基于标签重要程度的协同过滤推荐算法

针对传统协同过滤推荐算法在用户隐式反馈数据挖掘不够充分、用户兴趣偏好模型过于粗糙,提出一种标签重要程度的协同过滤推荐算法。用户使用标签的种类和频率可以反映用户的偏好和偏好程度;在此基础上建立新的用户兴趣偏好模型,将标签对用户的影响程度进行量化,建立新的相似度计算方法。最后获得目标用户的近邻集合和预测评分,为目标用户实施有效推荐。实验结果表明该算法大幅度提高了推荐的精准度、缓解了冷启动问题。

Collaborative filtering recommendation algorithm based on tag importance

At the fact that the traditional collaborative filtering recommendation algorithm is insufficient in the number of users'' implicit feedback, and the user interest preference model is too rough, a collaborative filtering recommendation algorithm with the importance of tags is proposed. Type and frequency of use of the label reflects user preferences and preferences, in order to establish a new user preferences model for better mining and use implicit user feedback data will affect the degree of the label on the user to quantify, to establish a new method for similarity computation. The experimental results show that the proposed algorithm has obvious advantages, improves the recommendation accuracy and alleviates the cold start problem