基于LM算法的企业资信网络评估模型研究

Levenberg-Marquardt-based Neural Network for Corporation Credit Rating

针对当前企业资信评估方法的不足,提出将基于Levenberg-Marquard(LM)算法的前向多层神经网络用于企业资信评估,并通过MATLAB神经网络工具对其进行模拟计算。实验结果表明,该方法稳定、快捷、预测准确,对企业资信评估有着良好的性能。

In this study, artificial neural network model, based on feed forward architecture and Levenberg-Marquardt as training algorithm, is applied to the problem of corporation credit rating to avoid the inability of conventional credit rating methods. Matlab Software and its neural network toolbox are used to establish the model. The experiment results show that the neural network model for credit rating is fast and accurate.