基于改进SOM神经网络的异网电信用户细分研究

doi:10.16088/j.issn.1001-6600.2018.03.003

广西师范大学学报（自然科学版） ›› 2018, Vol. 36 ›› Issue (3): 17-24.doi: 10.16088/j.issn.1001-6600.2018.03.003

基于改进SOM神经网络的异网电信用户细分研究

刘铭^*, 张双全, 何禹德

长春工业大学基础科学学院,吉林长春130012

收稿日期:2017-05-25 出版日期:2018-07-17 发布日期:2018-07-17
通讯作者: 刘铭(1979—),男,吉林白山人,长春工业大学副教授,博士。 E-mail:jlcclm@163.com
基金资助:
国家自然科学基金(61503150); 吉林省教育厅十二五科学规划项目([2015]111)

Classification Study of Differential Telecom Users Based on SOM Neural Network

LIU Ming^*, ZHANG Shuangquan, HE Yude

Basic Science College, Changchun University of Technology, Changchun Jilin 130012, China

Received:2017-05-25 Online:2018-07-17 Published:2018-07-17

摘要/Abstract

摘要： 在对用户价值认知的基础上,电信运营商对用户进行正确分类是其了解用户的重要手段。电信运营商可以将用户分为不同的类别,并以此制定差别化服务政策,从而进行差异化营销来提高企业效益。本文首先对异网电信用户进行了细分研究,为提高分类的准确率,在传统自组织映射神经网络基础上,对学习速度和权重向量初始值的确定进行了改进,提出了改进的自组织映射神经网络;同时采用改进的自组织映射神经网络对某省电信运营商提供的用户数据进行仿真。仿真结果表明:改进的自组织映射神经网络在兼顾稳定性的同时,很好地解决了自组织过慢问题,提高了用户分类的准确率,大幅度减小误差。最后根据分类结果为电信运营商实施差异化营销提供了基本规则。

关键词: 改进型自组织映射, 异网电信用户, 细分研究

Abstract: Based on the value cognition of consumers, it is a critical approach for telecom operators to classify consumers correctly in order to know them better. Telecom operators can divide the consumers into different categories and develop different service policies as well, so that they can advance the differentiated marketing to improve business benefits. Firstly, consumers of different telecom networks are classified in detail. In order to improve the classification accuracy, this research improves the determination of learning rate and the initial value's weight vectors based on the traditional self-organizing map neural network, proposing an improved self-organizing map neural network (ISOMNN). Then this ISOMNN is applied to the simulation experiment by using the consumer data provided by a telecom operator of a province. The simulation results reveal that ISOMNN can not only take the stability into account, but also solve the slow self-organizing problem well, boosting the accuracy of consumer-classification and reducing errors significantly. Finally, based on the results of classification, this paper provides the basic principles for the telecom operators, which will help them to implement differential marketing.

Key words: improved self-organizing map, different telecom network consumers, subdivision research

中图分类号:

TP183

刘铭, 张双全, 何禹德. 基于改进SOM神经网络的异网电信用户细分研究[J]. 广西师范大学学报（自然科学版）, 2018, 36(3): 17-24.

LIU Ming, ZHANG Shuangquan, HE Yude. Classification Study of Differential Telecom Users Based on SOM Neural Network[J]. Journal of Guangxi Normal University(Natural Science Edition), 2018, 36(3): 17-24.

