Predicting Express Train Choice of Metro Passengers from Smart Card Data

Abstract

This paper addresses the problem of predicting the express local train choices of metro passengers. The model was built and tested on the preferences observed from smart card data. The revealed preference data, because of intensiveness, can also accurately capture the marginal effects of the core attributes, in-vehicle time and wait time, on the express train choices by metro passengers. To be specific, the marginal disutility of a path decreases in in-vehicle time and increases in wait time. Accordingly, this paper employs a Box–Cox transform to adjust the constant marginality of a linear model to the nonconstant marginal disutility. The resulting nonlinear logit model improved the predictability of a conventional linear model. Tested on the Incheon–Yongsan interval of the Gyeong-In Line of the Seoul metropolitan area in South Korea, the model predicted a correct choice by a passenger in 99.9% and 99.5% of the cases during peak and nonpeak hour periods, respectively, compared with 96.9% and 95.8%, respectively, from a linear model. The model, applied to Line 9 without a parameter tuning, achieved a predictability greater than 95%.

Heterogeneity in Personal Attitudes and Preferences for High-Speed Metropolitan Railway Service by Travel Contexts in South Korea: A Hybrid Choice Modeling Approach

“…Studies on urban or suburban express railway services like GTX have found that the properties of express railways such as mobility (3) and punctuality (4) have a great influence on the mode choice process. In addition, the possibility of using the suburban express rail is also increased through reducing the out-vehicle time (5) by improving accessibility or strengthening the linkage of modes and enhancing convenience by reducing congestion (6,7) in the vehicle and similar results are obtained from studies on Gyeong-in Line and Line 9 (8)(9)(10) in the metropolitan area of Seoul based on transportation card data. Although these studies could provide meaningful insights about properties of express rail or suburban rail services in mode choice process, diverse travel contexts which might affect the utility of using the express railway services tend to be ignored.…”

Estimating Express Train Preference of Urban Railway Passengers Based on Extreme Gradient Boosting (XGBoost) using Smart Card Data

“…Lee et al distinguished the preference between the local train boarded group and the express train boarded using the Gaussian mixture model with smart card data (6). Kim et al also employed smart card data to develop an express train choice model, and the results of the train choice model indicated that passengers preferred the express train over the local (7).…”

A Comparison into the Factors Affecting Urban Rail Systems: Local, Express, and High-Speed Rail in Tunnels at a Great Depth in a Metropolitan Area

“…Kim et al [19] deduced whether the route chosen by passengers of Subway Line 9 comprised express, regular, or mixed commutes by using the boarding and alighting information at the first and last stations of the line and investigated changes in the commuters' choices between the express and local trains after the extension of the line. Kim et al [20] focused on the Gyeongin Line to establish both linear and non-linear utility functions, with in-vehicle time and waiting time set as explanatory variables, and assessed the goodness-of-fit of the model based on the degree of explanation provided by the coefficient.…”