based on the similarity of item's attributes to fill the matrix.And then a weight decrease by the time is given to increase the effectiveness of the measurement, thereby to improve the accuracy of the collaborative filtering algorithm.Experimental results show that the algorithm proposed in this paper can improve the accuracy of recognition and enhance the quality of the recommendation system.