摘要
针对电信客户流失问题的复杂性,融合粗糙集理论、神经网络和蜂群算法的优势,提出了一种新的客户流失预测模型——基于粗糙集理论、神经网络和蜂群算法线性集成多分类器的客户流失预测模型。首先利用自组织神经网络(SOM)对连续属性值进行非监督离散化处理;接着使用粗糙集方法(RS)对离散属性进行约简;然后分别使用BP神经网络、RBF神经网络、ELMAN神经网络和广义回归神经网络(GRNN)在约简属性集上建立4个子分类器;最后使用模型集成法对4个子分类器进行线性集成,并采用人工蜂群(ABC)算法优化线性组合的权重。将该模型应用于某电信客户流失,实验结果表明该集成方法是可行且有效的。
In this paper,on account of the complexity of customer churn in communication industry,fusing the advantages of rough sets,neural network and artificial bee colony algorithm（ABC）,a new customer churn prediction model is put forward,which is a linear-fused multiple classifier based on rough sets theory,neural network and artificial bee colony algorithm.Firstly,it completes the unsupervised separation of the continuous attributes using SOM;secondly,it reduces the discrete attributes using rough sets theory;thirdly,it builds four sub-classifiers on the reduced attribute set using BP neural network,radial basis function neural network（RBF）,ELMAN neural network and generalized regression neural network（GRNN）;finally,it integrates linearly the prediction results from the sub-classifiers and optimize the weights by ABC.Through applying the model to customer churn research in a telecommunication enterprise,the experiments results suggest that the integration technique is feasible and very efficient.
出处
《管理学报》
CSSCI
2011年第2期265-272,共8页
Chinese Journal of Management
基金
国家自然科学基金资助项目(70801021)
中国博士后科学基金资助项目(20080431276)
教育部人文社会科学基金资助项目(08JC630019)
关键词
客户流失
粗糙集理论
神经网络
人工蜂群算法
多分类器集成
customer churn
rough sets
neural network
artificial bee colony algorithm（ABC）
multiple classifiers fusing
