Forecasting crude palm oil price using Univariate and Box-Jenkins techniques / Nurul 'Adila Arrifin, Wan Syaniza Zainal Abidin and Mohamad Naqib Zulkarnain

In Malaysia, crude palm oil price forecasts represented fundamental and valuable
infonnation to traders who are involved directly or indirectly in the fat and oil
markets. It has been widely accepted that the price of oil is one of the reasons of the
world economy. Therefore, reliable crude oil forecasts are important for assessing
economic fluctuations and improving economic policy. In this research has used BoxJenkins
and Univariate Modelling Technique to analyse the problem of there are lack
of researchers that make studies on the accuracy between the Univariate and BoxJenkins
Techniques in forecasting the future CPO price of Malaysia with the
minimum error. Besides that, there are not much of studies using SARIMA method.
The objective of this study is to compare the model between Single Exponential
Smoothing, Double Exponential Smoothing and SARIMA model by measure the
model using Mean Squared Error (MSE), Mean Absolute Percentage Error (MAPE)
and Geometric Root Mean Squared Error (GRMSE), and also to forecast the future
crude palm oil price using the best model. The best method in this study we can
assume that Single Exponential Smoothing is the suitable method for the forecasting
the CPO prices.