基于BAS-BP网络的企业财务风险智能化预警系统研究  

Research on Intelligent Early Warning System for Enterprise Financial Risks Based on BAS-BP Network

作　　者：董文杰 DONG Wenjie(Dalian University of Finance and Economics,Dalian Liaoning 116000,China)

机构地区：[1]大连财经学院,辽宁大连116000

出　　处：《长春工程学院学报（自然科学版）》2024年第4期102-106,共5页Journal of Changchun Institute of Technology：Natural Sciences Edition

基　　金：辽宁省教育厅基本科研项目(LJBKYF2021001,LJKMR20221957)。

摘　　要：针对BP神经网络对企业财务风险预警准确率低的问题,采用BAS对BP神经网络初始权值与阈值优化,构建了基于BAS-BP神经网络的企业财务风险智能化预警系统。通过和GA、PSO的对比,验证了BAS对初始权值与阈值优化的良好性能,并采用试错法获得了BP神经网络隐含层最佳神经元的个数。将获取的10家企业数据输入到企业财务风险智能化预警系统中,得到了企业的财务风险等级,指出房地产行业、汽车行业的大部分企业在经营过程中面临的相对比较高的财务风险等级。对企业及时调整经营战略,确保企业的健康发展具有一定的参考价值。In response to the problem of low accuracy of BP neural network in early warning of corporate financial risks,BAS is used to optimize the initial weights and thresholds of BP neural network,and an intelligent early warning system for enterprise financial risk based on BAS-BP neural network is constructed.By comparing with GA and PSO,the good performance of BAS in optimizing initial weights and thresholds is verified,and the optimal number of neurons in the hidden layer of BP neural network is obtained using trial and error method.By inputting data from 10 enterprises into the intelligent financial risk warning system,the financial risk levels of the enterprises are obtained,indicating that most enterprises in the real estate and automotive industries face relatively high financial risk levels in the operations.It has certain practical application value for enterprises to adjust their business strategies in a timely manner and ensure their healthy development.

关 键 词：BAS-BP网络 企业财务风险 智能化预警系统 

分 类 号：TP415[自动化与计算机技术]