期刊
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS
卷 E102D, 期 4, 页码 737-744出版社
IEICE-INST ELECTRONICS INFORMATION COMMUNICATION ENGINEERS
DOI: 10.1587/transinf.2018DAP0003
关键词
top-N recommendation; sequential recommendation; recurrent neural network; word embedding; item embedding; time dependent; cold start
资金
- Special Fund for Strategic Pilot Technology of Chinese Academy of Sciences [XDA06040602]
- National Science and Technology Major Project [2017ZX03001019]
To solve the low accuracy problem of the recommender system for long term users, in this paper, we propose a top-N-balanced sequential recommendation based on recurrent neural network. We postulated and verified that the interactions between users and items is time-dependent in the long term, but in the short term, it is time-independent. We balance the top-N recommendation and sequential recommendation to generate a better recommender list by improving the loss function and generation method. The experimental results demonstrate the effectiveness of our method. Compared with a state-of-the-art recommender algorithm, our method clearly improves the performance of the recommendation on hit rate. Besides the improvement of the basic performance, our method can also handle the cold start problem and supply new users with the same quality of service as the old users.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据