A comparison between ARIMA, LSTM, ARIMA-LSTM and SSA for cross-border rail freight traffic forecasting: the case of Alpine-Western Balkan Rail Freight Corridor

Abstract

Excessive delays of railway traffic at border crossing points as a consequence of poor planning of border crossing procedures lower the performance of train service, increase its cost and reduce the satisfaction of shippers. Mid-term prediction of traffic flows may improve the process of planning border-crossing activities. In this paper, we model the intensity of cross-border railway traffic on the Alpine-Western Balkan Rail Freight Corridor (AWB RFC). For each of the four border crossing points: Dimitrovgrad, Presevo, Sid and Subotica, time series composed of 102 monthly export and import railway freight traffic observations are used for training and testing of alternative forecasting models. Traditional ARIMA, Long-Short-Term Memory (LSTM) neural network, hybrid ARIMA-LSTM and Singular Spectrum Analysis (SSA) models, are fitted to each of the eight time series. To enable the practical applicability of the proposed approach the “Best fit forecast” tool is developed.

On one approach to choosing unloading stations according to egalitarian principles in transport-type optimization problems

“…A large number of studies conducted in recent years are related to the issues of optimization of transport processes, rational distribution of cargo flows, including those considered within the framework of multimodal transportation systems [1][2][3][4][5][6][7][8][9][10]. For example, the paper [2] addresses the optimisation of transport processes within a logistic chain.…”

“…For example, the paper [2] addresses the optimisation of transport processes within a logistic chain. In paper [4], autors model the intensity of cross-border railway traffic on the Alpine-Western Balkan Rail Freight Corridor (AWB RFC). The paper [5] is focused on using of selected methods from applied mathematics in railway transport.…”

“…The paper [5] is focused on using of selected methods from applied mathematics in railway transport. The above analysis gives an idea of the relevance of research on the optimization of transport and technological systems in the regions, as well as the variety of methods used in this case [1][2][3][4][5][6][7][8][9][10]. It should be noted that a necessary condition for a client-oriented approach to the organization of the transport process is the solution of the problem, which consists in increasing the level of economic feasibility of this process.…”