Abstract
Time deposits or often referred to as deposits are deposits that take it in accordance with the time agreed. The position of time deposits in commercial banks and BPRs is monitored by Bank Indonesia, Because large time deposits affect the level of the economy in Indonesia, one of them to facilitate public credit in an opening and building businesses. However, in the course of this term deposit data position is influenced by many other factors that resulted in the existence of the data of this condition leads to the assumption of normality becomes unfulfilled. Some methods that can be used to overcome this problem include ARIMA Box-Jenkins with outliers detection and Bootstrapping ARIMA. In this case, the data is public time deposits at commercial banks and BPR from January 2010 to April 2016. The best ARIMA model is ARIMA (1,1,0), With the best method is ARIMA Bootstrap because it has MAPE value (out sample) of 4.8257% less than MAPE value’s ARIMA with outliers detection which it has 6.1610%. Based on these results it is concluded that in this case the nonparametric method is more appropriate to be used by ignoring the distribution assumption. Keywords : Deposits, ARIMA, Outliers detection, Bootstrap ARIMA
Paper version not known (
Free)
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call