一种新型高精度的区间数组合预测方法  

A New Interval Number Combination Forecasting Method With High Accuracy

作　　者：胡凌云[1] 杨威[1] 王恒娜[1] Hu Lingyun;Yang Wei;Wang Hengna(School of Management Science and Engineering,Anhui University of Finance and Economics,Bengbu Anhui 233030,China)

机构地区：[1]安徽财经大学管理科学与工程学院,安徽蚌埠233030

出　　处：《统计与决策》2021年第24期5-10,共6页Statistics & Decision

基　　金：安徽省哲学社会科学规划项目(AHSKY2020D42)。

摘　　要：在模糊型数据(区间数)的预测问题中,为了有效提高预测精度,学术界开展了变权系数组合预测方法的研究。文章引入新的广义诱导有序加权比例平均(GIOWPA)算子,以误差绝对值之和为最优准则,建立了基于GIOWPA算子及误差绝对值之和的区间数组合预测模型。通过实例分析,将构建的模型与已有文献中的方法作对比分析,结果显示该模型具有较高的预测精度。In order to improve the prediction accuracy in the prediction of fuzzy data(interval number), the academic circles have carried out researches on the combination forecasting method of variable weight coefficient. This paper introduces a new generalized inductively ordered weighted proportional average(GIOWPA) operator, takes the sum of the absolute values of the error as the optimal criterion to construct an interval number combination forecasting model based on the GIOWPA operator and the sum of the absolute values of the error. Through case analysis, the paper compares the proposed model with the methods in existing literature, and the results show that the proposed model has high prediction accuracy.

关 键 词：区间数组合预测 高精度 GIOWPA算子 误差绝对值之和 

分 类 号：C934[经济管理—管理学]