Customer loss prediction method and device, and storage medium

• Main Authors: SONG LINLI, LI WEI, LI TING
• Format: Patent
• Language: Chinese; English
• Published: 07.05.2021
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a customer loss prediction method, relates to the field of data analysis, and solves the problem that in the prior art, loss of a large number of customers is caused and the benefit of a unit is affected due to the fact that loss customers cannot be predicted.The method comprises the following steps: acquiring personal data of a customer; constructing an index feature wide table according to the personal data; determining a potential lost customer list by using an RF algorithm according to the feature wide table; according to the potential lost customer list and a Kmeans + + algorithm, grouping the potential lost customers, and determining features of the potential customers of each group; and predicting the potential loss list, performing grouping according to the list, maintaining the potential loss clients in a targeted manner, and reducing the loss of the clients to the greatest extent. 本申请公开了一种客户流失的预测方法，涉及数据分析领域，解决了现有技术中，不能对流失客户进行预测，导致大量客户流失，影响该单位的效益的问题，该方法包括：获取客户的个人数据；根据个人数据，构建指标