Customer churn prediction in telecommunications
Customer churn prediction in telecommunications
复制标题
DOI：
10.1016/j.eswa.2011.08.024
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
B. Huang;Mohand Tahar Kechadi;Brian Buckley
中科院分区：
文献类型：
--
作者：
B. Huang;Mohand Tahar Kechadi;Brian Buckley
本文提出了一套新的固网客户流失预测功能，包括 2 个 6 个月亨利细分、精确的 4 个月通话详细信息、线路信息、帐单和付款信息、帐户信息、人口统计概况、服务订单、投诉信息等。然后将七种预测技术（逻辑回归、线性分类、朴素贝叶斯、决策树、多层感知器神经网络、支持向量机和进化数据挖掘算法）应用于客户流失基于新功能，将流失作为预测变量。最后，进行了比较实验来评估新的特征集和用于客户流失预测的七种建模技术。实验结果表明，六种建模技术的新特征在电信服务领域的客户流失预测方面比现有特征更有效。
This paper presents a new set of features for land-line customer churn prediction, including 2 six-month Henley segmentation, precise 4-month call details, line information, bill and payment information, account information, demographic profiles, service orders, complain information, etc. Then the seven prediction techniques (Logistic Regressions, Linear Classifications, Naive Bayes, Decision Trees, Multilayer Perceptron Neural Networks, Support Vector Machines and the Evolutionary Data Mining Algorithm) are applied in customer churn as predictors, based on the new features. Finally, the comparative experiments were carried out to evaluate the new feature set and the seven modelling techniques for customer churn prediction. The experimental results show that the new features with the six modelling techniques are more effective than the existing ones for customer churn prediction in the telecommunication service field.