Please wait a minute...
Advanced Search
数据分析与知识发现  2020, Vol. 4 Issue (4): 83-90    DOI: 10.11925/infotech.2096-3467.2019.0715
  研究论文 本期目录 | 过刊浏览 | 高级检索 |
基于改进SOM神经网络模型与RFM模型的非寿险客户细分研究*
闫春1,2,刘璐1()
1 山东科技大学经济管理学院 青岛 266590
2 山东科技大学数学与系统科学学院 青岛 266590
Classifying Non-life Insurance Customers Based on Improved SOM and RFM Models
Yan Chun1,2,Liu Lu1()
1 College of Economics and Management, Shandong University of Science and Technology, Qingdao 266590, China
2 College of Mathematics and System, Shandong University of Science and Technology, Qingdao 266590, China
全文: PDF(1115 KB)   HTML ( 3
输出: BibTeX | EndNote (RIS)      
摘要 

【目的】 结合神经网络,解决非寿险客户细分问题,达到精准营销等目的。【方法】 同时从宏观与微观角度改进RFM模型并引入客户理赔金额指标,建立RFMC模型。动态设置SOM神经网络模型的训练速度与权重向量,提高模型收敛速度并实现客户细分。【结果】 采用某保险公司非寿险客户信息进行实验,结果表明改进的SOM神经网络模型在保证模型稳定性的同时,模型自组织速度提高21.6%。【局限】 仅采用一家保险公司的非寿险客户数据进行细分。【结论】 本文方法将非寿险客户分为7类,并对不同类别客户提出营销策略,能有效提高营销决策质量。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
闫春
刘璐
关键词 RFM模型SOM神经网络客户细分营销策略    
Abstract

[Objective] This paper uses neural network algorithms to classify non-life insurance customers, aiming to realize precision marketing. [Methods] We modified the RFM model from the macro and micro perspectives, and then introduced the index of claim amounts to establish the RFMC model. Then, we dynamically set the training speed and weight vector of the SOM neural network model. Finally, we improved the convergence speed of the proposed model and finished customer classification. [Results] We examined our model with information on non-life insurance customers. The proposed model was stable and its self-organization speed increased by 21.6%. [Limitations] All of the non-life insurance customers were from the same insurance company. [Conclusions] This paper divides non-life insurance customers into seven categories, and proposes different strategies for each type, which effectively improve the marketing decisions.

Key wordsRFM Model    SOM Neural Network    Customer Classification    Marketing Strategy
收稿日期: 2019-06-19     
中图分类号:  F840.32  
基金资助:*本文系国家自然科学基金项目“基于结构化大数据深度挖掘的非寿险保险公司经营风险模型研究”(61502280);全国统计科学研究重点项目“异构社交大数据多源信息融合的保险客户精准画像研究”的研究成果之一(2019LZ10)
通讯作者: 刘璐     E-mail: 617128404@qq.com
引用本文:   
闫春,刘璐. 基于改进SOM神经网络模型与RFM模型的非寿险客户细分研究*[J]. 数据分析与知识发现, 2020, 4(4): 83-90.
Yan Chun,Liu Lu. Classifying Non-life Insurance Customers Based on Improved SOM and RFM Models. Data Analysis and Knowledge Discovery, DOI:10.11925/infotech.2096-3467.2019.0715.
