Forecasting the export quantity of frozen and chilled chicken

Abstract

The purpose of this research was to construct an appropriate forecasting model for the export quantity of frozen and chilled chicken using three time series analysis methods, including Box-Jenkins method, Holt’s exponential smoothing method, and damped trend exponential smoothing method. Time series data from the website of the Office of Industrial Economics with total 130 months during January, 2004 to October, 2014 were used and they were divided into two series. Fristly, 120 months from January, 2004 to December, 2013 were used to build the forecasting models and lastly, 10 months from January until October, 2014 were used to compare the forecasting methods accuracies via the criteria of the lowest mean absolute percentage error and root mean squared error. Research findings indicated that all forecasting methods that had been studied, damped trend exponential smoothing method were the most accurate method and showed the forecasting model as where m represented the number of periods to forecast ahead with the starting value was January 2014 (m = 1).