A novel nonlinear ensemble forecasting model incorporating GLAR and ANN for foreign exchange rates
Computers and Operations Research
Hi-index | 0.00 |
A predictor based on interacting multiple model (IMM) algorithm is proposed to forecast hourly travel time index (TTI) data in the paper. It is the first time to propose the approach to time series prediction. Seven baseline individual predictors are selected as combination components. Experimental results demonstrate that the IMM-based predictor can significantly outperform the other predictors and provide a large improvement in stability and robustness. This reveals that the approach is practically promising in traffic forecasting.