Towards investigation of iterative strategy for data mining of short-term traffic flow with Recurrent Neural Networks

The smart cities of modern nations rely on the smooth flow of transportation that depends on the predictions of the traffic flow patterns. Since last few years, deep learning based methods have emerged to show better results for short-term traffic flow prediction. For multi-step-ahead prediction, researchers applying statistical methods have used the iterative strategies for preparing input data and building forecast models. In studies applying recurrent neural networks (RNN), the iterative strategies are not used. Hence, we investigate the usage of an iterative strategy for building the RNN models for short-term traffic flow forecasting.