链接本文:  
http://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2019.0715
指标体系 细分类别
消费近度(R) R1:某客户购买非寿险产品近度与全部客户购买非寿险产品平均近度之比
R2:某客户最近一年购买非寿险产品近度与自身历史平均近度之比
消费频度(F) F1:某客户购买非寿险产品次数与全部客户平均购买非寿险产品次数之比
F2:某客户最近一年购买非寿险产品次数与自身购买非寿险产品总次数之比
消费值度(M) M1:某客户购买非寿险产品总额与全部客户平均消费总额之比
M2:某客户最近一年购买非寿险产品总额与自身历史总额之比
理赔金额(C) C1:某客户所获理赔金额与全部客户所获平均理赔金额之比
C2:某客户最近一年所获理赔金额与自身历史所获理赔金额之比
表1  非寿险客户细分指标体系
图1  SOM神经网络的结构
图2  改进的SOM神经网络模型训练流程
指标 ω1 ω2
R 0.537 0.463
F 0.476 0.524
M 0.569 0.431
C 1.000 0.000
表2  RFMC模型细分指标权重
图3  邻近神经元间距情况
图4  每个神经元分类情况
图5  三种模型自适应时间对比
非寿险客户类别 客户簇编号 R F M C
重要保持客户 1,3,6
重要发展客户 5,7,9
一般重要客户 2,4
重要挽留客户 12,14,15
一般客户 8,13
无价值客户 11,16
高风险客户 10
表3  分类标签对应类属与购买行为
[1] Hushes A M . Strategic Database Marketing: The Master Plan for Starting and Managing a Profitable Customer-Based Marketing Program[M]. New York: McGraw-Hill, 2000.
[2] Chang H C, Tsai H P . Group RFM Analysis as a Novel Framework to Discover Better Customer Consumption Behavior[J]. Expert Systems with Applications, 2011,38(12):14499-14513.
[3] Khobzi H, Akhondzadeh-Noughabi E, Minaei-Bidgoli B . A New Application of RFM Clustering for Guild Segmentation to Mine the Pattern of Using Banks’ e-Payment Services[J]. Journal of Global Marketing, 2014,27(3):178-190.
doi: 10.1080/08911762.2013.878428
[4] Dursun A, Caber M . Using Data Mining Techniques for Profiling Profitable Hotel Customers: An Application of RFM Analysis[J]. Tourism Management Perspectives, 2016,18:153-160.
doi: 10.1016/j.tmp.2016.03.001
[5] Yan C, Sun H, Liu W , et al. An Integrated Method Based on Hesitant Fuzzy Theory and RFM Model to Insurance Customers’ Segmentation and Lifetime Value Determination[J]. Journal of Intelligent & Fuzzy Systems, 2018,35(1):159-169.
[6] 杜修平, 王中 . 基于决策树的证券客户流失模型[J]. 计算机应用与软件, 2009,26(9):230-233.
( Du Xiuping, Wang Zhong . The Stock Customers Churn Model Based on Decision Tree[J]. Computer Applications and Software, 2009,26(9):230-233.)
[7] 王文贤, 金阳, 陈道斌 . 基于RFM模型的个人客户忠诚度研究[J]. 金融论坛, 2012(3):75-80.
( Wang Wenxian, Jin Yang, Chen Daobin . A Study of Personal Customer Loyalty Based on RFM Model[J]. Financial Forum, 2012(3):75-80.)
[8] 赵萌, 齐佳音 . 基于购买行为RFM及评论行为RFMP模型的客户终身价值研究[J]. 统计与信息论坛, 2014,29(9):91-98.
( Zhao Meng, Qi Jiayin . The Research of Customer Lifetime Value Based on the Combination of Customer Purchase’s RFM and Customer Online Review’s RFMP[J]. Statistics & Information Forum, 2014,29(9):91-98.)
[9] 熊兰, 高炳 . 基于RFM多层级客户价值模型的客户细分研究[J]. 商业经济研究, 2017(5):55-57.
( Xiong Lan, Gao Bing . Research on Customer Segmentation Based on RFM Multi-Level Customer Value Model[J]. Journal of Commercial Economics, 2017(5):55-57.)
[10] MacQueen J. Some Methods for Classification and Analysis of Multivariate Observations[C]// Proceedings of the 5th Berkeley Symposium on Mathematics Statistics and Probability. 1967: 281-297.
[11] Quinlan J R . Induction of Decision Trees[J]. Machine Learning, 1986,1(1):81-106.
[12] Kohonen T . Self-organized Formation of Topologically Correct Feature Maps[J]. Biological Cybernetics, 1982,43(1):59-69.
doi: 10.1007/BF00337288
[13] 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.
