摘要
推荐系统包括两种主要方法,即协同过滤算法和基于内容的过滤算法,有助于提供有意义的建议。笔者使用了混合方法,即利用内容和协作过滤算法,讨论了算法与此领域之前工作的不同,同时,结合一种的分析方法,证明新方法的合理性,如何提供实用建议。上述方法在现有用户和对象数据上进行测试,与其他两种最受欢迎的方法--纯协同过滤和奇异值分解相比,具有改进效果。
Recommendation system includes two main methods, collaborative filtering algorithm and content-based filtering algorithm, which help to provide meaningful suggestions. The author uses a hybrid method, i.e. content and collaborative filtering algorithm, to discuss the difference between the algorithm and the previous work in this field. At the same time, combined with an analysis method, it proves the rationality of the new method and how to provide practical suggestions. Compared with the other two most popular methods, pure collaborative filtering and singular value decomposition, the above-mentioned methods have improved the performance.
作者
范志强
赵文涛
Fan Zhiqiang;Zhao Wentao(College of Computer Science and Technology, Henan Polytechnic University, Jiaozuo Henan 454000, China)
出处
《信息与电脑》
2019年第13期42-43,47,共3页
Information & Computer
关键词
推荐系统
稀疏性
协同过滤
基于内容的过滤
混合方法
recommendation system
sparsity
collaborative filtering
content-based filtering
hybrid approach