
The comparison of VAPE is confirmed in Tables 4, 5, 8, and 9. It may be seen that among the total 76 (in/outflow at 19 stations on weekdays and weekends) forecasts, the proposed mixed model outperforms others in forty seven forecasts. The approach adopts two forecasts as basic models and then uses a probabilistic model choice technique, random forest classification, to mix the 2 outputs to achieve a greater forecast. Two primary forecasts are obtained...