| 基于耦合关系的加权Slope One算法* |
| |
| 引用本文： | 沈学利,张 莹. 基于耦合关系的加权Slope One算法*[J]. 计算机应用研究, 2017, 34(12) |
| |
| 作者姓名： | 沈学利 张 莹 |
| |
| 作者单位： | 辽宁工程技术大学 电子与信息工程学院,辽宁工程技术大学 研究生院 |
| |
| 基金项目： | 国家青年科学基金(No.61003162) |
| |
| 摘 要： | Slope One算法就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,本文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Movielens数据集上进行验证表明具有较高的推荐准确度。
|
| 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 |
| 收稿时间： | 2016-11-28 |
| 修稿时间： | 2017-10-16 |
Based on the coupling relationship between weighted Slope One algorithm |
| |
| Shen xue li and Zhang ying. Based on the coupling relationship between weighted Slope One algorithm[J]. Application Research of Computers, 2017, 34(12) |
| |
| Authors: | Shen xue li and Zhang ying |
| |
| Affiliation: | School of Electronics and Information Engineering,Liaoning Technical University, |
| |
| Abstract: | 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 proposes a weighted Slope One algorithm based on coupling relationship. The algorithm constructs 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 Movielens dataset show that this algorithm has higher accuracy of recommendation. |
| |
| Keywords: | collaborative filtering Slope One algorithm item coupled similarity user coupled similarity |
|
| 点击此处可从《计算机应用研究》浏览原始摘要信息 |
|
点击此处可从《计算机应用研究》下载全文 |
