Please wait a minute...
Advanced Search
数据分析与知识发现  2017, Vol. 1 Issue (12): 21-31     https://doi.org/10.11925/infotech.2096-3467.2017.0588
  研究论文 本期目录 | 过刊浏览 | 高级检索 |
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
胡晓雪()
西安财经学院管理学院 西安 710100
Customer Segmentation with Adaptive Evolutionary Clustering
Hu Xiaoxue()
School of Management, Xi’an University of Finance and Economics, Xi’an 710100, China
全文: PDF (1911 KB)   HTML ( 3
输出: BibTeX | EndNote (RIS)      
摘要 

目的】针对多时段动态客户细分问题, 提出一种面向契约型客户的类结构变动自适应进化聚类框架。【方法】通过构建一个动态更新相似矩阵和聚类参数的聚类环, 实现对客户细分结果的跟踪。在每个聚类时段, 首先, 以前一相邻时段的聚类结果为基础, 依据客户契约的失效信息制定类消亡的判定准则; 其次, 计算原客户在该时段的估计相似矩阵, 根据新客户数据判断类结构的变动情况并制定创建新类的准则; 最后, 在更新的相似矩阵和聚类参数上运行静态聚类算法得到该时段的聚类结果。【结果】采用某电力企业客户数据进行实验, 结果表明, 该框架在保证聚类质量的基础上通过取消聚类数目判定和聚类结果匹配两个环节, 能显著提高聚类效率。【局限】由于数据的可获得性, 尚未在其他领域或高维数据集上对算法效率进行验证。【结论】考虑类结构变动的自适应进化聚类框架不仅能有效追踪客户群的进化轨迹, 而且可以避免传统方法对聚类数目的重复判定和聚类结果的匹配问题, 适用于契约型客户的多时段动态细分。

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
胡晓雪
关键词 进化聚类动态聚类粗糙聚类客户细分    
Abstract

[Objective] This paper proposes an adaptive evolutionary clustering framework for contracted customer segmentation with changing cluster structure, aiming to solve the multi-period dynamic customer segmentation problem. [Methods] The proposed framework could track customer segmentation results within a clustering cycle, which updated the proximity matrix and clustering parameters dynamically. For each clustering period, we eliminated expired clusters from the latest adjacent period based on the contract termination date. Then, we calculated the estimated proximity matrix for current customers. We also changed the exiting clusters’ structure according to data of new customers and developed guidelines to add new clusters. Finally, we examined the proposed algorithm with the updated proximity matrix and parameters to obtain the final clustering results of a specific period. [Results] The proposed framework could significantly improve the efficiency of clustering by excluding the process of selecting and matching clusters. [Limitations] The proposed algorithm was not examined with other datasets. [Conclusions] The proposed framework could effectively track evolutionary trajectories of customer groups and eliminate problems facing traditional methods. It could do multi-period dynamic segmentation for contracted customers.

