首页> 外文会议>IEEE International Conference on Software Engineering and Service Science >Application of DE-GWO-SVM Algorithm in Business Order Prediction Model
【24h】

Application of DE-GWO-SVM Algorithm in Business Order Prediction Model

机译:DE-GWO-SVM算法在业务订单预测模型中的应用

获取原文

摘要

To judge whether customers will choose the time deposit business launched by the bank is a problem of prediction classification, and it is also a problem that bankers want to know and urgently need to solve. This paper constructs a prediction model of banking business order based on DE-GWO-SVM algorithm. The model uses Differential Evolution algorithm and Grey Wolf algorithm to optimize the Support Vector Machine, and then applies the model to the prediction of bank marketing business order, which can effectively classify and identify whether bank customers will buy the time deposit business. Finally through the model experiment and comparing the Grey Wolf algorithm for without optimization, it is concluded that the model of banking business order based on DE-GWO-SVM algorithm, at an effective prediction accuracy of 96.8%, will help Banks identify the target customer groups, carry on the accurate marketing, improve the success rate of business marketing.
机译:判断客户是否选择银行开设的定期存款业务是预测分类的问题,也是银行家想知道且迫切需要解决的问题。本文建立了基于DE-GWO-SVM算法的银行业务订单预测模型。该模型利用差分进化算法和灰狼算法对支持向量机进行优化,然后将该模型应用于银行营销业务订单的预测,可以有效地分类识别银行客户是否愿意购买定期存款业务。最后通过模型实验并比较了未经优化的Gray Wolf算法,得出基于DE-GWO-SVM算法的银行业务订单模型的有效预测精度为96.8%,将有助于银行识别目标客户。团体,进行准确的营销,提高企业营销的成功率。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

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