摘要
协同过滤算法近年来在电子商务推荐系统中得到了广泛的应用,但该算法也存在数据稀疏性和缺乏个性化等问题,这些问题影响了推荐算法的效率和准确性。主要针对以上问题,提出引入Web日志分析的协同过滤算法,将用户对商品的隐性兴趣转化为显性兴趣,同时利用用户聚类等相关技术,不仅解决数据稀疏的问题也提高推荐的准确性。
Collaborative filtering algorithm has been widely used in the electronic commerce recommendation system in recent years,but collaborative filtering algorithm also has some problems,such as data sparseness and lack of individuation,these problems affected the efficiency and accuracy of recommendation algorithm.According to the problems,proposes the method of Web log analysis and user clustering related technology,this method transforms implicit interest to explicit interest of user for commodities,it not only solves the problem sparse data but also improve the recommend of accuracy.
出处
《现代计算机》
2011年第4期68-71,共4页
Modern Computer
关键词
日志分析
用户聚类
协同过滤
电子商务
Log Analysis
User Clustering
Collaborative Filtering
Electronic Commerce
