银行个人客户流失预警模型的研究与应用  

Research and Application of Bank Customer Churn Warning Models

作　　者：刘训艳 杨晓彦 李梦霄 陆雨欣 曹婉茹 牟槿 

机构地区：[1]上海银行股份有限公司

出　　处：《信息技术与标准化》2021年第6期30-34,共5页Information Technology & Standardization

摘　　要：针对商业银行传统金融业务正面临客户流失等巨大挑战,通过对商业银行理财/定存客户的特征分析,进行特征清洗、特征衍生和特征筛选,阐述应用梯度提升决策树(GBDT)建立客户流失预警模型的方法,划分训练集、测试集和验证集进行模型有效性验证。通过模型ABtest分析挽留客群筛选策略和营销策略,降低客户的流失金额。The traditional financial business of commercial banks is facing great challenges such as customer churn.In order to solve this problem,this paper analyzed the characteristics of financial management/time deposit customers of commercial banks,and carried out feature cleaning,feature derivation and feature screening.We described the method of building customer churn warning model using gradient boosting decision tree(GBDT),and divided the training set,test set and verification set to verify the effectiveness of the model.Through the method of ABtest,this paper analyzed the retaining customer group selection strategy and marketing strategy to reduce the loss of customers.

关 键 词：GBDT 客户流失 预测模型 客群筛选 营销策略 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] F830.3[自动化与计算机技术—控制科学与工程] F274[经济管理—金融学]