A Comparative Study of Time Series Models for Forecasting Thailand’s Export Using 21 Years of Monthly Data
Keywords:
Forecasting, Time Series Analysis, Thai Export, ARIMA Model, LogisticsAbstract
Exports served as a vital engine driving Thailand’s economic growth, particularly amid heightened international financial volatility. This study aimed to analyze the long-term trends and dynamic structural patterns of Thailand’s major export commodities during 2004–2025 by classifying the statistical components of each product group to develop forecasting models that were both appropriate and accurate in supporting national export performance. The study further sought to identify forecasting models that yielded the highest levels of accuracy and statistical suitability, thereby providing strategic guidance for future supply chain and logistics planning in Thailand’s export sector. The study's population comprised monthly secondary data on the export values of 20 major Thai export commodities, purposively selected for their significant contribution to national exports, covering the period from January 2004 to April 2025. Time series analysis and model evaluation were conducted using Minitab software. Model accuracy was assessed using Mean Absolute Percentage Error (MAPE), Mean Absolute Deviation (MAD), and Root Mean Square Error (RMSE), along with the Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) for ARIMA-based models.
The results revealed that appropriate forecasting models varied according to the structural characteristics of each commodity. Commodities exhibiting clear trends were best forecasted using Double Exponential Smoothing. At the same time, those with pronounced seasonal patterns, such as rice and air conditioners, were more accurately predicted using Holt–Winters or Seasonal ARIMA (SARIMA) models. Highly volatile commodities, such as gold, continued to exhibit relatively high forecasting errors even when advanced models were applied. The study recommended developing a national-level export forecasting database to support production planning, logistics management, and the formulation of effective international trade policies.
References
ธนาคารแห่งประเทศไทย. (2567). รายงานภาวะเศรษฐกิจไทยประจำปี 2566. https://www.bot.or.th
วรางคณา เรียนสุทธิ์. (2563). การพยากรณ์ปริมาณการส่งออกยางพาราในประเทศไทย. วารสารวิจัยและส่งเสริมวิชาการเกษตร, 38(2), 130–143.
สำนักงานนโยบายและยุทธศาสตร์การค้า. (2567). รายงานแนวโน้มการส่งออกสินค้าไทย ปี 2567.
Akhter, T., Ratna, T. S., Ahmed, F., Babu, M. A., & Hossain, S. F. A. (2024). Forecasting and unveiling the impeded factors of total export of Bangladesh using nonlinear autoregressive distributed lag and machine learning algorithms. Heliyon, 10(17). https://doi.org/10.1016/ j.heliyon.2024. e36274
Aloudah, M., Alajmi, M., Sagheer, A., Algosaibi, A., Almarri, B., & Albelwi, E. (2025). AI-powered trade forecasting: A data-driven approach to Saudi Arabia’s non-oil exports. Big Data and Cognitive Computing, 9(4), 94. https://doi.org/10.3390/bdcc9040094
Alqatawna, A., Abu-Salih, B., Obeid, N., & Almiani, M. (2023). Incorporating time-series forecasting techniques to predict logistics companies’ staffing needs and order volume. Computation, 11(7), 141. https://doi.org/10.3390/computation11070141
Banditvilai, S., & Araveeporn, A. (2024). Empirical comparison of forecasting methods for air travel and export data in Thailand. Modelling, 5(4), 1395-1412. https://doi.org/10.3390/modelling5040072
Ensafi, Y., Amin, S. H., Zhang, G., & Shah, B. (2022). Time-series forecasting of seasonal items sales using machine learning: A comparative analysis. International Journal of Information Management Data Insights, 2(1), 100058. https://doi.org/10.1016/j.jjimei.2022.100058
Fatima, S. S. W., & Rahimi, A. (2024). A review of time-series forecasting algorithms for industrial manufacturing systems. Machines, 12(6), 380. https://doi.org/10.3390/machines12060380
Klaharn, K., Ngampak, R., Chudam, Y., Salvador, R., Jainonthee, C., & Punyapornwithaya, V. (2024). Analyzing and forecasting poultry meat production and export volumes in Thailand: A time series approach. Cogent Food & Agriculture, 10(1), 2378173. https://doi.org/10.1080/23311932.2024.2378173
Kontopoulou, V. I., Panagopoulos, A. D., Kakkos, I., & Matsopoulos, G. K. (2023). A review of ARIMA vs. machine learning approaches for time series forecasting in data driven networks. Future Internet, 15(8), 255. https://doi.org/10.3390/fi15080255
United Nations Conference on Trade and Development (UNCTAD). (2023). Global trade update – March 2023. https://unctad.org/webflyer/global-trade-update-march-2023
World Bank. (2023). Thailand economic monitor: Trade for growth. https://www.worldbank.org/ en/country/thailand
