Short Term Traffic Flow Prediction Using Hybrid ARIMA and ANN Models

According to the complexity of the traffic historical data and the randomness of a lot of uncertain factors influence, a hybrid predicting model that combines both autoregressive integrated moving average (ARIMA) and multilayer artificial neural network (MLANN) is proposed in this paper. ARIMA is suitable for linear prediction and MLFNN is suitable for nonlinear prediction. This paper also investigates the issue on how to effectively model short term traffic flow time series with a new algorithm, which estimates the weights of the MLFNN and the parameters of ARMA model. Experimental results with real data sets indicate that the combined model can be an effective way to improve forecasting accuracy achieved by either of the models used separately.