Time-aware Recommender System Using Naive Bayes Classifier Weighting Technique

Collaborative filtering method have been widely used in the recommender system which has problems of scalability and highly time consuming between the process of recommendation and traditional method didn't concern over the difference of time that a user has rating for an item. In this paper, we proposed a Na ve Bayes Classifier technique that uses the user rating for the item and item information to construct a model with time awareness. It will provide better scalability and accuracy recommendation result even the system has more sparsity. In addition, it decreases time consuming by constructing a model in the offline and calculate the recommendation results in online phase. We show the result from our proposed can make the system get more efficient.