| 基于遗传算法和BP神经网络的信用风险测量模型 |
| |
| 引用本文： | 王宪全,陈李刚.基于遗传算法和BP神经网络的信用风险测量模型[J].哈尔滨工业大学学报(社会科学版),2006,8(5):87-92. |
| |
| 作者姓名： | 王宪全 陈李刚 |
| |
| 作者单位： | 哈尔滨工业大学,管理学院,哈尔滨,150001;哈尔滨工业大学,管理学院,哈尔滨,150001 |
| |
| 摘 要： | 随着新巴赛尔协议的推出,信用风险测量问题越来越受到重视。在西方发达国家,商业银行的信用风险管理测量技术已比较成熟,继传统的比例分析、主观分析之后,统计方法得到广泛的应用,如判别分析和logit回归分析等。自从20世纪80年代末期以来,人工智能技术如神经网络、专家系统等也被应用于商业银行信用风险测量中。目前,该领域应用最多的就是BP神经网络,但其固有的一些缺点,如易陷入局部极小点,会影响预测效果。但可以利用改进的遗传算法对BP神经网络进行优化,实验证明效果非常好。
|
| 关 键 词： | 信用风险 遗传算法 BP神经网络 |
| 文章编号： | 1009-1971(2006)05-0087-06 |
| 修稿时间： | 2006年7月4日 |
The Model of Credit Risk Measurement based on GA and BP NN |
| |
| WANG Xian-quan,CHEN Li-gang.The Model of Credit Risk Measurement based on GA and BP NN[J].Journal of Harbin Institute of Technology(Social Sciences Edition),2006,8(5):87-92. |
| |
| Authors: | WANG Xian-quan CHEN Li-gang |
| |
| Abstract: | Credit risk measurement becomes more important with the new Basel Capital Accord's publicizing.In developed countries,the technologies of credit risk measurement are mature.After traditional scale analysis and subjective analysis,statistic methods are used widely,for example discriminant analysis and Logit regression analysis.Artificial intelligence technologies as Neural Network and expert systems are also used in the field from 1980's.Now Back-Propagation Neural Network is used the most frequently in this field.But it has some shortcomings as likelihood of getting in local point.So effect will be impacted.This paper optimizes Back-Propagation Neural Network with improved Genetic Algorithm,and the result is good. |
| |
| Keywords: | credit risk genetic algorithm back propagation neural network |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