( Wang Xiaoguo, Huang Shaokun, Zhu Wei , et al. Method of Building Decision Trees of Customer Classification by Using C4.5 Algorithm[J]. Computer Engineering, 2003,29(14):89-91.)
[14] 林盛, 肖旭 . 基于RFM的电信客户市场细分方法[J]. 哈尔滨工业大学学报, 2006,38(5):758-760.
( Lin Sheng, Xiao Xu . A Method of Telecom Customer Market Segmentation Based on RFM Model[J]. Journal of Harbin Institute of Technology, 2006,38(5):758-760.)
[15] Kiang M Y . Extending the Kohonen Self-organizing Map Networks for Clustering Analysis[J]. Computational Statistics & Data Analysis, 2001,38(2):161-180.
[16] Lee S C K, Lin X S. Delta Boosting Machine and Its Application in Actuarial Modeling[R/OL]. https://www.soa.org/globalassets/assets/Files/Research/Projects/delta-boosting-report.pdf.
[17] Wuthrich M V . Covariate Selection from Telematics Car Driving Data[J]. European Actuarial Journal, 2017,7(1):89-108.
doi: 10.1007/s13385-017-0149-z
[18] Yanık S, Elmorsy A . SOM Approach for Clustering Customers Using Credit Card Transactions[J]. International Journal of Intelligent Computing and Cybernetics, 2019,12(3):372-388.
doi: 10.1108/IJICC-11-2018-0157
[19] 吴春旭, 鲍满园, 苟清龙 . 自组织映射聚类算法在电信客户细分中的应用[J]. 计算机系统应用, 2010,19(8):168-172.
( Wu Chunxu, Bao Manyuan, Gou Qinglong . Application of Self Organization Map to Classification of the Telecommunication Company[J]. Computer Systems and Applications, 2010,19(8):168-172.)
[20] 杨于峰, 余伟萍, 田盼 . 基于SOM神经网络的品牌丑闻微博传播分类预测研究[J]. 情报杂志, 2013,32(10):23-28.
( Yang Yufeng, Yu Weiping, Tian Pan . Classification and Prediction of Brand Scandal Spread on Microblogging Based on the SOM[J]. Journal of Intelligence, 2013,32(10):23-28.)
[21] 张连增, 王缔 . 保险大数据条件下车险费率厘定的研究——基于SOM神经网络方法的车险索赔强度建模[J]. 保险研究, 2018(9):56-65.
( Zhang Lianzeng, Wang Di . A Research on the Rate Making of Automobile Insurance with Big Data—Modeling of Automobile Insurance Claim Severity Based on SOM Neural Network[J]. Insurance Studies, 2018(9):56-65.)
[22] 陈伯成, 梁冰, 周越博 , 等. 自组织映射神经网络(SOM)在客户分类中的一种应用[J]. 系统工程理论与实践, 2004,24(3):8-14.
( Chen Bocheng, Liang Bing, Zhou Yuebo , et al. An Application of SOM Neural Network in Customer Classification[J]. Systems Engineering—Theory & Practice, 2004,24(3):8-14.)
[23] 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):21-28.
( 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):21-28.)
[1] 朱鹏, 赵笑笑, 伍薇. 移动电子商务消费者决策偏好影响因素实证研究*[J]. 数据分析与知识发现, 2017, 1(3): 1-9.
[2] 胡晓雪. 考虑类结构变动的自适应进化聚类及其在客户细分中的应用[J]. 数据分析与知识发现, 2017, 1(12): 21-31.
[3] 陈东沂,周子程,蒋盛益,王连喜,吴佳林. 面向企业微博的客户细分框架*[J]. 现代图书情报技术, 2016, 32(2): 43-51.
[4] 李英 吴园园 宁福锦. 基于PSO的K-means改进算法在证券客户细分中的应用[J]. 现代图书情报技术, 2010, 26(7/8): 88-94.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 2015 《数据分析与知识发现》编辑部
地址:北京市海淀区中关村北四环西路33号 邮编:100190
电话/传真:(010)82626611-6626,82624938
E-mail:jishu@mail.las.ac.cn