PDF(809 KB)
E-commerce customer churn prediction model combined with individual activity
JU Chun-hua, LU Qi-bei, GUO Fei-peng
Systems Engineering - Theory & Practice ›› 2013, Vol. 33 ›› Issue (1) : 141-150.
PDF(809 KB)
PDF(809 KB)
E-commerce customer churn prediction model combined with individual activity
In order to improve the accuracy of customer churn prediction at individual level, an E-commerce customer churn prediction model combined with individual activity called H-ULSSVM was established. Firstly, it used heuristic algorithm which integrated into geographic factors to calculate the optimal threshold and obtain the degree of individual activity, identify the correctly identified customers and incorrectly identified customers. On this basis, considering a large number of impact factors exist in E-commerce customer churn prediction, a rough equivalence class reduction method was proposed to extract important index. The correctly identified customers were sent to learn and train in unbalanced least squares support vector machine, and then used the classifier to judge the status of the incorrectly identified customers. The empirical study on B2C E-commerce platform shows that this model has better efficiency and accuracy than others.
customer churn prediction / heuristic algorithm / unbalanced least squares support vector machine / rough set {{custom_keyword}} /
[1] 张新安, 田澎. 顾客满意与顾客忠诚之间关系的实证研究[J]. 管理科学学报, 2007, 10(4): 62-71.Zhang X A, Tian P. Does consumer satisfaction really matter? An examination of its impact on consumer loyalty[J]. Journal of Management Sciences in China, 2007, 10(4): 62-71.
[2] Reinartz W J, Kumar V. On the profitability of long-life customers in a noncontractual setting: An empirical investigation and implications for marketing[J]. Journal of Marketing, 2000, 64(4): 17-35.
[3] Hopmann J, Thede A. Applicability of customer churn forecasts in a non-contractual setting[J]. Mathematics and Statistics, 2005, V: 330-337.
[4] 马少辉.客户资产分析与管理研究[D]. 天津:天津大学, 2007.Ma S H. A study on customer equity analysis and management[D]. Tianjin: Tianjin Universtiy, 2007.
[5] Fader P S, Hardie B G S. Probability models for customer-base analysis[J]. Journal of Interactive Marketing, 2009, 23: 61-69.
[6] 罗彬, 邵培基, 罗尽尧,等.基于多分类器动态集成的电信客户流失预测[J]. 系统工程学报, 2010, 25(5): 703-711.Luo B, Shao P J, Luo J Y, et al. Telecommunication customer churn prediction based on the dynamic integration of multiple classifiers[J]. Journal of Systems Engineering, 2010, 25(5): 703-711.
[7] Tamaddoni Jahromia A, Sepehria M M, Teimourpoura B, et al. Modeling customer churn in a non-contractual setting: The case of telecommunications service providers[J]. Journal of Strategic Marketing, 2010, 7(18): 587-598.
[8] Verbeke W, Martens D, Mues C, et al. Building comprehensible customer churn prediction models with advanced rule induction techniques[J]. Expert Systems with Applications, 2011, 38: 2354-2364.
[9] 盛昭瀚, 柳炳祥. 客户流失危机分析的决策树方法[J]. 管理科学学报, 2005, 8(2): 20-25.Sheng Z H, Liu B X. Research method of custom forfeit crisis based on decision tree[J]. Journal of Management Sciences in China, 2005, 8(2): 20-25.
[10] 琚春华,郭飞鹏. 基于支持向量机的分布数据挖掘模型DSVM[J]. 系统工程理论与实践, 2010, 30(10): 1855-1863.Ju C H, Guo F P. Distributed data mining model based on support vector machines[J]. Systems Engineering——Theory & Practice, 2010, 30(10): 1855-1863.
[11] 刘学伟.基于Pareto/NBD+朴素贝叶斯组合模型的电子商务客户流失预测研究[D].成都:四川大学, 2006.Liu X W. Research for eBusiness customer churns based on assembled model of Pareto/NB and Naíve Bayes[D]. Chengdu: Sichuan University, 2006.
[12] 朱帮助. 基于SMC-RS-LSSVM的电子商务客户流失预测模型[J]. 系统工程理论与实践, 2011, 30(11): 1960-1967.Zhu B Z. E-Business customer churn prediction based on integration of SMC, rough sets and least square support vector machine[J]. Systems Engineering——Theory & Practice, 2011, 30(11): 1960-1967.
[13] Fader P S, Hardie B G S, Lee K L. "Counting Your Customers" the easy way: An alternative to the Pareto/NBD model[J]. Marketing Science, 2005, 24(2): 275-284.
[14] 张楠, 苗夺谦, 岳晓冬. 区间值信息系统的知识约简[J]. 计算机研究与发展, 2010, 47(8): 1362-1371.Zhang N, Miao D Q, Yue X D. Approaches to knowledge reduction in interval-valued information systems[J]. Journal of Computer Research and Development, 2010, 47(8): 1362-1371.
[15] 张家录, 赵晓东. 基于模糊包含的粗糙集模型与模糊信任测度[J]. 模式识别与人工智能, 2010, 23(4): 531-538.Zhang J L, Zhao X D. Rough set models based on fuzzy inclusion and fuzzy belief measures[J]. Pattern Recognition and Artificial Intelligence, 2010, 23(4): 531-538.
[16] 马建敏, 张文修, 朱朝晖. 基于信息量的序信息系统的属性约简[J]. 系统工程理论与实践, 2010, 30(9): 1679-1683.Ma J M, Zhang W X, Zhu C H. Information quantity-based attribute reduction in ordered information systems[J]. Systems Engineering——Theory & Practice, 2010, 30(9): 1679-1683.
[17] 薛贞霞, 刘三阳, 刘万里.不平衡最小二乘支持向量机[J]. 系统仿真学报, 2009, 21(14): 4324-4327.Xue Z X, Liu S Y, Liu W L. Unbalanced least squares support vector machines[J]. Journal of System Simulation, 2009, 21(14): 4324-4327.
[18] Yu X B, Guo S S, Guo J, et al. An extended support vector machine forecasting framework for customer churn in e-commerce[J]. Expert Systems with Applications, 2011, 38: 1425-1430.
[19] Wubben M, Wangenheim F V. Instant customer base analysis: Managerial heuristics often "get it right"[J]. Journal of Marketing, 2008, 72: 82-93.
PDF(809 KB)
/
| 〈 |
|
〉 |
