基于耦合关系的加权Slope One算法  

Weighted Slope One algorithm based on coupling relationship

作　　者：沈学利[1] 张莹 

机构地区：[1]辽宁工程技术大学电子与信息工程学院,辽宁葫芦岛125105 [2]辽宁工程技术大学研究生院,辽宁葫芦岛125105

出　　处：《计算机应用研究》2017年第12期3704-3707,共4页Application Research of Computers

基　　金：国家青年科学基金资助项目(61003162)

摘　　要：Slope One算法是一种基于项目的协同过滤推荐算法,它对项目属性内和属性间依赖耦合关系的考虑较为欠缺,推荐效果并不理想。基于此,提出一种基于耦合关系的加权Slope One算法。该算法构造了项目属性耦合关系模型和用户属性耦合关系模型,采取用户耦合相似度和项目耦合相似度对加权Slope One算法进行改进。本算法在Movie Lens数据集上进行验证表明具有较高的推荐准确度。Slope One algorithm is a kind of collaborative filtering recommendation algorithm based on the item,it considers the coupling relationship between the attributes and the attributes of the project is not enough. Based on this,this paper proposed a weighted Slope One algorithm based on coupling relationship. The algorithm constructed the item properties coupling model and user attributes coupling relationship model,taking the user similarity and item coupling of weighted similarity of Slope One algorithm was improved. Validated on Movie Lens dataset show that this algorithm has higher accuracy of recommendation.

关 键 词：协同过滤 SLOPE One算法 项目耦合相似度 用户耦合相似度 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]