基于IGOWMA算子的变权系数区间型组合预测模型

The combined prediction model based on IGOWMA operator for the number of intervals of variable weight coefficients

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.

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 parameterλexhibit a significant effect on the weight coefficient,the optimal objective function value and the error indicator of the model,while the preference coefficientαperform 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.