首页> 外国专利> Predictive device for customer churn using Deep Learning and Boosted Decision Trees and method of predicting customer churn using it

Predictive device for customer churn using Deep Learning and Boosted Decision Trees and method of predicting customer churn using it

机译:使用深度学习和增强决策树的客户流失预测设备以及使用其预测客户流失的方法

摘要

The present invention relates to a customer departure prediction device for predicting whether a customer will leave from the service provided by the company, Customer departure prediction device according to an embodiment of the present invention, An input unit into which customer data is input; A pre-processing unit that pre-processes the customer data input to the input unit and classifies it into time-based pre-processing data and customer-based pre-processing data; The behavioral pattern is extracted using the classified time-based pre-processing data, the customer's statistical index is extracted using the classified customer-based pre-processing data, and the customer's departure is determined using the extracted behavioral pattern and statistical index. Predicting customer churn prediction unit; And an output unit which outputs a prediction result of the customer departure prediction unit.
机译:本发明涉及一种用于预测顾客是否将从公司提供的服务中离开的顾客离场预测装置,根据本发明实施例的顾客离场预测装置,用于输入顾客数据的输入单元,以及用于输入顾客数据的顾客离场预测装置。预处理单元,对输入到输入单元的客户数据进行预处理,并将其分类为基于时间的预处理数据和基于客户的预处理数据;使用分类的基于时间的预处理数据来提取行为模式,使用分类的基于客户的预处理数据来提取客户的统计指标,并使用提取的行为模式和统计指标来确定客户的离开。预测客户流失预测单元;输出单元输出顾客离场预测单元的预测结果。

著录项

  • 公开/公告号KR1021299620000B1

    专利类型

  • 公开/公告日2020-07-03

    原文格式PDF

  • 申请/专利权人

    申请/专利号KR1020180057094

  • 发明设计人 이지형;우상명;김경태;

    申请日2018-05-18

  • 分类号

  • 国家 KR

  • 入库时间 2022-08-21 10:57:14

相似文献

  • 专利
  • 外文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号