Analysis of possibility of using neural network to forecast passenger traffic flows in Russia
At present the problem of forecasting passenger transport demand is of immense importance for air transport producers as well as for investors since investment efficiency is greatly affected by the accuracy and adequacy of the estimation performed. The aim of the present research is to analyze the possibility of using a neural network approach to forecast the expansion of the air-transport network in Russia. The neural network model that has been developed to forecast passenger traffic flows includes 28 time-lagged feed-forward artificial neural networks. The number of the neural networks corresponds to the forecasted number of intraregional and interregional passenger traffic. The relative forecasting error for these neural networks at the adaptation stage is less then 5 %. Analyses of the forecast of intraregional and interregional passenger traffic for 2006–2010 proved that the neural model developed adequately described the passenger traffic demand for the next two or three years. The model can therefore be used for short-term forecasts of the Russian air transport network
First published online: 14 Oct 2010
This work is licensed under a Creative Commons Attribution 4.0 International License.