| 基于项目分层的个性化推荐方法 |
| |
| 引用本文： | 雷瑛,吴晶,熊璋.基于项目分层的个性化推荐方法[J].计算机工程与设计,2007,28(21):5257-5260. |
| |
| 作者姓名： | 雷瑛 吴晶 熊璋 |
| |
| 作者单位： | 北京航空航天大学,计算机学院,北京,100083 |
| |
| 摘 要： | 协同过滤目前较为成功地应用于个性化推荐系统中.但随着系统规模的扩大和待推荐项目的不断增加,协同过滤面临着稀疏性问题和新项目推荐问题,制约了推荐效果.在此分析了传统协同过滤推荐方法中存在的问题,提出一种基于项目分层的个性化推荐方法.采用了基于多层兴趣表示的用户相似性算法,并结合相似用户推荐项与项目相似性来推荐新项目.该推荐方法在稀疏数据集上能表现出较好的推荐质量,同时也能够有效地解决新项目推荐问题.
|
| 关 键 词： | 个性化推荐 协同过滤 相似性 分层 推荐算法 基于项目 个性化 推荐方法 hierarchy item based schema recommendation 推荐质量 表现 稀疏数据集 项目相似性 合相似 相似性算法 用户 存在 分析 效果 稀疏性问题 项目推荐 |
| 文章编号： | 1000-7024（2007）21-5257-04 |
| 修稿时间： | 2006-11-09 |
Personalization recommendation schema based on item hierarchy |
| |
| LEI Ying,WU Jing,XIONG Zhang.Personalization recommendation schema based on item hierarchy[J].Computer Engineering and Design,2007,28(21):5257-5260. |
| |
| Authors: | LEI Ying WU Jing XIONG Zhang |
| |
| Affiliation: | School of Computer Science and Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100083, China |
| |
| Abstract: | Collaborative filtering is a successful technology for building recommendation systems.But with the expanse of the systems and a large number of new items,this method faces problems such as sparsity and recommendation of new items,which makes the re- commendation efficiency decline.Problems in collaborative filtering are analyzed and a method based item hierarchy is suggested.It used the arithmetic of user's similarity based multilayer user-item matrix,and recommended new items through combining the similarity of items and the items which recommended by similar users.This method represents better efficiency when the data is sparse and solve the problems of the recommendation of new items. |
| |
| Keywords: | personalizationrecommendation collaborative filtering similarity hierarchy recommendation algorithm |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
