数字内容技术与服务研究中心知识库

Collaborative filtering is widely used in recommender systems. When training data are extremely sparse, neighbor selection methods work ineffectively. To address this issue, this paper proposes a distributed representation model that represents users as low-dimensional vectors for neighbor selection by considering the chronological order of users' ratings. Experiments show that the proposed method outperforms the state-of-the-art methods solving the sparsity problem with regard to precision and ranking quality.