应用Tensorflow 2进行银行客户分类研究  

Research on Bank Customer Classification Based on Tensorflow 2

作　　者：沈巧云[1] 曾棕根[2] SHEN Qiaoyun;ZENG Zonggen(School of innovation and Entrepreneurship,Ningbo Polytechnic,Ningbo,China,315800;School of Electronic Information Engineering,Ningbo Polytechnic,Ningbo,China,315800)

机构地区：[1]宁波职业技术学院创新创业学院,浙江宁波315800 [2]宁波职业技术学院电子信息工程学院,浙江宁波315800

出　　处：《福建电脑》2021年第4期91-94,共4页Journal of Fujian Computer

基　　金：宁波职业技术学院校级课题“基于MOOC平台线上线下混合式教学模式研究与实践”(No.NZ19C009)资助。

摘　　要：本文利用当前最流行的深度学习框架Tensorflow 2.3,设计了全连接神经网络模型,对银行历史购买理财产品的客户数据进行训练,生成了准确度高的神经网络模型,并利用该模型对新客户是否会购买理财产品预测。结果表明,该模型准确度达到90%以上,获得了较好的应用效果。This paper uses tensorflow 2.3, the most popular deep learning framework, to design a fully connected neural network model, train the historical data of bank customers who buy financial products, generate a neural network model with high accuracy, and use the model to predict whether new customers will buy financial products. The results show that the accuracy of the model is more than 90%, and the application effect is good.

关 键 词：深度学习 人工智能 Tensorflow 二分类问题 电话营销 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]