A Comparison of Forecasting Models for Kraft Paper Production Volume

Abstract

The purpose of this research is to create a suitable forecasting model of kraft paper production volume. The data is gathered from the website of the Office of Industrial Economics during January 2016 to October 2021 amount 70 values and was divided into two sets of categories. The first category has 60 values which are Quantity of Kraft Paper production volume data during January 2016 to December 2021. The second category has 10 values which are quantity of kraft paper production volume data during January 2021 to October 2021. The first category use to construct the forecasting model with Holt's exponential smoothing, Brown's exponential smoothing, and the Box-Jenkins method. The second category for checking the accuracy of the forecasting models via the criterion of the lowest mean absolute percentage error. The results showed that the Box-Jenkins forecasting model is most suitable for this time series and the forecast model was ARIMA(1,1,0) with no constant term.