Forecasting of Thai International Imports and Exports Using Holt-Winters’ and Autoregressive Integrated Moving Average Models

Pianpool Kamoljitprapa; Orathai Polsen; Umar Kabir Abdullahi

Authors

Pianpool Kamoljitprapa Department of Applied Statistics, Faculty of Applied Science, King Mongkut’s University of Technology North Bangkok
Orathai Polsen Department of Applied Statistics, Faculty of Applied Science, King Mongkut’s University of Technology North Bangkok
Umar Kabir Abdullahi Department of Statistics, Ahmadu Bello University

Keywords:

Imports, Exports, ARIMA model, Holt-Winters’model, Seasonal, Forecasting

Abstract

Imports and exports are two vital issues of the Thai economy, which were ranked as the 23rd largest economy in the world in 2020. This research aimed to examine the monthly import and export volume trends (in million Baht) from January, 2010 to December, 2022. To conduct the analysis, the research employed Holt-Winters’ additive and multiplicative models, as well as various seasonal ARIMA models. The models were evaluated using different selection measure criteria, and the results indicated that the Holt-Winters’ multiplicative forecasting model was optimal for predicting both import and export volumes, as it produced the least mean absolute error (MAE) and root mean square error (RMSE). Therefore, it is recommended for future Thai imports and exports forecasts. However, it is notable that the COVID-19 pandemic had a significant impact on the country's imports and exports during the 2019-2020 period.

References

Benvenuto,D., Giovanetti,M., Vassallo,L., Angeletti, S.,& Ciccozzi,M.(2020).Application of the ARIMA model on the COVID-2019 epidemic dataset.Data in Brief, 29,105340.

Box, G. E. P.,& Jenkins,G. M.(1976).Time series analysis: forecasting and control.San Francisco, CA: Holden-Day.

Chatfield, C., & Yar, M.(2014). Holt-Winters forecasting: some practical issues.Journal of the Royal Statistical Society: Series D (The Statistician), 34(2-3), 215-225.

Fattah, J., Ezzine, L., Aman, Z., El Moussami, H., & Lachhab, A.(2018).Forecasting of demand using ARIMA model.International Journal of Engineering Business Management, 10,1–9.https://doi.org/10.1177/1847979018808673

Hyndman,R. J.,& Athanasopoulos G.(2021).Forecasting: Principles and Practice(3rded.).https://otexts.com/fpp3/decomposition.html

Kamoljitprapa, P.,& Sookkhee, S.(2022).Forecasting Models for Carbon Dioxide Emissions in Major Economic Sectors of Thailand.Journal of Physics: Conference Series 2346, 012001.

Kaur, P.,& Rakshit, M.(2019).Seasonal and Periodic Autoregressive Time Series Models Used for Forecasting Analysis of Rainfall Data.International Journal of Advanced Research in Engineering and Technology, 10(1),230-242.

Ministry of Energy. (2021).Thailand's energy situation. https://www.energy.go.th /en/energy-situation/energy-situation-in-thailand/

Mladenović,J., Lepojević,V.,& Janković-MilićV.(2016).Modelling and Prognosis of the Export of The Republic of Serbia by using Seasonal Holt-Winters and ARIMA Method.Economic Themes, 54(2),233-260.

Nieto,M. R., Carmona-Benitez,R. B.,&Martinez,J. N.(2021)Comparing models toforecast cargo volume at port terminals.Journal of Applied Research and Technology, 19(3),238-249.

OECD. (2017).Economic survey of Thailand 2017. https://www.oecd.org/ economy/surveys/economic-survey-thailand.htm

Office of the Permanent Secretary. (2023). Ministry of Commerce.https:// tradereport.moc.go.th/Report/ReportEng.aspx?Report=TradeEnBalanceYearly

Oghenekevwe, O. A., & Mercy, O. O.(2021). Forecasting Export and Import Performance in the Agricultural Sector of Nigeria Using ARIMA Models.International Journal of Agricultural and Biological Engineering, 14(4), 145-152.

Panday, P. K., & Dhakal, R.(2020). ForecastingExports and Imports of Nepal’s Agricultural Sector: A Comparison of ARIMA, ANN and ETS Models.International Journal of Applied Sciences and Biotechnology, 8(1), 15-20.

Trade Policy and Strategy office. (2022).Ministryof Commerce. https://www.tpso.moc.go.th /th/node/12413

Winters,P. R. (1960). Forecasting Sales byExponentially Weighted Moving Averages.ManagementScience, 6(3), 324-342.

Wongoutong,C.(2021).The Effect of Forecasting Accuracy of the Holt-WinterMethod When Using the Incorrect Model on a Non-Stationary Time Series.Thailand Statistician, 19(3),565-582.

World,Bank. (2022). World development indicators.https://databank.worldbank.org/source/world-development-indicators