基于高斯pLSA模型与项目的协同过滤混合推荐  

Hybrid Gaussian pLSA model and item based collaborative filtering recommendation

作　　者：陈登科[1] 孔繁胜[1] 

机构地区：[1]浙江大学计算机学院,杭州310027

出　　处：《计算机工程与应用》2010年第23期209-211,234,共4页Computer Engineering and Applications

摘　　要：协同过滤是推荐系统中常用的一种技术。以往的推荐算法往往只从用户或商品的角度单一地进行推荐,在推荐准确率上存在瓶颈和局限性。提出了一种新的混合推荐方法——结合基于高斯概率潜在语义分析模型与改进的基于项目的协同过滤算法,通过建立用户群体混合模型和基于目标项目的邻居集进行预测推荐。实验证明该算法与其他协同过滤算法相比具有更高的准确率。Collaborative Filtering（CF） is one of the most popular techniques that help users to make choices and find rele-vant items in a recommend system.Many proposed algorithms predict users preferences only based on the connections of users or products,which have bottlenecks and accuracy limitations.A hybird recommend method has been developed,which combines the Gaussian probabilistic latent semantic analysis and the improved item based collaborative filtering together.That method models a mixture of user communities and generates similar items of target item respectively.Experiments on the movielens dataset show that the proposed approach compares favorably with other collaborative filtering techniques.

关 键 词：概率潜在语义分析 高斯模型 基于项目的协同过滤 基于模型的协同过滤 混合推荐 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]