In order to solve data sparsity and inaccurate recommended item lists in traditional collaborative
filtering algorithms, a collaborative filtering recommendation algorithm is proposed in this
paper on the basis of information related to user potential. By applying user attributes data to the
scoring matrix, the algorithm integrates the project clustering method and the time sign of user
scoring into the project recommendation process, reducing the sparseness of scoring matrix and
improving the recommendation accuracy to a certain extent. For illustration, this paper also uses
samples of movie recommendations to test the feasibility of the algorithm. Empirical results
show that the proposed methods can effectively improve the overall performance of the
proposed system, provided that the data related to user attributes, the time stamp and the project
clustering method are properly applied. Therefore, this algorithm system provides an effective
solution to the problems of data sparsity and low accuracy in collaborative filtering algorithms.