Proceedings of TUSUR University / Archive / Issue of Journal № 4, t. 28, 2025 / Developing a hybrid model for forecasting transportation demand based on SARIMA and XGBoost intelligent methods

Developing a hybrid model for forecasting transportation demand based on SARIMA and XGBoost intelligent methods

DOI: 10.21293/1818-0442-2025-28-4-127-135

Download article in PDF format

JATS xml

Abstract: Forecasting demand for road freight transportation is a highly complex task due to the nonlinear dynamics of time series, pro-nounced seasonality and the influence of other exogenous fac-tors. Traditional statistical time series models effectively iden-tify autocorrelation structures and seasonal patterns; however, they do not always show satisfactory results when modeling nonlinear dependencies. Machine learning algorithms, in con-trast, successfully identify hidden patterns in multidimensional data, but require significant amounts of training samples and demonstrate instability during extrapolation. Based on the above, the aim of this study is to develop a hybrid model for forecasting transportation demand that combines the ad-vantages of statistical and algorithmic approaches. The meth-odology is based on the sequential integration of SARIMA to isolate the temporal data structure and XGBoost to model resid-ual variation, taking into account the constructed set of features (time, lag variables, aggregated statistics). The empirical base consists of data from the digital cargo transportation platform for the period January 2024 to December 2025, including about 10,000 daily observations. On the author's test sample (Octo-ber–December 2025), the hybrid model proved to be more ac-curate than isolated SARIMA, XGBoost and Random Forest across all metrics: the average absolute percentage error was 5.21% with R2 = 0.928, which is 38.1% lower than SARIMA and 11.2% lower than XGBoost. Among the predictors, it was found that weekly seasonality and medium-term trends contrib-ute the most to the model's predictive ability. The results are applicable for optimizing the planning of transport capacities and route networks by logistics platform operators.

Keywords: demand forecasting, cargo transportation, hybrid model, SARIMA, XGBoost, time series, machine learning

For citation:
Bokarev D. V. Developing a hybrid model for forecasting transportation demand based on SARIMA and XGBoost intelligent methods. Doklady Tomskogo gosudarstvennogo universiteta sistem upravleniya i radioelektroniki, 2025, vol. 28, no. 4, pp. 127–135. DOI: 10.21293/1818-0442-2025-28-4-127-135

Authors and copyright holders:

Bokarev D. V. , Russian Presidential Academy of National Economy and Public Administration (Moscow, Russia)

1. Transport v Rossii [Transport in Russia]. 2024. Statistical handbook. Rosstat. Moscow, 2024, 100 p. (in Russ.).
2. Rodrigue J.-P. The Geography of Transport Systems. 5th ed. New York, Routledge, 2020, 456 p.
3. Litvinov A.V., Donchenko V.V. [Estimation of elasticities of travel demand based on urban travel mode choice models]. International Journal of Advanced Studies, 2020, vol. 10, no. 4, pp. 40–57. DOI: 10.12731/2227-930X-2020-4-40-57 (in Russ.).
4. Karlaftis M.G., Vlahogianni E.I. Statistical methods versus neural networks in transportation research: Differences, similarities and some insights. Transportation Research Part C: Emerging Technologies, 2011, vol. 19, no. 3, pp. 387–399. DOI: 10.1016/j.trc.2010.10.004.
5. Malovetskaya E.V., Mozalevskaya A.K. [Possibilities of Application of ARIMA models in building forecasting values of car-flows]. T-Comm, 2023, vol. 17, no. 1, pp. 33–41. DOI: 10.36724/2072-8735-2023-17-1-33-41 (in Russ.).
6. Dong H., Jia L., Sun X., Li C., Qin Y. Road traffic flow prediction with a time-oriented ARIMA model. Proceedings of the Fifth International Joint Conference on INC, IMS and IDC. Seoul, Korea, IEEE, 2009, pp. 1649–1652. DOI: 10.1109/NCM.2009.224.
7. Mrówczyńska B., Cieśla M., Król A., Sładkowski A. Application of artificial intelligence in prediction of road freight transportation. PROMET – Traffic & Transportation, 2017, vol. 29, no. 4, pp. 363–370. DOI: 10.7307/ptt.v29i4.2227.
8. Agafonov A.A., Myasnikov V.V. An algorithm for traffic flow parameters estimation and prediction using composition of machine learning methods and time series models. Computer Optics, 2014, vol. 38, pp. 539–549. DOI: 10.18287/0134-2452-2014-38-3-539-549.
9. Mohsen B., Mohsen M. An AI-driven framework for forecasting freight demand: Integrating the transportation services index with energy and modal indicators. SSRN Electronic Journal, 2025. DOI: 10.2139/ssrn.5352403.
10. Chen T., Guestrin C. XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, USA, ACM, 2016, pp. 785–794. DOI: 10.1145/2939672.2939785.
11. Semanjski I., Lopez A., Gautama S. Forecasting transport mode use with support vector machines based approach. Transactions on Maritime Science, 2016, vol. 5, pp. 111–120. DOI: 10.7225/toms.v05.n02.002.
12. Yuan F., Fan Y., Bing X., Tian Z., Yuan Ch., Li Y. Traffic flow forecasting: STL decomposition and hybrid models. arXiv preprint, 2025, arXiv:2510.23668.
13. Khan N., Hanbali A. Machine learning approaches for disaggregated and intermittent demand forecasting for last-mile logistics. Transportation Research Procedia, 2025, vol. 84, pp. 307–314. DOI: 10.1016/j.trpro.2025.03.077.
14. Salais-Fierro T.E., Martínez J.A.S. Demand forecasting for freight transport applying machine learning into the logistic distribution. Mobile Networks and Applications, 2022, vol. 27, pp. 2172–2181. DOI: 10.1007/s11036-021-01854-x.
15. Thejovathi M. et al. Optimizing product demand forecasting with hybrid machine learning and time series models. SSRN Electronic Journal, 2024. DOI: 10.2139/ssrn.5076161.
16. Ajiboye A.O. Hybrid modeling for sales prediction using SARIMA, CNN, LSTM, and stacking ensemble. International Journal of Computer (IJC), 2024, vol. 53, no. 1, pp. 114–149.
17. Tsolaki K., Vafeiadis T., Nizamis A., Ioannidis D., Tzovaras D. Utilizing machine learning on freight transportation and logistics applications: A review. ICT Express, 2022, vol. 9. DOI: 10.1016/j.icte.2022.02.001.
18. Sonnleitner B., Kourentzes N., Ehrig C., Pflaum A. Forecasting for optimization in road freight transport: A review. Transportation Research Part E: Logistics and Transportation Review, 2025, vol. 204, pp. 104378. DOI: 10.1016/j.tre.2025.104378.