计算机与现代化

• 数据库与数据挖掘 • 上一篇    下一篇

基于MLP神经网络模型的客户评分应用研究

  

  1. 1.广东省邮政信息技术局,广东广州510000; 2.巴黎第九大学,法国巴黎75775
  • 收稿日期:2016-08-05 出版日期:2017-03-29 发布日期:2017-03-30
  • 作者简介:王冰(1984-),女,辽宁沈阳人,广东省邮政信息技术局工程师,硕士,研究方向:应用数学,数据分析,数据挖掘; 韩俊宇(1984-),男,广东广州人,巴黎第九大学讲师,博士,研 究方向:宏观经济学,货币政策。

Research on Customer Scoring Application Based on MLP Neural Network Model

  1. 1. Guangdong Postal Information Technology Bureau, Guangzhou 510000, China;
    2. University ParisDauphine, Paris 75775, France
  • Received:2016-08-05 Online:2017-03-29 Published:2017-03-30

摘要:

判断客户对产品购买的可能性,是企业营销人员重点关注的问题。针对保险产品客户与其他金融客户交叉销售,采用人工智能方法高精度量化客户的潜在购买力。根据对个人保险客户营销的总结,
提出保险客户购买评分模型。通过使用中国邮政代理金融的简易保险客户数据,对模型的有效性进行实证研究。研究结果表明,该模型提供了较高效的预测准确率和具体的评价标准,具有良好的预测功
能,可以帮助企业及时发现最有效的营销客户,最大程度上提高营销成功率。

关键词: 评分模型, 多层感知器(MLP), 神经网络, 数据挖掘

Abstract:

The judgment of the possibility that customers purchase products is the focus of the enterprise marketers attention. The paper addresses the crossselling for the
insurance product customers and other financial product customers, thereby highly accurately quantifies their potential purchasing power. According to the summary of the applied
theory of the personal insurance business, this paper presents a customer purchasing behavior scoring model. Through the use of the simplified insurance customer data of China
Post Financiers, this paper carries out an empirical analysis of the model effectiveness. The results of the study show that the model, with a good forecasting performance,
provides more efficient predictions and specific evaluation criteria, thus being able to help enterprises timely identify the most effective marketing tool for customer
acquisition and retention, ultimately improving marketing success to a greater extent.

Key words: scoring model, multilayer perceptron (MLP), neural network, data mining

中图分类号: