数据缺失下的IFRSIFCM协同过滤推荐算法  

IFRSIFCM Collaborative Filtering Recommendation Algorithm with Missing Data

作　　者：张艳菊[1] 马璐 ZHANG Yan-ju;MA Lu(School of Business Administration,Liaoning Technical University,Huludao 125105,China)

机构地区：[1]辽宁工程技术大学工商管理学院,辽宁葫芦岛125105

出　　处：《控制工程》2022年第3期542-550,共9页Control Engineering of China

基　　金：2019年教育厅青年项目(LJ2019QL022)。

摘　　要：为了进一步提高协同过滤算法的精确性,更好地满足用户需求、进行商品推荐,针对传统推荐算法存在的缺失数据和模糊性问题,构建了直觉模糊粗糙集和基于目标函数的直觉模糊C均值聚类相结合的协同过滤推荐算法(IFRSIFCM-CF)。算法首先运用直觉模糊粗糙集对缺失数据进行处理,并计算直觉模糊数;其次用密度函数初始化聚类中心,并通过直觉模糊C均值聚类找到目标用户所在聚类类别;最后用特征系数代替传统相似系数来确定邻居集,用优先关系定序法代替传统的推荐算法形成推荐列表。在MovieLens与Jester数据集上对算法进行有效性检验,实验结果表明所提算法能够有效解决数据缺失问题并提高推荐精度。In order to further improve the accuracy of collaborative filtering algorithm,so as to better meet the needs of users and make commodity recommendation,aiming at the problems of missing data and fuzziness in traditional recommendation algorithms,a collaborative filtering recommendation algorithm based on intuitionistic fuzzy rough set and intuitionistic fuzzy C-means clustering based on objective function(IFRSIFCM-CF)is constructed.Firstly,the intuitionistic fuzzy rough set is used to deal with the missing data,and the intuitionistic fuzzy number is calculated.Secondly,the clustering center is initialized with the density function,and the clustering category of the target user is found by intuitionistic fuzzy C-means clustering.Finally,the feature coefficient is used instead of the traditional similarity coefficient to determine the neighbor set,and the priority relation ordering method is used to replace the traditional recommendation algorithm to form the recommendation list.The effectiveness of the algorithm is tested on MovieLens and Jester data sets,and the experimental results show that the algorithm can effectively solve the problem of missing data and improve the accuracy of recommendation.

关 键 词：模糊C均值聚类 协同过滤推荐算法 直觉模糊粗糙集 缺失数据 

分 类 号：TP391.3[自动化与计算机技术—计算机应用技术]