Context-aware recommendation algorithm incorporating time information

There are two deficiencies in the traditional collaborative filtering recommendation. One is the data sparsity; the other is that the change of user preferences can't be reflected in time. To solve these problems, we propose a context-aware recommendation algorithm incorporating time information. Firstly, a calculating method of the time weight is presented. According to the user's rating time, we assign a different time weight to each rating. Then the time weight is incorporated into the basic matrix model. Secondly, we use the gradient descent method to calculate the matrix and predict the ratings directly based on the results of the matrix factorization. Finally, we conduct experiments on the MovieLens dataset and compare the performance of the proposed algorithm with other algorithms. Experimental results show that our algorithm can achieve higher recommendation accuracy. Copyright © 2012 Binary Information Press.