检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
机构地区:[1]新乡学院计算机与信息工程学院,河南新乡453000
出 处:《计算机仿真》2011年第7期329-332,共4页Computer Simulation
基 金:河南省科技厅科技发展计划项目(092400440056)
摘 要:电信流失客户数据精确预测是挽留客户的有效手段。电信业的管理中对收费、投诉、业务受理等问题,显然是一种典型的非平衡样本,传统用标准的支持向量机没有考虑样本分布不平衡问题,虽然在样本数据平衡前提下具有较好的预测精度,但对于不平衡电信客户数据,预测精度大大下降。为提高预测精度,针对支持向量机处理不平衡样本时的缺陷,提出了基于代价敏感学习的支持向量机模型。模型利用代价敏感学习对不平衡样本集分别采用不同惩罚系数,然后建立电信客户流失预测模型,最后对实际电信客户流失数据进行测试。通过与标准支持向量机、神经网络对比,结果表示模型提高了预测精度,有效地解决了数据集非平衡性问题,是一种有效的电信客户流失预测方法。Telecom losing customers prediction is an effective means to retain customers.The management of the telecommunications industry includes charge,complaints,and the business acceptation,which obviously is a typical unbalanced sample,and the traditional support vector machine does not consider sample imbalance problem,although it has good prediction accuracy for the balanced sample data.But the prediction accuracy is dramatically reduced for unbalance telecom customer data.To improve the forecasting accuracy,an improved SVM model is put forward based on the traditional SVM.The model adopts different punishment coefficient for unbalanced samples,then builds up telecom customer churning models,and finally is tested with the actual telecom customer data.Compared with the standard support vector machine and neural network,the results show that the proposed model improves the accuracy of the predictions,effectively solves the data unbalance problem,and it is an effective method for customer churn telecom prediction.
分 类 号:TP18[自动化与计算机技术—控制理论与控制工程]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.124