基于神经网络的电信客户流失预测主题建模及实现被引量：18

Telecom churn prediction modeling and application based on neural network

下载PDF

导出

摘要客户流失管理是电信运营商通过对客户需求满意度调查进行有针对性挽留客户的一个重要方法,其中最关键的就是对客户流失行为做出预测。提出了一种基于神经网络的客户流失预测模型。根据行业专家经验值选取分析变量,通过神经网络计算分析变量的权值,建立客户流失预测模型并对客户流失趋势进行预测。该方法与决策树和贝叶斯网络等算法相比,通过使用两次神经网络,从原始数据上千个属性中提炼出与客户流失度相关性较大的属性,分析出的影响流失属性更利于下一步的客户挽留工作。 Churn management is a major focus of mobile operators to retain subscribers via satisfying their needs under resource constraints. One of the most important tasks is churn prediction. A customer churn prediction model based on neural network was put forward. Choose analysis variable according to expert empirical evaluation, and calculate the weight of analysis variable using neural network, set up customer churn prediction model and predict customer churn. Compared to decision tree and Bayesian network, the attributes closely related to churn degree were abstracted by using two neural networks. The attributes obtained are more favorable for customer detainment.

作者田玲邱会中郑莉华

机构地区电子科技大学计算机科学与工程学院

出处《计算机应用》 CSCD 北大核心 2007年第9期2294-2297,共4页 journal of Computer Applications

基金四川省科技厅科技攻关项目(2006Z01-011)

关键词 BP神经网络关键绩效指标客户流失商业智能 Back Propagation Neural Network （BPNN） Key Performance Indicator （KPI） churn management business intelligent

分类号 TP183 [自动化与计算机技术—控制理论与控制工程]

引文网络
相关文献

参考文献7

1HUNG S Y,YEN D C,WANG H Y.Applying data mining to telecom churn management[J].Expert Systems with Applications,2006,31(3):515-524.
2MATTERSION R.Telecom churn management[D].Fuquay-Varina:APDG Publishing,2001.
3WEI C P,CHIU I T.Tuning telecommunications call detail to churn prediction:A data mining approach[J].Expert Systems with Applications,2002,23:103-112.
4LEJEUNE M.Measuring the impact of data mining on churn management[J].Internet Research:Electronic Network Applications and Policy,2001,11(5):375-387.
5郭明,郑惠莉,卢毓伟.基于贝叶斯网络的客户流失分析[J].南京邮电学院学报（自然科学版）,2005,25(5):79-83. 被引量：14
6叶进,张向利,张润莲.基于数据挖掘的移动客户流失分析系统[J].计算机系统应用,2005,14(2):61-64. 被引量：3
7叶进,林士敏.基于贝叶斯网络的推理在移动客户流失分析中的应用[J].计算机应用,2005,25(3):673-675. 被引量：12

二级参考文献15

1CHICKERING D, HECKERMAN D. Efficient Approximations for the Marginal Likelihood of Bayesian Networks with Hidden Variables [ A]. Proceeding of the 12th conference on Uncertainty in Artificial Intelligence[C]. 1996. 158 ～ 168.
2HECKERMAN D. Bayesian networks for data mining[J]. Data Mining and Knowledge Discovery, 1997,1 ( 1 ) :79 ～ 119.
3COOPER G, HERSKOVITS E. A Bayesian method for the induction of probabilistic networks from data[J]. Machine Learning , 1992,9(4) :309 ～347.
4CHICKERING D, HECKERMAN D, GEIGER D. Learning Bayesian networks: search methods and experimental results [ A ]. proceedings of fifth conference on artificial intelligence and statistics[C]. 1995.
5MADIGAN D, YORK J. Bayesian graphical models for discrete data[J]. International Statistical Review, 1995,63(2): 307 ～347.
6GIUDICI P, CASTELO R. Improving markov chain monte carlo model search for data mining [ J ]. Machine Learning, 2003,50 ( 1-2) :215 ～232.
7IBM. Mining your own business in telecoms using DB2 Intelligent Miner for Data[ EB/OL ]. http :∥www. redbooks. ibm. com
8HECKERMAN D, GEIGER D, CHICKERING D. Learning Bayesian networks: The combination of knowledgeand statistical data[ J ]. Machine Learning, 1995.20 ( 3 ) :241 ～ 243.
9FRIEDMAN N, GEIGER D, GOLDSZMIDT M. Bayesian Network Classifiers [ J ]. Machine Learning, 1997,29 ( 2 - 3 ) : 131 - 163.
10FAYYAD U, PIATET G S, SMYTH P. Knowledge Discovery and Data Mining: Towards a Unifying Framework [ A ]. Proceedings of the Second International Conference on Knowledge Discovery and Data Mining[ C]. 1996.82 ～ 88.