Forecasting Short-Term Export Volumes with Hybrid Models Integrating SARIMA with Attention-Based LSTM

Wenhao WangDepartment of Trade and Logistics, Daegu Catholic University, Gyeongsan, Daegu, Republic of KoreaAuthorhttps://orcid.org/0009-0000-7141-2545
Siyi ShenDepartment of Trade and Logistics, Daegu Catholic University, Gyeongsan, Daegu, Republic of KoreaAuthorhttps://orcid.org/0009-0008-3295-9896
Ye YuanDepartment of Trade and Logistics, Daegu Catholic University, Gyeongsan, Daegu, Republic of KoreaAuthorhttps://orcid.org/0009-0009-4920-5393

DOI:

Keywords:

Short term export volume forecast, Time series analysis, SARIMA, Attention mechanism, Mixed forecasting model

Abstract

The short-term export volume forecast is of great significance for international trade decision-making and macroeconomic regulation, but the time series of export volume usually contains significant seasonal, trend and nonlinear fluctuation characteristics at the same time, so it is difficult to obtain ideal results with a single forecast model. In order to improve the prediction accuracy and stability, this paper proposes a hybrid prediction method combining seasonal autoregressive moving average model (SARIMA) and attention based memory network (attention based LSTM). Firstly, SARIMA model is used to describe the linear structure and seasonal components in the export volume series, and its prediction residual is modeled; Then, the attention LSTM is used to learn the nonlinear dynamic characteristics in the residual sequence, and finally the prediction results are obtained by additive fusion. The experimental results based on the monthly export volume data of Poland show that compared with the traditional SARIMA, LSTM and other comparative models, the MAE, RMSE and MAPE of the SARIMA-Attention-LSTM (Proposed) on the test set are reduced, on average, by about 20%–35%, respectively. The prediction residual fluctuation converges significantly, and shows better stability and generalization ability in repeated experiments. The results show that the effective integration of statistical model and deep learning model can significantly improve the short-term export forecasting performance, and provide a feasible and efficient solution for the prediction of complex economic time series.

References

[1] Kashpruk, N., Piskor-Ignatowicz, C., & Baranowski, J. (2023). Time series prediction in industry 4.0: A comprehensive review and prospects for future advancements. Applied sciences, 13(22), 12374. DOI: https://doi.org/10.3390/app132212374

[2] Quang, P. D., & Thang, T. Q. (2025). Analysis and forecasting of daily global gold price: an SARIMA-LSTM approach with Random Forest technique. Cogent Economics & Finance, 13(1), 2568969. DOI: https://doi.org/10.6084/m9.figshare.30329180

[3] Ghadami, A., & Epureanu, B. I. (2022). Data-driven prediction in dynamical systems: recent developments. Philosophical Transactions of the Royal Society A, 380(2229), 20210213. DOI: https://doi.org/10.1098/rsta.2021.0213

[4] Slater, L., Arnal, L., Boucher, M. A., Chang, A. Y. Y., Moulds, S., Murphy, C., ... & Zappa, M. (2022). Hybrid forecasting: using statistics and machine learning to integrate predictions from dynamical models. Hydrology and Earth System Sciences Discussions, 2022, 1-35. DOI: https://doi.org/10.5194/hess-27-1865-2023

[5] Ahmed, S. F., Alam, M. S. B., Hassan, M., Rozbu, M. R., Ishtiak, T., Rafa, N., ... & Gandomi, A. H. (2023). Deep learning modelling techniques: current progress, applications, advantages, and challenges. Artificial Intelligence Review, 56(11), 13521-13617. DOI: https://doi.org/10.1007/s10462-023-10466-8

[6] Wu, Z., Rincon, D., Gu, Q., & Christofides, P. D. (2021). Statistical machine learning in model predictive control of nonlinear processes. Mathematics, 9(16), 1912. DOI: https://doi.org/10.3390/math9161912

[7] Gettelman, A., Geer, A. J., Forbes, R. M., Carmichael, G. R., Feingold, G., Posselt, D. J., ... & Zuidema, P. (2022). The future of Earth system prediction: Advances in model-data fusion. Science Advances, 8(14), eabn3488. DOI: https://doi.org/10.1126/sciadv.abn3488

[8] Sham, F. A. F., El-Shafie, A., Jaafar, W. Z. W., Sherif, M., & Ahmed, A. N. (2025). Advances in AI-based rainfall forecasting: A comprehensive review of past, present, and future directions with intelligent data fusion and climate change models. Results in Engineering, 27, 105774. DOI: https://doi.org/10.1016/j.rineng.2025.105774

[9] Sharma, P., Rohatgi, S., & Jasuja, D. (2023). Scientific mapping of gravity model of international trade literature: A bibliometric analysis. Journal of Scientometric Research, 11(3), 447-457. DOI: https://doi.org/10.5530/jscires.11.3.48

[10] Xue, R., Li, K., Wang, F., & Baron, C. (2024). Research progress and hot-spot analysis of the economic complexity research based on Citespace. Advances in Management and Applied Economics, 14(1), 1-10. DOI: https://doi.org/10.47260/amae%2F14110

