Forecasting a logistic service demand based on neural network

Forecasting facilitates cutting down operational and management costs while ensuring service level for a logistics service provider. Our case study here is to investigate how to forecast logistic demand for a LTL carrier. First only time series forecasting is employed as no suitable explanatory indicators can be found for the regression approach. Among the times series forecasting methods, NN is adopted considering its feasibility and applicability. The simulation results verified its advantage over other two conventional time series approaches. The work done in the paper helps manager to select prediction method in practice.