云模型与用户聚类的个性化推荐

针对传统推荐系统数据稀疏、相似性计算方法导致共同评分用户少的问题，提出利用云模型定性概念与定量数值转换的优势，研究云模型、用户聚类的个性化推荐改进算法。用户对项目属性评价的偏好，转换为用户对加权综合云模型表示的数字特征的偏好。利用改进的聚类算法，对评分数据、原始用户属性标准化后的信息进行聚类；同时考虑用户兴趣的变化，结合用户之间项目属性评价的综合云模型的相似度、用户对项目评分的聚类、用户属性聚类这三种方法产生的邻居用户的并集进行推荐。理论分析和实验结果表明，提出的改进算法不但解决数据稀疏性带来的共同评分用户少的弊端，即使是在新用户的情况下，仍能获得较低的平均绝对误差和平均平方误差

Personal recommendation based on cloud model and user clustering

In order to solve the problem of lack of co-rated users caused by data sparseness and similarity calculation method, the authors, by making use of the advantage of cloud model transformation between qualitative concept and quantitative numerical value, proposed an improved personal recommendation algorithm based on cloud model and users clustering. The users’ preference on the evaluation of item attribute was transformed to preference on digital characteristics represented by integrated cloud model. By using the improved clustering algorithm, the authors clustered the rating data and the standardized original user attribute information, and at the same time, by taking into account the changes of the users’ interests, recommended the neighbor users’ union generated by similarity based on integrated cloud model of items attributes evaluation between users, clustering of users for item rating, and clustering of user attributes these three methods. The theoretical analysis and experimental results show that the proposed improved algorithm can not only solve the problem of lack of co-rated users caused by data sparseness, but also obtain satisfactory mean absolute error and root-mean-square error even when the users are new.Theoretical analysis and experimental results show that the proposed improved algorithm can not only solve the problem of lack of co-rated users caused by sparseness data, but also obtain satisfactory mean absolute error and root-mean-square error even when the users are new.