基于购买行为的客户分类方法研究

摘要/Abstract

摘要： 在序列对齐方法的基础上，提出了客户购买行为的相似比较标准。在比较过程中，考虑了客户购买产品的类别和相应产品的购买金额，给出了快速计算客户购买行为相似度的算法。在此基础上，对客户聚类应用模拟退火遗传算法改善聚类的质量，使每一类客户具有更相似的购买行为。实例分析结果表明，所提出的方法能够有效地根据购买行为对客户加以分类。

关键词: 客户分类, 序列对齐方法, 聚类, 遗传算法, 模拟退火

Abstract: A similarity measurement of customers purchase behaviors was proposed based on the sequence alignment method. Purchased product varieties and their corresponding monetary values were taken into consideration in the comparison processes between different customers. A quick algorithm for the computation of similarity between purchase behaviors of customers was proposed. Based on this algorithm, a genetic algorithm with simulated annealing approach was adopted to improve cluster segmentation quality so that customers in the same cluster would have the closest purchase pattern. Analysis results of examples indicated that the proposed method was effective for customer segmentation based on purchase behaviors.

Key words: customer segmentation, sequence alignment method, clustering, genetic algorithm, simulated annealing

中图分类号:

TP391

闫相斌，李一军，叶强. 基于购买行为的客户分类方法研究[J]. .

AN Xiang-bin, LI Yi-jun, YE Qiang. Research on customer segmentation based on purchase behaviors[J]. .

参考文献

［1］ KOTLER P.Kotler on marketing:how to create,win,and dominate markets［M］.Columbus,OH,USA:Free Press,1999.1-30.

[2] PAINTER D. Customer intelligence: getting past the “failure” of CRM［Z］. St.Albans,U.K.: White papers of Clarity Blue Limited, 2003.1-5.

[3] HAMMOND K, EHRENBERG A S C, GOODHARDT G J. Market segmentation for competitive brands［J］. European Journal of Marketing, 1996, 30(12):39-49.

[4] NATTER M. Conditional market segmentation by neural networks: a monte-carlo study［J］. Journal of Retailing and Consumer Services, 1999, 6(4):237-248.

[5] CHOU P B, GROSSMAN E, GUNOPULOS D, et al. Identifying prospective customers［A］.Proceedings of The Sixth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining［C］. Boston, MA,USA: ACM Press, 2000. 447-456.

[6] KRUSKAL J. An overview of sequence comparison［A］. Time Warps, String Edits and Macromolecules: The Theory and Practice of Sequence Comparison［C］. London,U.K.: Addison-Wesley, Reading, Mass, 1983.1-44.

[7] JOH C H, ARENTZE T A, TIMMERMAN H J P. A position-sensitive sequence-alignment method illustrated for space-time activity-diary data［J］. Environment and Planning, 2001, 33(2): 313-338.

[8] BRADLEY P S, FAYYAD U M. Refining initial points for K-means clustering［A］. Proceedings of The 15th International Conference on Machine Learning［C］.Madison,USA:Moran Kaufman,1998. 91-99.

[9] TSAI C Y, CHIU C C. A purchase-based market segmentation methodology［J］.Expert Systems with Applications, 2004, 27: 265-276.

[10] HOLLAND J. Adaptation in natural and artificial system［M］. Ann Arbor: The University of Michigan Press, 1975. 1-20.

[11] MURTHY C A, CHOWDHURY N. In search of optimal clusters using genetic algorithms［J］. Pattern Recognition. Letters,1996,17:825-832.

[12] KIRPATRICK S, GELATT C D, VECCHI M P. Optimization by simulated annealing［J］. Science, 1983, 220: 671-680.

[1]	高子建,张晗睿,窦万春,徐江民,孟顺梅. 基于谱聚类和隐语义模型的智能协同推荐方法[J]. 计算机集成制造系统, 2021, 27(9): 2517-2524.
[2]	陈年,金涛,王建民. 基于变异反馈的临床路径优化[J]. 计算机集成制造系统, 2021, 27(9): 2556-2564.
[3]	尚正阳,顾寄南,王建平. 求解带能力约束车辆路径优化问题的改进模拟退火算法[J]. 计算机集成制造系统, 2021, 27(8): 2260-2269.
[4]	黎英杰,刘建军,陈庆新,毛宁. 多层级装配作业车间等量分批策略与调度算法[J]. 计算机集成制造系统, 2021, 27(8): 2307-2320.
[5]	王奕祺,张晓冬. 基于仿真评价方法的适应性合作换线策略[J]. 计算机集成制造系统, 2021, 27(7): 1918-1928.
[6]	樊盼盼,袁逸萍,孙文磊,樊小朝,赵琴,马占伟. 融合多时段SCADA数据的风电机组风险态势预测[J]. 计算机集成制造系统, 2021, 27(7): 1993-2004.
[7]	王文中,张树生,余隋怀,陈登凯. 基于解构·重构思维的潜水器舱室布局优化[J]. 计算机集成制造系统, 2021, 27(7): 2045-2052.
[8]	尚正阳,顾寄南,潘家保. 考虑LIFO约束的2L-CVRP优化[J]. 计算机集成制造系统, 2021, 27(7): 2134-2143.
[9]	王勇,周雪,刘永,许茂增. 基于车辆共享的多中心共同配送联盟优化[J]. 计算机集成制造系统, 2021, 27(6): 1820-1832.
[10]	董舒豪,徐志刚,常艳茹,秦开仲,朱建峰,苏开远. 考虑物料装卸点与搬运通道的多行设施布局[J]. 计算机集成制造系统, 2021, 27(5): 1269-1280.
[11]	张昊鹏,郭宇,汤鹏洲,黄少华,刘道元,李晗. 基于图像匹配的增强现实装配系统跟踪注册方法[J]. 计算机集成制造系统, 2021, 27(5): 1281-1291.
[12]	胡金昌,刘紫薇,马文凯,吴耀华. 考虑学习效应的单人作业车间多目标调度算法[J]. 计算机集成制造系统, 2021, 27(5): 1361-1370.
[13]	孙殿柱,沈江华,汪思腾,李延瑞,林伟. 复杂型面点云的法向特征聚类分级估计方法[J]. 计算机集成制造系统, 2021, 27(5): 1440-1446.
[14]	李珍萍,田宇璇,卜晓奇,吴凌云. 无人仓系统订单分批问题及K-max聚类算法[J]. 计算机集成制造系统, 2021, 27(5): 1506-1517.
[15]	李海龙,陈发源,计效园,李建斌,周建新. 基于改进SPEA2算法的铸造并行车间主生产计划[J]. 计算机集成制造系统, 2021, 27(4): 1072-1080.