基于ARIMA与GM(1,1)模型的民航月度运输总周转量预测

Forecasting of total monthly transportation turnover of civil aviation based on ARIMA and GM(1,1)model

比较ARIMA与GM(1,1)两种模型对中国民航月度运输总周转量预测结果,选择拟合程度较高的模型应用于运输总周转量短期预测分析。分别运用SPSS22.0软件和Matlab软件对选取的2009年10月—2019年9月的数据进行ARIMA建模和GM(1,1)建模,根据2019年10月—12月的预测数据拟合效果,确定预测民航月度运输总周转量的最佳模型。结果表明:ARIMA(2,1,0)(0,1,1)12模型和GM(1,1)模型的计算值与实际值拟合程度都相对较好,均可用于未来短期数据的预测。两个模型对2019年10—12月预测值的平均相对误差分别为2.26%和4.15%。ARIMA(2,1,0)(0,1,1)12模型可以更好地与实际民航月度运输周转量历史数据相拟合,可以应用于民航月度运输总周转量的预测。预测结果可为民航发展规划战略提供相应的数据支持。

To compare the forecasting results of ARIMA model and GM(1,1)model on the monthly total transportation turnover of CAAC,the model with a higher fitting degree was select to apply to the short‑term forecasting analysis of the total transportation turnover.The selected data from October 2009 to September 2019 were modeled by ARIMA and GM(1,1)respectively using SPSS22.0 software and MATLAB.According to the fitting effect of the forecast data from October 2019 to December 2019,the best model for predicting the total monthly transportation turnover of civil aviation was determined.The results showed that the calculated values of ARIMA(2,1,0)(0,1,1)12 model and GM(1,1)model fit the actual values relatively well,and both of them can be used to predict the future short‑term data.The average relative errors of the two models'forecasts for October 2019 to December 2019 are 2.26%and 4.15%,respectively.ARIMA(2,1,0)(0,1,1)12 model can better fit with the historical data of actual civil aviation transportation turnover,and can be applied to the prediction of the total monthly transportation turnover of civil aviation.The forecast results can provide the corresponding data support for the development planning strategy of civil aviation.