摘要
现有的区间组合预测模型往往是将单项预测方法不同时刻的预测精度转化为实数,这将导致预测信息的损失。因此,文章提出一种新的区间预测精度的概念,将单项预测方法不同时刻的精度用区间数表示,并利用可能度对其进行排序;将排序后的预测精度作为诱导变量,构建基于区间预测精度和诱导有序加权平均(induced ordered weighted averaging,IOWA)算子的区间变权组合预测模型;实例分析说明了该区间组合预测方法的有效性;最后,对模型参数做了灵敏度分析。
In the existing interval combination forecasting model,the prediction accuracy of single forecasting method in different time is usually transferred into real number,which will lead to the loss of forecasting information.In this paper,a new conception of interval prediction accuracy is proposed,in which the prediction accuracy of single forecasting method in different time is expressed by interval number and ranked with possibility degree.The indexes of prediction accuracy are utilized as induced variables,and a variable weight combination forecasting model is established based on interval prediction accuracy and induced ordered weighted averaging(IOWA)operator.An example is illustrated to show that the model is valid.Finally,the sensitivity analysis of the parameters in the model is done.
作者
张宇菲
陈华友
何智莉
ZHANG Yufei;CHEN Huayou;HE Zhili(School of Mathematical Sciences,Anhui University,Hefei 230601,China)
出处
《合肥工业大学学报（自然科学版）》
CAS
北大核心
2018年第4期570-576,共7页
Journal of Hefei University of Technology：Natural Science
基金
国家自然科学基金资助项目(71371011
71301001)
安徽省高等学校自然科学研究资助项目(KJ2016A250)
安徽大学大学生科研训练计划资助项目(KYXL2016009)
安徽大学研究生学术创新研究资助项目(yfc100022)
关键词
区间预测精度
可能度排序
诱导有序加权平均(IOWA)算子
组合预测
灵敏度分析
interval prediction accuracy
ranking of possibility
induced ordered weighted averaging(IOWA)operator
combination forecasting
sensitivity analysis
