Passenger travel behaviour on Chinese high‐speed railways using machine learning based on revealed‐preference data

Abstract

Existing studies on the selection of railway travel modes almost always compare high‐speed trains and regular‐speed trains. In this study, three high‐speed trains (Revival, Harmony, and Electric multiple unites (EMU)) on the Beijing–Shanghai line, and the first‐ and second‐class seats on these three trains are selected as research objects to analyse the travel selection behaviour of Chinese high‐speed train passengers. Three methods are selected to study this behaviour: the Support Vector Machine, Nested Logit model, and Multiple Logit model. The results of these three models are calibrated using LIBSVM software and STATA software and show that age, funding source, income level, and purpose of travel are major factors that affect Chinese railway passengers' choices on high‐speed railways. Finally, it is shown that the Support Vector Machine is the most accurate of these three methods, followed by the Nested Logit model. The results of this study can complement existing research on the travel selection behaviour of Chinese railway passengers and has important implications for enabling China's high‐speed rail operators to adjust their passenger transportation products.