摘要
目前经济预警方法主要包括指标预警、统计预警、模型预警3类,这3类方法各有优劣。模型预警法常使用ARCH模型预警与人工神经网络模型预警。将自组织数据挖掘方法引入经济预警建模过程,通过实证研究发现:自组织数据挖掘方法在经济预警研究中具有较强的学习能力,在模型变量筛选时能有效避免人为因素的影响;与人工神经网络相比较,它建立的显式模型能够反映输入指标对输出指标的具体影响状况,将有助于分析警源,排除警情。研究结果表明,自组织数据挖掘方法将为经济预警提供一种新的模型预警法。
The methods used in the economic pre-warning are very important and include the index economic pre-warning, statistic economic pre-warning and model economic pre-warning. The ARCH model and the nerval net model are often used in the model economic pre-warning. The self-organization data mining in the economic pre-warning is tried to use. It has the powerful ability of study in the research of the economic pre-warning and can avoid the personal influence when selecting variable of the model. Compared with the nerval net model the self-organization data mining can reflect the influence of the index input to the index output. This helps to analyze the origin of the warning and dissolve it. The results show that the self-organization data mining provides a new method to the model economic pre-warning.
出处
《成都信息工程学院学报》
2005年第1期101-106,共6页
Journal of Chengdu University of Information Technology
基金
国家自然科学基金资助项目(70271073)
关键词
经济预警
模型预警
自组织数据挖掘方法
economic pre-warning
model pre-warning
self-organization data mining