Key wordsEvolutionary Clustering    Dynamic Clustering    Rough Clustering    Customer Segmentation
收稿日期: 2017-06-16      出版日期: 2017-12-29
ZTFLH:  C93  
引用本文:   
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.
Hu Xiaoxue. Customer Segmentation with Adaptive Evolutionary Clustering. Data Analysis and Knowledge Discovery, 2017, 1(12): 21-31.
链接本文:  
https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2017.0588      或      https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/Y2017/V1/I12/21
  自适应进化聚类过程[19]
  考虑类结构变动的自适应进化聚类框架
  第一时段聚类结果
  第二时段聚类过程和聚类结果
  第三时段聚类过程和聚类结果
时段 类数 类编号 类规模 粗糙度
(%)
αt
下近似 上近似
1 3 类1 7 12 19.67 /
类2 21 24
类3 21 25
2 4 类2 21 27 16.67 0.66
类3 21 25
类4 19 23
类5 14 15
3 4 类2 26 31 12.28 0.41
类3 32 35
类4 28 33
类5 14 15
  电力客户各时段细分结果
  三种方法在5个时段的聚类精度
  本文方法和传统AFFECT不同时段的聚类效率
[1] Liautaud B, Hammond M.商务智能[M]. 北京: 电子工业出版社, 2002: 186-205.
[1] (Liautaud B, Hammond M.Business Intelligence[M]. Beijing: Electronic Industry Press, 2002: 186-205.)
[2] Hiziroglu A.Soft Computing Applications in Customer Segmentation: State-of-art Review and Critique[J]. Expert Systems with Applications, 2013, 40: 6491-6507.
doi: 10.1016/j.eswa.2013.05.052
[3] Peters G, Weber R.Dynamic Clustering with Soft Computing[J]. WIREs: Data Mining and Knowledge Discovery, 2012, 2(3): 226-236.
doi: 10.1002/widm.1050
[4] Crespo F, Weber R.A Methodology for Dynamic Data Mining Based on Fuzzy Clustering[J]. Fuzzy Sets and Systems, 2005, 150(2): 267-284.
doi: 10.1016/j.fss.2004.03.028
[5] 郭崇慧, 赵作为. 基于客户行为的4S店客户细分及其变化挖掘[J]. 管理工程学报, 2015, 29(4): 18-26.
doi: 10.13587/j.cnki.jieem.2015.04.003
[5] (Guo Chonghui, Zhao Zuowei.Customer Segmentation and Change Mining Based on Customer Behavior for 4S Shop[J]. Journal of Industrial Engineering Management, 2015, 29(4): 18-26.)
doi: 10.13587/j.cnki.jieem.2015.04.003
[6] Akhondzadeh-Noughabi E, Albadvi A.Mining the Dominant Patterns of Customer Shifts Between Segments by Using Top-k and Distinguishing Sequential Rules[J]. Management Decision, 2015, 53(9): 1976-2003.
doi: 10.1108/MD-09-2014-0551
[7] Mark T, Lemon K N, Vandenbosch M, et al.Caputuring the Evolution of Customer-Firm Relationships: How Customers Become More (or Less) Valuable Over Time[J]. Journal of Retailing, 2013, 89(3): 231-245.
doi: 10.1016/j.jretai.2013.04.001
[8] Benitez I, Quijano A, Diez J L, et al.Dynamic Clustering Segmentation Applied to Load Profiles of Energy Consumption from Spanish Customers[J]. International Journal of Electrical Power & Energy Systems, 2013, 55(2): 437-448.
doi: 10.1016/j.ijepes.2013.09.022
[9] 叶强, 卢涛, 闫相斌, 等. 客户关系管理中的动态客户细分方法研究[J]. 管理科学学报, 2006, 9(2): 44-52.
doi: 10.3321/j.issn:1007-9807.2006.02.006
[9] (Ye Qiang, Lu Tao, Yan Xiangbin, et al.Research on Dynamic Customer Segmentation in Customer Relationship Management[J]. Journal of Management Sciences in China, 2006, 9(2): 44-52.)
doi: 10.3321/j.issn:1007-9807.2006.02.006
[10] Peters G, Weber R, Nowatzke R.Dynamic Rough Clustering and Its Applications[J]. Applied Soft Computing, 2012, 12(10): 3193-3207.
doi: 10.1016/j.asoc.2012.05.015
[11] Perez-Suarez A, Martínez-Trinidad J F, Carrasco-Ochoa J A, et al. A Dynamic Clustering Algorithm for Building Overlapping Clusters[J]. Intelligent Data Analysis, 2012, 16: 211-232.
doi: 10.3233/IDA-2012-0520
[12] Perez-Suarez A, Martínez-Trinidad J F, Carrasco-Ochoa J A, et al. An Algorithm Based on Density and Compactness for Dynamic Overlapping Clustering[J]. Pattern Recognition, 2013, 46: 3040-3055.
doi: 10.1016/j.patcog.2013.03.022
[13] Chi Y, Song X, Zhou D, et al.Evolutionary Spectral Clustering by Incorporating Temporal Smoothness[C]// Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM Press, 2007: 153-162.
[14] Langone R, Suykens J A K. Community Detection Using Kernel Spectral Clustering with Memory[J]. Journal of Physics: Conference Series, 2012, 410: 1-4.
doi: 10.1088/1742-6596/410/1/012100
[15] Wang Y, Liu S, Feng J, et al.Milling Naturally Smooth Evolution of Clusters from Dynamic Data[C]// Proceedings of the 7th SIAM International Conference on Data Mining. 2007: 125-134.
[16] Xu T, Zhang Z, Yu P S, et al.Generative Models for Evolutionary Clustering[J]. ACM Transactions on Knowledge Discovery from Data, 2012, 6(2): 1-27.
doi: 10.1145/2297456.2297459
[17] Li R, Zhang W, Zhao Y, et al.Sparsity Learning Formulations for Mining Time-varying Data[J]. IEEE Transactions on Knowledge and Data Engineering, 2015, 27(5): 1411-1423.
doi: 10.1109/TKDE.2014.2373411
[18] Rosswog J, Ghose K.Detecting and Tracking Spatio-temporal Clusters with Adaptive History Filtering[C]// Proceedings of the 2008 IEEE International Conference on Data Mining Workshops, Pisa, Italy. 2008: 448-457.
[19] Xu K S, Kliger M, Hero III A O. Adaptive Evolutionary Clustering[J]. Data Mining and Knowledge Discovery, 2014, 28(2): 304-336.
doi: 10.1007/s10618-012-0302-x
[20] Peters G.Some Refinements of Rough k-means Clustering[J]. Pattern Recognition, 2006, 39(8): 1481-1491.
doi: 10.1016/j.patcog.2006.02.002
[21] 肖丽妍, 齐佳音, 屈启兴. 基于客户行为的交易关系与客户风险研究[J]. 北京邮电大学学报: 社会科学版, 2013, 15(2): 86-94.
[21] (Xiao Liyan, Qi Jiayin, Qu Qixing.Study of Transactional Relationship and Customer Risk Based on Customer Behavior[J]. Journal of Beijing University of Posts and Telecommunications: Social Sciences Edition, 2013, 15(2): 86-94.)
[22] Žalik K R, Žalik B.Validity Index for Clusters of Different Sizes and Densities[J]. Pattern Recognition Letters, 2011, 32(2): 221-234.
doi: 10.1016/j.patrec.2010.08.007
[23] 潘俊, 王瑞琴. 基于选择性聚类集成的客户细分[J]. 计算机集成制造系统, 2015, 21(6): 1662-1668.
doi: 10.13196/j.cims.2015.06.030
[23] (Pan Jun, Wang Ruiqin.Customer Segmentation Based on Selective Clustering Ensemble[J]. Computer Integrated Manufacturing Systems, 2015, 21(6): 1662-1668.)
doi: 10.13196/j.cims.2015.06.030
[1] 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.
[2] 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.
[3] 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