摘要
简单介绍了企业信用评价的一般模型以及BP神经网络的基本结构,在此基础上给出了一个具体的基于BP神经网络的企业信用评价模型。它把用来描述某类企业信用评价对象特征的信息作为神经网络的输入向量,而把代表相应综合评价结果的值即信用等级作为神经网络的输出,并用足够的样本训练这个网络,使不同的输入向量得到不同的输出量值。最后分析了使用BP神经网络技术评价企业信用等级的优越性。
Some traditional models for evaluating enterprise credit and the basic structure of BP neural networks are introduced firstly. And then a model for evaluating enterprise credit is given, which is based on BP neural networks. It takes the characteristics that are used to describe the credit of some enterprise as input vector of the neural network and considers the evaluating result as the output, which is the credit rank. After trained with enough specimens, the network will obtain different output values with different inputting vectors. Finally the superiorities of the model is analyzed.
出处
《控制工程》
CSCD
2003年第5期404-406,共3页
Control Engineering of China
