Hybrid Support Vector Machine and ARIMA Model for Short-Term Traffic Flow Forecasting

The autoregressive integrated moving average (ARIMA) model has been one of the most widely used linear models in short-term traffic flow forecasting. However, the ARIMA model cannot easily capture the nonlinear patterns whereas Support vector machines (SVMs) have been successfully applied in solving nonlinear regression estimation problems. Therefore, this investigation proposes a hybrid methodology that exploits the unique strength of the ARIMA model and the SVMs model in short-term traffic flow forecasting problems. Real data sets of traffic flow were used to examine the forecasting accuracy of the proposed model. The results of computational tests are very promising.