Application of box Jenkin’s and single exponential smoothing in forecasting of export cocoa production / Nor Anith Dayana Sakri, Wan Nor Shilawati Wan Mamat and Nurul Ashhadah Amirah Roslan

Cocoa has an important role in the export sector for production plantation in Malaysia. The
cocoa production can maintain their strategic management by making the forecast for
export of cocoa production within a certain period. It is compulsory to study the pattern of
export cocoa production in the future. This report reviews the export of cocoa production in
Malaysia over 3 7 years starting from the year 1980 to the year 2016. Secondary time series
data were used which obtained from the Division of Statistic Malaysia. There are two
models that have been used in the study, namely the Autoregressive Integrated Moving
Average (ARIMA) and Single Exponential Smoothing Model. This model is comparable to
Mean Squared Error (MSE), Mean Absolute Percentage Error (MAPE) and Root Mean
Squared Error (RMSE) to get the best model. Akaike' Information Criteria (AIC), Schwarz
Criteria (BIC), Durbin Watson, Adjusted R-squared and R-squared are taken in diagnostic
test statistics for the Autoregressive Moving Average (ARIMA) model. Single Exponential
Smoothing model were tested by using Microsoft Excel and the criteria of Mean Squared
Error (MSE) emphasize the lowest value that will be chosen as the best model. Based on
the results, the Autoregressive Integrated Moving Average (ARIMA) model was selected
as the appropriate model for forecasting the export of cocoa production.