Freight volume forecasting based on a decompose–ensemble method Available to Purchase

Logistics freight volume forecasting plays a crucial role in the formulation of a rational planning strategy for a country. To improve forecasting accuracy, a novel multilevel decompose–ensemble method based on trend and wavelet decomposition combined with a linear regression model (LR) and an auto regression model (AR) is proposed in this study. First, the original data are resolved into trend and non-trend subseries by trend transform. Then, non-trend subseries are further broken down into one approximation subseries and several detailed subseries by wavelet transform. With respect to their different dynamically changing features and influencing factors, trend subseries are forecast by LR and non-trend subseries are, respectively, forecast by AR. The final prediction results are the summation of these subseries predictions. Forecasting results prove that the complex forecasting problem has been decomposed into some simple problems based on this multilevel decompose–ensemble method, which can improve prediction accuracy, when compared with individual models, the traditional decompose–ensemble method and a combination model. Consequently, the proposed method is a feasible forecasting approach for freight volume. According to this multilevel decompose–ensemble forecasting method combined with LR and AR, China's logistics freight volume in 2017 will increase to 69 010·16 million metric tonnes, and the average annual growth for the coming 5 years is 10·9%.