| 基于邻域粗糙集和神经网络的财务预警研究 |
| |
| 引用本文： | 马超群,吴丽华.基于邻域粗糙集和神经网络的财务预警研究[J].软科学,2009,23(11):123-126,139. |
| |
| 作者姓名： | 马超群 吴丽华 |
| |
| 作者单位： | 湖南大学,工商管理学院,长沙,410082 |
| |
| 基金项目： | 国家自然科学基金资助项目，国家杰出青年科学基金资助项目 |
| |
| 摘 要： | 利用邻域粗糙集对属性进行约简,得到由财务指标和非财务指标构成的预警指标体系。将其作为神经网络的输入变量对我国上市公司财务状况进行预测。实证研究表明,模型能有效剔除冗余信息,避免传统粗糙集模型因数值离散化带来的信息丢失。在大大缩短训练时间的同时,模型的预测精度达91.7%,高于同等条件下神经网络模型、Logistic模型。
|
| 关 键 词： | 财务预警 邻域粗糙集 属性约简 BP神经网络 |
A Study on Prediction Financial Distress of Firms Based on Integration of Nejghborhood Rough Sets and Neural Network |
| |
| MA Chao-qun,WU Li-hua.A Study on Prediction Financial Distress of Firms Based on Integration of Nejghborhood Rough Sets and Neural Network[J].Soft Science,2009,23(11):123-126,139. |
| |
| Authors: | MA Chao-qun WU Li-hua |
| |
| Abstract: | Based on attribute reduce of neighborhood rough sets,this paper gets the reduced information,including financial ratios and non-financial attributes.Then it is used to train neural network to get financial early-warning.Experiment result shows that comparing with classical rough sets,the model can effectively remove redundant information and avoid information loss because of discretizing of numerical attributes;the prediction accuracy of that model reaches to 91.5%,which is more accurate than that by neural network and Logistic approach respectively,when saves training time. |
| |
| Keywords: | financial distress neighborhood rough set attribute reduce BP neutral network |
| 本文献已被 维普 万方数据 等数据库收录！ |
|
