I am trying to forecast month end balances of the TOTAL portfolio using PROC ARIMA procedure. INside the portfolio there are 3 major product segments A, B and C. Each of which has a separate trend and seasonality as shown below in the graph
I wanted to try two methods,
method 1: Forecast of the TOTAL portfolio balance using PROC ARIMA (univariate)
method 2: Forecast of the TOTAL portfolio balance using PROC ARIMA (multi variate) using segment A, B and C BALANCES as input variables
Need help in forecasting the portoflio balance with multiple input variables, like average term , average interest rate, prepayments etc..
Which procedure can I use to achieve this?
Method 1 works fine but with method 2 I am getting these warnings
More values of input variable A are needed
More values of input variable B are needed
More values of input variable C are needed
METHOD 1:
proc arima data=upb_2 plots=all;
identify var=UPB(1,12) noprint;
estimate noconstant method=ml;
forecast lead=17 interval=month id=RPT_PRD_DATE out=outf;
run;
METHOD 2:
proc arima data=UPB_INDUSTRY_2 plots=all;
identify var=TOTAL(1,12) noprint crosscorr=(A B C);
estimate input=(A B C) noconstant method=ml;
forecast lead=17 interval=month id=RPT_PRD_DATE_2 out=outf_input;
run;