| 基于ART2模型的信用风险评估 |
| |
| 引用本文： | 马海英. 基于ART2模型的信用风险评估[J]. 华东理工大学学报(社会科学版), 2006, 21(4): 47-51 |
| |
| 作者姓名： | 马海英 |
| |
| 作者单位： | 华东理工大学商学院,上海,200237 |
| |
| 摘 要： | 自适应共振模型是为了能够分类任意次序模拟输入模式而设计的,它可以按任意精度对输入的模拟观察矢量进行分类,较好地解决了前稳定性和灵活性问题,同时能够避免对网络先前所学的学习模式修改。本文将ART2模型应用于信用风险评估,通过实证比较研究,结果显示应用自适应共振模型进行信用风险评估在精度和准确性上,都优于其他神经网络模型和统计方法。
|
| 关 键 词： | 适应共振 神经网络 信用风险 |
| 文章编号： | 1008-7672(2006)04-0047-05 |
| 修稿时间： | 2006-09-07 |
Credit Risk Evaluation Based On ART2 |
| |
| MA Haiying. Credit Risk Evaluation Based On ART2[J]. Journal of East China University of Science and Technology:Social Science Edition, 2006, 21(4): 47-51 |
| |
| Authors: | MA Haiying |
| |
| Abstract: | IART2 is designed to classify simulated input mode with random order. It can classify simulated observing vector based on random precision, which solves problems of pre-stability and flexibility; still, it can avoid amendment of former study mode of the network. This paper uses ART2 to evaluate credit risk, and its precision and accurateness are prior to other nerve network mode and statistical method through comparative research of real case. |
| |
| Keywords: | ART2 neural network credit risk |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
