Welcome to Francis Academic Press

Academic Journal of Computing & Information Science, 2023, 6(8); doi: 10.25236/AJCIS.2023.060817.

Research on Logistics Cargo Volume Forecasting Based on SETAR Model


Xingguo Xu1, Qiaojun Chen2, Yiqiang Xia1

Corresponding Author:
Xingguo Xu

1College of Science, Liaoning Technical University, Fuxin, Liaoning, 123000, China

2College of Safety, Liaoning Technical University, Huludao, Liaoning, 125000, China


With the rapid development of e-commerce platforms, logistics networks have ushered in new challenges. In order to predict the cargo volume of logistics routes over a period of time, this paper takes a transportation network as an example, and calibrates three routes as observation points based on the cargo volume of historical logistics routes. Selects a SETAR model with more time considerations than time series, establishes an AR model in each subinterval by setting the upper limit of the number of model orders, delay steps and the number of thresholds, and then changes the threshold value to select the optimal threshold value is selected by the AIC criterion. Then the number of delay steps is changed and the procedure is repeated to achieve the optimal prediction result. Finally, the prediction results of cargo transportation volume of the three routes are obtained. This study is important for the rational arrangement of logistics transportation resources.


SETAR Model, Logistics Cargo Volume, AR Model

Cite This Paper

Xingguo Xu, Qiaojun Chen, Yiqiang Xia. Research on Logistics Cargo Volume Forecasting Based on SETAR Model. Academic Journal of Computing & Information Science (2023), Vol. 6, Issue 8: 138-145. https://doi.org/10.25236/AJCIS.2023.060817.


[1] Yang H-M, Pan Z-Song, Bai Wei. A review of time series forecasting methods[J]. Computer Science, 2019, 46(01):21-28.

[2] Wang X, Wu J, Liu Chao, Yang H-Y, Du Y-L, Niu W-S. Fault time series prediction based on LSTM recurrent neural network [J]. Journal of Beijing University of Aeronautics and Astronautics, 2018, 44(04):772-784.

[3] Ruohui Zhang. A study of SSE Composite Index returns based on ARMA-GARCH model [J]. China Market, 2023(13): 43-46.

[4] Geng H, Wang W, Xing Chengbin. Research on tide level fitting and interpolation based on ARMA model [J]. Marine mapping, 2021, 41(05):17-20+25.

[5] Huang Shuiren, Liu Yuji, Hu J. Construction of robust ARMA residual control charts and their application in financial markets [J]. Mathematical Theory andApplications, 2022, 42(01):117- 129.

[6] Zhang Chen. A test of reversal and inertia effects in the Chinese stock market [D]. Northeast Normal University, 2016.

[7] Yu-Ping Y. Research on urban logistics demand forecasting based on the BP neural network method[J].Journal of Qinghai Normal University(Natural Science Edition), 2017.

[8] Chen Le, Prediction of plunger pump leakage based on time-series method [D]. Lanzhou University of Technology, 2022.

[9] W. J. Shi, L. S. Hu. Performance estimation of a class of nonlinear systems basedon SETAR model [J]. Control Engineering, 2010, 17(S2):97100.

[10] Wei J. Y. Research on the application of cross-period arbitrage of stock indexfutures based on GARCH-GED and SETAR models [D]. Henan University of Economics and Law, 2021.