基于IOWA组合模型的高速铁路客运量预测研究

A High-Speed Railway Traffic Forecast based on IOWA Combined Model

准确预测高速铁路客运量,对铁路资源配置及经营管理具有重要作用。在考虑高速铁路客运量存在多重相关性影响因素和灰色特性的基础上,运用偏最小二乘回归模型和灰色GM(1,1)预测模型对我国高速铁路客运量进行预测,通过采用IOWA算子,依据单项预测方法在样本区间上各个时点的预测精度从高到低按顺序赋权,以误差平方和为准则构建IOWA组合预测模型,并运用该模型对"十三五"期间我国的高速铁路客运量进行预测。预测结果表明,IOWA组合预测模型能提高预测精度。

Accurately predicting the passenger traffic volume of high-speed railway plays an important role in the railway resource allocation as well as in the business management. On the basis of considering the multiple correlative influencing factors and grey characteristics of highspeed railway passenger traffic volume, we use the partial least-squares regression model and the grey GM（1,1） forecasting model to predict the passenger traffic volume of high-speed railway in China. According to the single forecasting method, the prediction accuracy of each time point in the sample interval is weighted in order from high to low, and IOWA combined forecasting model is constructed based on the sum of squared errors by using the IOWA operator. And the model is applied to the high-speed railway passenger traffic volume forecast during the ＂13 th Five-Year Plan＂ period in China. The forecast results show that IOWA combined forecasting model can improve the accuracy of combined forecasting.