摘要
首先构建了行业间中小企业信用评估指标体系,然后利用安徽省不同行业的800家中小企业调查数据,将其分为训练样本集和测试样本集,对BP神经网络的构造进行讨论,确定BP神经网络的算法,建立起基于BP神经网络的行业间信用评估模型,并代入2003年度全国农业和工业的部分分行业数据进行实证,并对仿真结果做出分析,指出造成农、工行业信用较大差距的原因,并提出加强农业行业信用建设的建议.
This paper first build an assessment indicator system for middle and small business among industries. Then utilizes the investigating data from 800 middle and small businesses in different industries in Anhui Province, divides them into training sample and testing sample, discusses the construction of BP neural network, decides the algorithm of BP neural network, so as to set up the credit assessment model among industries based on BP neural network. After carrying on a demonstrated analysis by inputting the data from some sub-industries in agricultural industry and industrial industry in the year of 2003, and analyzing the simulation result, it points out the reasons to result in the large gap between agricultural and industrial industry, and puts forward the suggestion aiming at the credit construction in agricultural industry.
出处
《数学的实践与认识》
CSCD
北大核心
2007年第24期47-54,共8页
Mathematics in Practice and Theory
关键词
BP神经网络
信用评估
比较分析
BP neural network
credit assessment
comparative analysis