面向个性化推荐系统的二分网络协同过滤算法研究

为提高个性化推荐系统的推荐效率和准确性, 提出了个性化推荐系统的二分网络协同过滤算法。协同过滤算法引入二分网络描述个性化推荐系统, 使用灰色关联度来度量用户相似性和项目相似性, 对灰色关联相似度加权求和预测用户对项目的预测打分值, 从而提供给用户排序后的项目列表。实验结果表明, 协同过滤算法有效提高了过滤推荐的精准度和可靠性, 具有良好的推荐效果。

Research on collaborative filtering algorithm of bipartite network oriented to personal recommendation system

In order to improve the recommendation efficiency and accuracy of personalized recommendation system, this paper presented a collaborative filtering algorithm based on bipartite network for personalized recommendation system. The collaborative filtering algorithm described personal recommendation system using bipartite network, and used grey relationship degree to measure user similarity and object similarity. It forecasted the object score of user evaluation with similarity-weighted of grey relationship degree, and then provided ordered object list to every user. Experimental results show that the collaborative filtering algorithm can effectively resolve above problems, and it is higher accuracy and reliability and better recommendation results.