宏观经济风险分析的动态贝叶斯分类器方法  

Method of dynamic Bayesian classifier for analysis of macroeconomic risk

作　　者：冷翠平[1] 王双成[1,2] 高瑞[1] 

机构地区：[1]上海立信会计学院数学与信息学院,上海201620 [2]上海立信会计学院开放经济与贸易研究中心,上海201620

出　　处：《计算机工程与应用》2016年第3期224-229,共6页Computer Engineering and Applications

基　　金：教育部人文社科基金项目(No.10YJA630154);上海市教委科研创新项目(No.11YZ240);上海市教委重点学科建设项目(No.J51702)

摘　　要：相关因素对宏观经济风险影响的时滞分析是研究中国经济运行情况的重要问题之一,目前,主要采用数量经济方法进行宏观经济风险时滞影响分析方面的研究,但这些方法主要利用时序或非时序信息,不易实现二者的有机结合。k阶多马尔科夫链动态朴素贝叶斯分类器是一种特殊的动态贝叶斯分类器,在该分类器中,属性和类均构成马尔科夫链,通过朴素贝叶斯网络结构将这些马尔科夫链组合在一起形成分类器结构,从而使相关指标的动态和静态信息均能得到充分的利用,并将其用于宏观经济风险时滞影响分析。实验结果证明该分类器在时滞影响分析方面更加可靠和实用。The time-delay analysis of relevant factors to macroeconomic risk is an important issue for studying China＇ s economic operation.At present, there have been some researches on the time-delay analysis of macroeconomic risk based on quantitative economics methods.But these methods mainly use timing or non-timing information so that two kinds of information can not be used together.K order multi Markov chain dynamic naive Bayesian classifier is a special dynamic naive Bayesian classifier.In this classifier, attributes and class separately form Markov chains.These Markov chains are combined with naive Bayesian network to form classifier structure.Then dynamic and static information can been fully used between macroeeonomic indicators.Experimental results show that this classifier can improve the reliability and the availability of time-delay analysis.

关 键 词：宏观经济风险 时滞影响分析 动态朴素贝叶斯分类器 马尔科夫链 识别能力 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]