基于改进K-近邻规则的数据库营销分析  

Analysis of Database Marketing Based on Improved K-nearest Neighbors Rule

作　　者：王昱[1] 朱芝孺 Wang Yu;Zhu Zhiru(School of Economics ＆ Business Administration,Chongqing University,Chongqing 400030,China)

机构地区：[1]重庆大学经济与工商管理学院

出　　处：《统计与决策》2018年第19期175-178,共4页Statistics & Decision

基　　金：国家自然科学基金面上项目(71471022)

摘　　要：文章提出一种基于改进K-近邻规则的数据库营销模型。根据数据样本的近邻信息动态确定其最优的近邻个数K,以避免人为设定K这一重要参数可能造成的影响。根据K个近邻距样本的距离,设定不同的投票权重以预测样本属于某一类别的概率。在实际数据集上的实证结果表明,提出的改进K-近邻规则不仅为K值设定提供了一种有效的方法,还能够提高数据库营销的准确性和结果的可解释性,可以有效应用于实际的数据库营销。This paper proposes a database marketing model based on improved K-nearest neighbors rule. Optimal number of neighbor K is determined according to the dynamic condition of neighborhood information so as to avoid the possible impact of human intervention on determining the important parameter K. According to the distance between K neighboring samples, the voting weights of different neighbors are set to obtain the probability of predicting a sample belonging to a certain class. The empirical study on a real-world dataset indicates that the proposed approach not only provides an effective way to determine the optimal K value in K-nearest neighbors rule, but also improves the accuracy and interpretability of database marketing, which can be effectively applied to actual database marketing

关 键 词：K-近邻规则 近邻信息 数据库营销 

分 类 号：C931.6[经济管理—管理学]