[1]王荣波,王亚杰,黄孝喜,等.基于多算法融合的移动通信客户流失预测模型[J].计算机技术与发展,2018,28(08):152-155.[doi:10.3969/ j. issn.1673-629X.2018.08.032]
　WANG Rong-bo,WANG Ya-jie,HUANG Xiao-xi,et al.Customer Churn Prediction Model of Mobile Communication Based on Multi-algorithm Fusion[J].,2018,28(08):152-155.[doi:10.3969/ j. issn.1673-629X.2018.08.032]
点击复制

基于多算法融合的移动通信客户流失预测模型()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
28
期数:
2018年08期
页码:
152-155
栏目:
应用开发研究
出版日期:
2018-08-10

文章信息/Info

Title:
Customer Churn Prediction Model of Mobile Communication Based on Multi-algorithm Fusion
文章编号:
1673-629X(2018)08-0152-04
作者:
王荣波; 王亚杰; 黄孝喜; 谌志群
杭州电子科技大学 计算机学院,浙江 杭州 310018
Author(s):
WANG Rong-bo; WANG Ya-jie; HUANG Xiao-xi; CHEN Zhi-qun
School of Computer Science and Technology,Hangzhou Dianzi University,Hangzhou 310018,China
关键词:
移动通信; 客户流失; 权重; 数据仓库; 组合模型
Keywords:
mobile communication; customer churn; weight; data warehouse; combinatorial model
分类号:
TP311.5
DOI:
10.3969/ j. issn.1673-629X.2018.08.032
文献标志码:
A
摘要:
针对移动通信行业中客户不断流失的现状,提出了一种优于传统单一算法模型预测的组合模型。 该组合模型的元模型分别为决策树模型、Logistic 回归模型和 BP 神经网络模型,该模型综合了各个元模型的优势。 通过构造拉格朗日函数的方式来确定每个元模型的最优权重,使组合后的预测模型达到最优的预测效果,并在某移动通信公司提供的数据仓库中随机选取足够数量的流失客户作为数据集进行实验。 实验结果表明,该模型在预测的正确率上比每一个元模型均有明显的提高。 该方法有很好的预测效果,能够帮助移动通信公司找出即将离网的客户,对其制定相应的业务来维护自身商业利益。 该方法的局限在于仅考虑了各个元模型间线性组合的情况。
Abstract:
Aiming at the present situation of the continuous loss of customers in the mobile communication industry,we propose a combi- natorial model which is superior to the traditional single algorithm model,of which the meta-model are the decision tree model,the logis- tic regression model and the BP neural network model. It combines the advantages of each meta-model. The optimal weight of each meta -model is determined by constructing the Lagrange function,and the combined prediction model is used to achieve the optimal prediction effect. In a data warehouse provided by a mobile communication company,a large number of lost customers are selected randomly as the data sets for experiment which shows that the model has a significant improvement in the accuracy of each model. The method has a great predictive effect,and can help mobile communication companies to find out the off-line customers,to develop their own business to maintain their own business interests. The limitation of this method is that only the linear combination of each meta-model is taken into account.

相似文献/References:

[1]肖楠 郑文岭 马文丽[] 梁斌.一种基于RFID的物流管理系统的设计[J].计算机技术与发展,2008,(07):237.
　XIAO Nan,ZHENG Wen-ling,MA Wen-li,et al.Design of Logistics Management System Based on RFID[J].,2008,(08):237.
[2]杨杉 何跃.数据仓库和数据挖掘技术在保险公司中的应用[J].计算机技术与发展,2011,(06):157.
　YANG Shan,HE Yue.Application of Data Warehouse and Data Mining to Life Insurance Company[J].,2011,(08):157.
[3]程艳云,张守超,杨杨. 基于大数据的时间序列预测研究与应用[J].计算机技术与发展,2016,26(06):175.
　CHENG Yan-yun,ZHANG Shou-chao,YANG Yang. Research and Application of Time Series Forecasting Based on Big Data[J].,2016,26(08):175.
[4]王振杰,王强民,杨小玲.基于移动云交换的智能 IoT 系统[J].计算机技术与发展,2018,28(10):199.[doi:10.3969/ j. issn.1673-629X.2018.10.041]
　WANG Zhen-jie,WANG Qiang-min,YANG Xiao-ling.Intelligent IoT System Based on Mobile Cloud Exchange[J].,2018,28(08):199.[doi:10.3969/ j. issn.1673-629X.2018.10.041]
[5]马文斌,夏国恩.基于深度神经网络的客户流失预测模型[J].计算机技术与发展,2019,29(09):76.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 015]
　MA Wen-bin,XIA Guo-en.Customer Churn Prediction Model Based on Deep Neural Network[J].,2019,29(08):76.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 015]
[6]胡永培,张 琛.基于 AP 聚类与随机森林的客户流失预测研究[J].计算机技术与发展,2021,31(02):49.[doi:10. 3969 / j. issn. 1673-629X. 2021. 02. 009]
　HU Yong-pei,ZHANG Chen.Research on Prediction Model of Customer Churn Based on AP Clustering and Random Forest[J].,2021,31(08):49.[doi:10. 3969 / j. issn. 1673-629X. 2021. 02. 009]
[7]利向晴,夏国恩,张显全,等.基于深度神经网络权重集成的客户流失预测[J].计算机技术与发展,2021,31(10):18.[doi:10. 3969 / j. issn. 1673-629X. 2021. 10. 004]
　LI Xiang-qing,XIA Guo-en,ZHANG Xian-quan,et al.Customer Churn Prediction Based on Deep Neural Network Weight Ensemble[J].,2021,31(08):18.[doi:10. 3969 / j. issn. 1673-629X. 2021. 10. 004]

更新日期/Last Update: 2018-09-10