TITLE:
Building the ARIMA Model for Forecasting the Production of Vietnam’s Coffee Export
AUTHORS:
Duy Quang Phung, Quoc Thang Trinh, Quang Truong Do, Ngan Giang Nguyen, Van Ha Nguyen, Gia Khiem Ngo, Thi Minh Ngoc Tran
KEYWORDS:
ARIMA, Forecasting, Coffee Export Volume, Data Science
JOURNAL NAME:
Journal of Applied Mathematics and Physics,
Vol.12 No.4,
April
28,
2024
ABSTRACT: Coffee is a significant industry, accounting for 3% of Vietnam’s GDP, with annual export turnover consistently exceeding USD 3 billion. Despite global economic challenges affecting purchasing power at various times, Vietnam’s coffee exports in December 2023 continued to surge, reaching the highest level in the past 9 months at 190,000 tons, a 59.3% increase compared to November 2023, but still a slight 3.5% decrease from the same period last year. The export turnover reached USD 538 million, a 51% increase from November 2023 and a 26.4% increase from the same period last year. Therefore, forecasting the coffee export volume holds significant importance for coffee producers nationwide. This research employs the Box-Jenkins method to construct an ARIMA model for forecasting Vietnam’s coffee export volume based on annual data published by the General Statistics Office. Results indicate that among the models considered, the ARIMA(1, 1, 2) model is the most suitable. The study also provides short-term forecasts for Vietnam’s coffee export volume. However, the current model is limited to forecasting and is not yet optimized, as the assumed linearity in the model is a simplification.