基于人口统计学的改进聚类模型协同过滤算法

发布时间：2018-07-09 21:15

本文选题：协同过滤 + 人口统计学　；参考：《计算机科学》2017年03期

【摘要】：针对传统基于用户的协同过滤推荐算法在大数据环境下存在评分高维稀疏性、推荐精度低的问题,提出一种基于人口统计学数据与改进聚类模型相结合的协同过滤推荐算法,以提高推荐系统精度和泛化能力。该方法首先通过用户人口统计学数据属性,结合用户-项目评分矩阵计算各个用户间的相似度;然后对用户、项目进行分层近邻传播聚类,根据用户对项目的评分数据计算用户或项目之间的相似性,产生目标用户或项目的兴趣近邻;最后根据兴趣最近邻进行推荐。对Epinions,MovieLents等数据集进行仿真实验,仿真的结果表明,与传统的协同过滤算法相比,提出的算法提高了推荐精度,为传统的协同过滤推荐算法提供了参考。
[Abstract]:In order to solve the problem of high dimensionality sparsity and low recommendation accuracy in traditional user-based collaborative filtering recommendation algorithm in big data environment, a collaborative filtering recommendation algorithm based on demographic data and improved clustering model is proposed. In order to improve the accuracy and generalization of the recommendation system. In this method, the similarity between users is calculated by the attributes of user demographic data and the user-item scoring matrix, and then the users and items are clustered by hierarchical neighbor propagation. The similarity between users or items is calculated according to the evaluation data of users, and the nearest neighbor of interest of the target user or project is generated. Finally, the nearest neighbor of interest is recommended according to the nearest neighbor of interest. The simulation results of EpinionsMovie agents and other data sets show that compared with the traditional collaborative filtering algorithm, the proposed algorithm improves the recommendation accuracy and provides a reference for the traditional collaborative filtering recommendation algorithm.
【作者单位】：淮阴工学院计算机与软件工程学院;河海大学计算机与信息学院;
【基金】：国家自然科学基金(61403060) 江苏重点研发计划-产业前瞻与共性关键技术(BE2015127) 江苏省高校自然科学研究面上项目(15KJB520004) 江苏省先进制造技术重点实验室开放基金(HGAMTL-1401) 江苏省科技厅产学研联合研究项目(BY2014097) 淮安市科技计划项目(HAG2015060,HAG201602,HAC201601)资助
【分类号】：TP391.3

【相似文献】