基于代价敏感的决策树的电信离网分析模型

随着电信行业竞争的加剧,客户流失率日益攀升,因此提高客户流失的预测精度将直接关系到电信企业的生存和发展.而电信客户数据集中存在严重的数据不平衡问题,会导致两类错分代价明显不等同.而基于传统决策树的客户流失模型却是在两类错分代价相等的前提下建立的,与实际情况不符.因此引入代价敏感学习理论,该理论将不同的错分代价纳入建模过程,以建立一个基于代价敏感的决策树的电信客户离网分析模型.该方法有效地提高了模型对流失客户的预测性能.这对促进电信业的发展具有相当重要的意义.

Telecom Customer Churn Prediction Model Based on Cost-sensitive Decision Tree

With the fiercer competition in telecom industry,the customer churn rate is increasing.So,to predict churn precisely becomes a key factor of the existence and development of telecom corporations.Because of the seriously unbalanced data set,the two misclassification costs are obviously different in this field.But the prediction model based on traditional decision tree ignores this difference.Thus results the impracticability.This paper brings forward the cost-sensitive learning theory,which brings different ...