A BP neural network model for the demand forecasting of road freight transportation system

To address the prediction problem of road freight transport demand, this paper firstly establishes preliminary forecasting indicators, analyses them using grey relational analysis methods and predicts freight volumes by taking advantage of the non-linear mapping of BP neural networks. The prediction results are eventually compared with the exponential smoothing method and the GM(1,1) method. The study find that the GRA-BPNN-based prediction has ideal prediction results, with higher accuracy and more stable prediction.