Forecasting RON97 fuel prices in Malaysia using the Box-Jenkins methodology

Abstract

Forecasting RON97 fuel prices is essential for economic planning and policy-making, as they influence transportation costs and the inflation rate. This study uses the Box-Jenkins method to develop a forecasting model for Malaysia's future four-week RON97 fuel price. The data was collected from Malaysia's official open data portal, covering the weekly period from March 30, 2017, to July 25, 2024. The R programming language was used for in-depth data analysis and model development. Using an 80:20 training–testing split, with residual adequacy assessed through the Ljung–Box test and forecasting accuracy evaluated using the Mean Absolute Percentage Error (MAPE), the ARIMA (2,1,0) model was identified as the most appropriate forecasting model. The model achieved an MAPE of 0.13%, indicating excellent predictive accuracy. The findings indicate that RON97 prices are forecast to remain relatively stable over the next four weeks. The findings provide valuable insights for policymakers and stakeholders in the energy sector, enabling more informed decision-making and strategic planning.