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.
作者
沈巧云
曾棕根
SHEN Qiaoyun;ZENG Zonggen(School of innovation and Entrepreneurship,Ningbo Polytechnic,Ningbo,China,315800;School of Electronic Information Engineering,Ningbo Polytechnic,Ningbo,China,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。