参考文献

[1] KHODAKARAMI F, CHAN Y E.Exploring the role of customer relationship management (CRM) systems in customer knowledge creation[J]. Information and Management, 2014, 51(1):27-42.DOI: 10.1016/j.im.2013.09.001.
[2] CHEN Y, ZHANG G, HU D, et al.Customer segmentation based on survival character[J]. Journal of Intelligent Manufacturing, 2007, 18(4): 513-517. DOI:10.1007/s10845-007-0059-z.
[3] 王晓国, 黄韶坤, 朱炜, 等. 应用C4.5算法构造客户分类决策树的方法[J]. 计算机工程, 2003, 29(14):89-91. DOI: 10.3969/j.issn.1000-3428.2003.14.036.
[4] 闫相斌, 李一军, 叶强. 基于购买行为的客户分类方法研究[J]. 计算机集成制造系统, 2005, 11(12):1769-1774.DIO: 10.3969/j.issn.1006-5911.2005.12.023.
[5] LIOU J J H, TZENG G H. A dominance-based rough set approach to customer behavior in the airline market[J].Information Sciences, 2010, 180(11): 2230-2238. DOI:10.1016/j.ins.2010.01.025.
[6] CHICCO G, NAPOLI R, PIGLIONE F.Comparisons among clustering techniques for electricity customer classification[J].IEEE Transactions on Power Systems, 2006, 21(2): 933-940. DOI: 10.1109/TPWRS.2006.873122.
[7] 关云鸿. 改进K-均值聚类算法在电信客户分类中的应用[J]. 计算机仿真, 2011, 28(8):138-140,152. DOI:10.3969/j.issn.1006-9348.2011.08.033.
[8] 李文英. 基于数据挖掘的电信客户细分研究[D]. 西安:西安理工大学, 2009.
[9] 侯越. DE优化T-S模糊神经网络的交通流量预测[J]. 计算机工程与设计, 2013, 34(9):3284-3287. DIO: 10.3969/j.issn.1000-7024.2013.09.056.
[10] BOONE D S, ROEHM M.Retail segmentation using artificial neural networks[J]. International Journal of Research in Marketing, 2002, 19(3): 287-301. DOI: 10.1016/S0167-8116(02)00080-0.
[11] WANG J S, LI S X, GAO J.SOM neural network fault diagnosis methods of polymerization kettle equipment optimezed by improved pso algorithm[J]. The Scientific World Journal, 2014:937680. DOI:10.1155/2014/937680.
[12] KOHONEN T.Essentials of the self-organizing map[J]. Neural Networks, 2013, 37:52-65.DOI: 10.1016/j.neunet.2012.09.018.
[13] SONG M, ZHAO X, HAIH E, et al.Statistics-based CRM approach via time series segmenting RFM on large scale data[J]. Knowledge-Based Systems, 2017:282-291.DOI: 10.1016/j.knosys.2017.05.027.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于改进SOM神经网络的异网电信用户细分研究

Classification Study of Differential Telecom Users Based on SOM Neural Network

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 7

Metrics

本文评价

推荐阅读 0

[1]	罗兰, 周楠, 司杰. 不确定细胞神经网络鲁棒稳定新的时滞划分法[J]. 广西师范大学学报（自然科学版）, 2019, 37(4): 45-52.
[2]	范瑞,蒋品群,曾上游,夏海英,廖志贤,李鹏. 多尺度并行融合的轻量级卷积神经网络设计[J]. 广西师范大学学报（自然科学版）, 2019, 37(3): 50-59.
[3]	周戎龙,罗玉玲,闭金杰,岑明灿,丘森辉,廖志贤. 图像并行加密算法在手持设备上的应用研究[J]. 广西师范大学学报（自然科学版）, 2019, 37(3): 60-70.
[4]	张金磊, 罗玉玲, 付强. 基于门控循环单元神经网络的金融时间序列预测[J]. 广西师范大学学报（自然科学版）, 2019, 37(2): 82-89.
[5]	万雷,罗玉玲,黄星月. 脉冲神经网络硬件系统性能监测平台[J]. 广西师范大学学报（自然科学版）, 2018, 36(1): 9-16.
[6]	林晓宇, 钟一文, 王爱荣. 趋药性人工蜂群算法训练神经网络研究[J]. 广西师范大学学报（自然科学版）, 2011, 29(3): 120-124.
[7]	朱经纬, 芮挺, 李决龙, 方虎生, 张金林. 基于蚁群神经网络的机械手自组织逆运动规划[J]. 广西师范大学学报（自然科学版）, 2011, 29(2): 125-129.