Client loss early warning model establishment method and device, terminal equipment and medium

• Main Authors: LI ZHENGDAO, GUO SHIPING, LAI XULU, XIAO YAHONG, GUO XING, XIAO BING
• Format: Patent
• Language: Chinese; English
• Published: 25.06.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention is suitable for the technical field of machine learning, and provides a client loss early warning model establishment method and device, terminal equipment and a medium. The method comprises the steps: obtaining a training sample set which comprises a plurality of pieces of client data; extracting a plurality of attributes from the training sample set, and establishing a decision tree according to the plurality of attributes and the training sample set; trimming the decision tree according to the weights of the plurality of attributes, and taking the attributes in the decision tree after trimming as influence indexes of customer loss; and according to the influence index and the pruned decision tree, training a preset neural network model to obtain the customer loss early warning model. The customer loss early warning model established through the method has relatively high pre-judgment accuracy and relatively high robustness. 本申请适用于机器学习技术领域，提供了客户流失预警模型的建立方法、装置、终端设备及介质，所述方法包括：获取训练样本集，所述训练样本集包括多个