FORECASTING OF PERCENTAGE TIME THAT PARTS FOR INDUSTRIAL PROJECTS IN AUSTRALIA

This paper endeavors to study the Australia percentage time that parts for industrial projects available when needed. Box-Jenkins methodology is used to forecast next 20 observations. To apply Box-Jenkins methodology data should be stationary and unit root test is used to check stationarity of data. It is found that a minor trend is found in data set and to remove trend 1st difference is applied which makes the data stationary. For model identification ACF and PACF are plotted. Furthermore, using Box-Jenkins methodology best model is selected on the basis of smaller AIC, SBC and MSE. Since, ARIMA (0,1,1) has the lowest value of AIC, SBC and MSE. So, this model is recommended as best for forecasting. In addition, to check the accuracy of forcasted values MAPE, MAE, RMSE are also computed. It can be concluded that the percentage time that parts for industrial projects in Australia will increase gradually.