摘要
我国进出口贸易数据序列呈波浪上升趋势,传统预测方法难以获得理想预测效果。小波变换可去除原始信号中的噪声,灰色DGM(2,1)模型适合波动时间序列的预测。运用小波变换和灰色DGM(2,1)模型相结合的方法预测我国进出口贸易总额,取得了理想效果,2017年的预测误差仅为3.404 1%,比灰色GM(1,1)模型的10.849 3%减小22.485 3%,比普通灰色DGM(2,1)模型的15.801 1%减小46.777 1%。由模型预测得到2018年我国进出口贸易总额为4.378 288万亿美元。
The data sequence of China＇s import and export trade shows a wave rising trend, and the traditional prediction method is difficult to obtain the ideal prediction effect. The wavelet transform can remove the noise in the original signal, and the grey DGM（2, 1）model is suitable for the prediction of the time series. In this paper, the combined method of wavelet transform and grey DGM（2, 1） model is used to predict the total import and export trade of China. The ideal effect is achieved. The prediction error in 2017 is only 3.404 1%,which is 22.485 3% lower than that of the gray GM（1, 1） model, which is 46.777 1% less than that of the ordinary grey DGM（2, 1） model15.801 1%. It was predicted by the model that the total import and export trade of China was 4.378 288 trillion dollars in 2018.
作者
舒服华
Shu Fuhua(School of Mechanical and Electrical Engineering, Wuhan University of Technology, Wuhan, Hubei 430070, Chin)
出处
《保定学院学报》
2018年第3期17-23,共7页
Journal of Baoding University
