Forecasting daily passenger traffic volumes in the Moscow metro

Abstract

In this paper we have developed a methodology for the medium-term prediction of daily volumes of passenger traffic in the Moscow metro. It includes three options for the forecast: (1) based on artificial neural networks (ANNs), (2) singular-spectral analysis implemented in the Caterpillar–SSA package, and (3) a combination of the ANN and Caterpillar–SSA approaches. The methods and algorithms allow the mediumterm forecasting of passenger traffic flows in the Moscow metro with reasonable accuracy.