Computer Engineering and Applications ›› 2012, Vol. 48 ›› Issue (13): 63-66.

Previous Articles     Next Articles

Study of non-personalized recommender systems based on vague value

CUI Chunsheng1, SU Baiyun2   

  1. 1.College of Computer and Information Engineering, Henan University of Economics and Law, Zhengzhou 450002, China
    2.Department of Mathematics and Information Science, Henan University of Economics and Law, Zhengzhou 450002, China
  • Online:2012-05-01 Published:2012-05-09

基于Vague值的非个性化产品推荐研究

崔春生1,苏白云2   

  1. 1.河南财经政法大学 计算机与信息工程学院,郑州 450002
    2.河南财经政法大学 数学与信息科学系,郑州 450002

Abstract: Non-personalized recommender systems has become a popular online advertising method due to the comprehensive applications of users and products. In the previous research, Vague value method has been used to study the recommender system, which is approved to be used in this field. The general characteristics and advantages of non-personalized recommender are reviewed. Hence, the feasibilities of using eigenvalue method and the “Matthew Effect” score function method in products-ranking are studied based on description of products by Vague set. The effectiveness and coconscious of two methods are then proved with examples.

Key words: non-personalized recommender systems, Vague value, eigenvalue, “Matthew Effect&rdquo, score function

摘要: 在网络用户和网络产品急剧攀升的背景下,非个性化产品推荐成为一种很好的网络广告手段,已有的研究中,Vague集方法已被应用于推荐系统中,并取得了较好的效果。分析了非个性化产品推荐的一般特征和优点;借助Vague值描述的产品,研究了特征值方法和“马太效应”记分函数方法运用于产品排序的可行性;最后,通过实例验证了两种方法的在非个性化产品推荐中的有效性和一致性。

关键词: 非个性化推荐, Vague值, 特征值, &ldquo, 马太效应&rdquo, 函数