Forecasting Model for the Export Volumes of Cassava

Abstract

The objective of this study was to construct the appropriate forecasting model for the export volumes of cassava. The data gathered from the website of the Office of Industrial Economics during January, 2004 to January, 2015 of 133 values were used and divided into 2 sets. The first set had 126 values from January, 2004 to June, 2014 for constructing the forecasting models by Box-Jenkins method, Winters’ multiplicative exponential smoothing method, and decomposition method. The second set had 7 values from July, 2014 to January, 2015 for comparing accuracy of the forecasts via the criteria of the lowestmean absolute percentage error and root mean squared error.Research findings indicated thatfor all forecasting methods that had been studied, the most accurate method was Winters’ multiplicative exponential smoothing method.