基于支持向量机预测的时序多属性决策法

Decision-making method of time series multiple attribute based on prediction with support vector machine

针对时序多属性决策问题中的预测量大且时间样本有限的特点,以各决策单元的属性时间序列为样本数据,进行多变量时间序列相空间重构,建立用支持向量机预测未来属性值方法,进而提出综合考察决策单元的过去、现在与未来的情况下进行更科学、合理的时序多属性决策方法.

Aimed at the feature of decision-making of time sequencing attribute where the prediction amount was large and the time sample was limited in number,a method for prediction of future attribute value was developed based on support vector machine.Multivariable phase space reconstruction was conducted for the time sequencing by taking the attribute time series of several decision-making units as sample data,so that a more scientific and rational method for decision-making of time series multiple attribute was presented,in which the past,present and future condition of decision-making units was comprehensively investigated.