Justification of the acceptability of a hybrid approach to passenger and freight flows' predictive modelling in the context of sustainable development

¹ Ukrainian State University of Railway Transport, Department of Railway Stations and Units, 7 Oboronnyi Val Sq., Kharkiv, Ukraine
² State University “Kyiv Aviation Institute”, Air Transportation Management Department, 1 Liubomyra Huzara Ave., Kyiv, Ukraine
³ Ukrainian State University of Railway Transport, Department of Freight and Commercial Operations Management, 7 Oboronnyi Val Sq., Kharkiv, Ukraine

^* Corresponding author: This email address is being protected from spambots. You need JavaScript enabled to view it.

Abstract

The relevance of the study is determined by the need for more accurate long-term forecasting in modeling passenger and freight flows. The methodological basis of the study consists of methods of analysis and forecasting of time series, methods of recurrent neural networks, and various methods of expert assessments. A hybrid SARTMAX/LSTM method for long-term forecasting of freight and passenger traffic flows has been implemented, and a scheme for long-term forecasting and a scheme for applying the hybrid SARIMAX/LSTM method have been proposed. An assessment of the overall accuracy of long-term forecasting using the SARIMAX/LSTM hybrid method for the transport and logistics market in general, for railway and air transport in particular has been carried out.