An Effective Recommendation Algorithm for Improving Prediction Quality

A recommender system utilizes in general an information filtering technique called collaborative filtering. To improve prediction quality, collaborative filtering needs reinforcements such as utilizing useful attributes of the items as well as a more refined neighbor selection. In this paper we present that the recommender systems that utilizing the attributes of the items in collaborative filtering improves prediction quality. The experimental results show that the recommender systems using the attributes provide better prediction qualities than other methods that do not utilize the attributes.