Research and Application of Urban Logistics Demand Forecast Based on Radial Basic Function Neural Network

Considering the issues that the urban logistics system was an uncertain, nonlinear, dynamic and complicated system, and it was difficult to describe it by traditional methods, an urban logistics demand forecast method based on radial basic function neural network (RBFNN) is presented in this paper. We construct the structure of RBFNN that used for forecasting urban logistics demand, and adopt the K-Nearest Neighbor algorithm and least square method to train the network. The main parameters of affecting urban logistics demand are studied. With the ability of strong function approach and fast convergence of radial basic function neural network, the forecast method can truly forecast the urban logistics demand by learning the index information of affect urban logistics demand. The actual forecasting results show that this method is feasible and effective.