YANG Ye,YUAN Hongjun,HU Lingyun.The combined prediction model based on IGOWMA operator for the number of intervals of variable weight coefficients[J].Journal of Yanbian University,2023,(01):8-15.
基于IGOWMA算子的变权系数区间型组合预测模型
- Title:
- The combined prediction model based on IGOWMA operator for the number of intervals of variable weight coefficients
- 文章编号:
- 1004-4353(2023)01-0008-08
- Keywords:
- interval number; prediction accuracy; combined prediction; IGOWMA operator; sensitivity analysis
- 分类号:
- F224.0
- 文献标志码:
- A
- 摘要:
- 为了保持区间数内部的整体性及提高区间数的预测精度,提出了一种将改进相关系数和诱导广义有序加权多重平均(IGOWMA)算子相结合的区间型组合预测方法.该方法首先将区间数进行转化,以等价信息的中心和半径来表示区间数; 然后以预测精度为诱导因子,构建IGOWMA算子; 最后选取改进后的Pearson相关系数作为最优准则来建立多目标非线性规划模型,并通过引入偏好系数将模型转化为单目标规划模型.实例验证证明,该区间型组合预测模型不仅能够保证区间数内部的整体性,而且其预测结果显著优于文献中的3种单项预测方法和1种组合预测方法.对模型的参数进行灵敏度分析显示,参数λ的取值对模型的权系数、最优目标函数值以及误差指标有较明显的影响,偏好系数α则对模型的影响较小.上述结果表明,该组合预测方法能有效提高预测精度,可应用于区间数的模糊预测中.
- Abstract:
- In order to maintain the internal wholeness and improve the prediction accuracy of interval numbers, a combined interval number prediction method associated with both improved correlation coefficients and induced generalized ordered weighted multiple averaging(IGOWMA)operators is proposed.Firstly, the number of intervals is transformed into centers and radii of equivalent information; secondly, the IGOWMA operator is constructed with prediction accuracy as the inducing factor; thirdly, the improved Pearson correlation coefficient is selected as the optimal criterion and a multi - objective non - linear programming model; finally, the model is transformed into a single - objective programming model by introducing preference coefficients.The empirical validation proves that this interval number combined forecasting model not only ensures the wholeness of the interval number, but also its forecasting results are significantly better than the three single forecasting methods and the one combined forecasting method in the literature.A sensitivity analysis of the model parameters shows that the value of the parameter λ exhibit a significant effect on the weight coefficient, the optimal objective function value and the error indicator of the model, while the preference coefficient α perform a small effect on the model as a whole.The above results show that the combined prediction method can effectively improve the prediction accuracy and can be applied to the fuzzy prediction of interval data.
参考文献/References:
[1] 袁宏俊,陈华友,胡凌云.基于指数支撑度的最优组合预测模型及其性质研究[J].应用概率统计,2012,28(2):150 - 160.
[2] 孙浩,杨桂元.基于一种贴近度的IGOWLA算子的最优组合预测模型[J].延边大学学报(自然科学版),2017,43(1):19 - 24.
[3] 朱家明,陈华友,周礼刚,等.基于ICOFWA算子的连续区间模糊组合预测模型及其应用[J].模糊系统与数学,2016(3):172 - 184.
[4] 袁宏俊,杜康,胡凌云.基于三角模糊数相似度的区间型组合预测模型[J].统计与决策,2019,35(6):24 - 29.
[5] 杜康,袁宏俊,郑亚男.基于三角模糊数及GIOWA算子的区间型组合预测模型[J].统计与决策,2019,35(16):22 - 28.
[6] 张娜,葛磊蛟.基于SOA优化的光伏短期出力区间组合预测[J].太阳能学报,2021,42(5):252 - 259.
[7] 邱红洁,谷银山,李翠.模糊预测的组合预测[J].统计与决策,2009(17):155 - 157.
[8] 朱家明,陈华友,周礼刚,等.基于TFWPA算子的模糊优化组合预测模型及其应用[J].运筹与管理,2017,26(5):102 - 109.
[9] 戴现朝,李浩,周礼刚,等.一种基于IGOWMA算子和广义向量夹角余弦的最优区间组合预测模型[J].系统科学与数学,2022,42(11):3060-3072.
[10] ERDEM O, CEYHAN E, VARLI Y.A new correlation coefficient for bivariate time - series data [J].Physica A: Statistical Mechanics and its Applications, 2014,414:274 - 284.
[11] 陈华友,李翔,金磊,等.基于相关系数及IOWA算子的区间组合预测方法[J].统计与决策,2012(6):83 - 86.
相似文献/References:
[1]孙冲,侯为波,孙敏.基于模糊数对证券投资组合选择模型有效前沿的动态分析[J].延边大学学报(自然科学版),2017,43(02):154.
SUN Chong,HOU Weibo,SUN Min.Dynamic analysis for portfolio selection efficient frontier based on fuzzy number[J].Journal of Yanbian University,2017,43(01):154.
[2]胡凌云,袁宏俊,周洁.基于区间数距离的IGOWLA算子的区间型组合预测模型[J].延边大学学报(自然科学版),2018,44(02):109.
HU Lingyun,YUAN Hongjun,ZHOU Jie.The interval combination forecasting model based on interval number distance and IGOWLA operator[J].Journal of Yanbian University,2018,44(01):109.
[3]朱国成,陈利群.决策信息数据为区间数的一种多属性群决策方法[J].延边大学学报(自然科学版),2021,47(02):146.
ZHU Guocheng,CHENG Liqun.A multi - attribute group decision - making method for interval number decision information data[J].Journal of Yanbian University,2021,47(01):146.
[4]朱国成,陈利群.区间数刻画属性值下的两种多属性决策新算法[J].延边大学学报(自然科学版),2021,47(04):297.
ZHU Guocheng,CHEN Liqun.Two new algorithms for multi - attribute decision making under attribute values are described by interval number[J].Journal of Yanbian University,2021,47(01):297.
备注/Memo
收稿日期: 2022-11-28
基金项目: 安徽省哲学社会科学规划项目(AHSKY2020D42); 安徽财经大学重大科研基金(ACKYA21004);
安徽省高校研究生科研项目(YJS20210440)
第一作者: 杨烨(1999—),男,硕士研究生,研究方向为经济组合预测与分析.