[11] Istaiteyeh, R., Najem, F., & Saqfalhait, N. (2023). Exports-and imports-led growth: Evidence from a time series analysis, case of Jordan. Economies, 11(5), 135. DOI: https://doi.org/10.3390/economies11050135

[12] Jetwiriyanon, J., Susnjak, T., & Ranathunga, S. (2025). Generalisation Bounds of Zero-Shot Economic Forecasting using Time Series Foundation Models. Machine Learning and Knowledge Extraction, 7(4), 135. DOI: https://doi.org/10.3390/make7040135

[13] Dubey, A. K., Kumar, A., García-Díaz, V., Sharma, A. K., & Kanhaiya, K. (2021). Study and analysis of SARIMA and LSTM in forecasting time series data. Sustainable Energy Technologies and Assessments, 47, 101474. DOI: https://doi.org/10.1016/J.SETA.2021.101474

[14] Sirisha, U. M., Belavagi, M. C., & Attigeri, G. (2022). Profit prediction using ARIMA, SARIMA and LSTM models in time series forecasting: A comparison. Ieee Access, 10, 124715-124727. DOI: https://doi.org/10.1109/ACCESS.2022.3224938

[15] He, K., Ji, L., Wu, C. W. D., & Tso, K. F. G. (2021). Using SARIMA–CNN–LSTM approach to forecast daily tourism demand. Journal of Hospitality and Tourism Management, 49, 25-33. DOI: https://doi.org/10.1016/j.jhtm.2021.08.022

[16] Insaad, T., & Sribunrueang, P. (2025). A SARIMA-Based Time Series Analysis of Sugar Export Quantity and Price Trends in Thailand. Journal of Business, Innovation and Sustainability (JBIS), 20(2), 111-128. DOI: https://doi.org/10.71185/jbis.2025.277638

[17] Gonzales Martinez, R. (2024). Apocalypse unleashed: a critical perspective on complexity science, catastrophes, and black swan events in international business. Critical perspectives on international business, 20(1), 94-120. DOI: https://doi.org/10.1108/cpoib-03-2022-0014

[18] Alizadegan, H., Rashidi Malki, B., Radmehr, A., Karimi, H., & Ilani, M. A. (2025). Comparative study of long short-term memory (LSTM), bidirectional LSTM, and traditional machine learning approaches for energy consumption prediction. Energy Exploration & Exploitation, 43(1), 281-301. DOI: https://doi.org/10.1177/01445987241269496

[19] Alzara, M., Gihad, N., Abdou, H., Soltan, A., Hilal, A., & Ehab, A. (2025). Macroeconomic-aware forecasting of construction costs in developing countries: Using gated recurrent unit and long short-term memory deep learning framework. PLoS One, 20(10), e0333189. DOI: https://doi.org/10.1371/journal.pone.0333189

[20] Al-Selwi, S. M., Hassan, M. F., Abdulkadir, S. J., & Muneer, A. (2023). LSTM inefficiency in long-term dependencies regression problems. Journal of Advanced Research in Applied Sciences and Engineering Technology, 30(3), 16-31. DOI: https://doi.org/10.37934/araset.30.3.1631

[21] Hajirahimi, Z., & Khashei, M. (2023). Hybridization of hybrid structures for time series forecasting: A review. Artificial Intelligence Review, 56(2), 1201-1261. DOI: https://doi.org/10.1007/s10462-022-10199-0

[22] Alharbi, F. R., & Csala, D. (2022). A seasonal autoregressive integrated moving average with exogenous factors (SARIMAX) forecasting model-based time series approach. Inventions, 7(4), 94. DOI: https://doi.org/10.3390/inventions7040094

[23] Xu, B., Wang, Y., Yuan, L., & Xu, C. (2023). A novel second-order learning algorithm based attention-LSTM model for dynamic chemical process modeling. Applied Intelligence, 53(2), 1619-1639. DOI: https://doi.org/10.1007/s10489-022-03515-2

[24] Wen, X., & Li, W. (2023). Time series prediction based on LSTM-attention-LSTM model. IEEE access, 11, 48322-48331. DOI: https://doi.org/10.1109/ACCESS.2023.3276628

[25] Zhao, T., Chen, G., Pang, C., & Busababodhin, P. (2025). Application and Performance Optimization of SLHS-TCN-XGBoost Model in Power Demand Forecasting. CMES-Computer Modeling in Engineering and Sciences, 143(3), 2883-2917. DOI: https://doi.org/10.32604/cmes.2025.066442

[26] Zhao, T., Chen, G., Suraphee, S., Phoophiwfa, T., & Busababodhin, P. (2025). A hybrid TCN-XGBoost model for agricultural product market price forecasting. PLoS One, 20(5), e0322496. DOI: https://doi.org/10.1371/journal.pone.0322496

Downloads

PDF Download

Published

2026-01-02 — Updated on 2026-01-02

Data Availability Statement

The data that support the findings of this study are available upon request from the corresponding authors, W.W.

Issue

Volume. 4, No. 1 (March 2026)

Section

Research Article

License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

This work is licensed under the Creative Commons Attribution International License (CC BY 4.0).

How to Cite

Forecasting Short-Term Export Volumes with Hybrid Models Integrating SARIMA with Attention-Based LSTM. (2026). International Scientific Technical and Economic Research , 1-22. https://doi.org/10.71451/ISTAER2601