Estimation method for railway passengers’ train choice behavior with smart card transaction data

Smart card systems have become the predominant method of collecting public transport fares in Japan. Transaction data obtained through smart cards have resulted in a large amount of archived information on how passengers use public transportation. The data have the potential to be used for modeling passenger behavior and demand for public transportation. This study focused on train choices made by railway passengers. If each passenger’s train choice can be identified over a long period of time, this information would be useful for improving the customer relationship management of the railway company and for improving train timetables. The aim of this study was to develop a methodology for estimating which train is boarded by each smart card holder. This paper presents a methodology and an algorithm for estimation using long-term transaction data. To validate the computation time and accuracy of the estimation, an empirical analysis is carried out using actual transaction data provided by a railway company in Japan. The results show that the proposed method is capable of estimating passenger usage patterns from smart card transaction data collected over a long time period.     

Analyzing high speed rail passengers’ train choices based on new online booking data in China

This study explores two nonparametric machine learning methods, namely support vector regression (SVR) and artificial neural networks (ANN), for understanding and predicting high-speed rail (HSR) travelers’ choices of ticket purchase timings, train types, and travel classes, using ticket sales data. In the train choice literature, discrete choice analysis is the predominant approach and many variants of logit models have been developed. Alternatively, emerging travel choice studies adopt non-utility-based methods, especially nonparametric machine learning methods including SVR and ANN, because (1) those methods do not rely on assumptions on the relations between choices and explanatory variables or any prior knowledge of the underlying relations; (2) they have superb capabilities of iteratively identifying patterns and extracting rules from data. This paper thus contributes to the HSR train choice literature by applying and comparing SVR and ANN with a real-world case study of the Shanghai-Beijing HSR market in China. A new normalized metric capturing both the load factor and the booking lead time is proposed as the target variable and several train service attributes, such as day of week, departure time, travel time, fare, are identified as input variables. Computational results demonstrate that both SVR and ANN can predict the train choice behavior with high accuracy, outperforming the linear regression approach. Potential applications of this study, such as rail pricing reform, have also been identified.     

Validating and improving public transport origin–destination estimation algorithm using smart card fare data

Smart card data are increasingly used for transit network planning, passengers’ behaviour analysis and network demand forecasting. Public transport origin–destination (O–D) estimation is a significant product of processing smart card data. In recent years, various O–D estimation methods using the trip-chaining approach have attracted much attention from both researchers and practitioners. However, the validity of these estimation methods has not been extensively investigated. This is mainly because these datasets usually lack data about passengers’ alighting, as passengers are often required to tap their smart cards only when boarding a public transport service. Thus, this paper has two main objectives. First, the paper reports on the implementation and validation of the existing O–D estimation method using the unique smart card dataset of the South-East Queensland public transport network which includes data on both boarding stops and alighting stops. Second, the paper improves the O–D estimation algorithm and empirically examines these improvements, relying on this unique dataset. The evaluation of the last destination assumption of the trip-chaining method shows a significant negative impact on the matching results of the differences between actual boarding/alighting times and the public transport schedules. The proposed changes to the algorithm improve the average distance between the actual and estimated alighting stops, as this distance is reduced from 806 m using the original algorithm to 530 m after applying the suggested improvements.     

Passengers’ response to transit fare change: an ex post appraisal using smart card data

Fare change is an effective tool for public transit demand management. An automatic fare collection system not only allows the implementation of complex fare policies, but also provides abundant data for impact analysis of fare change. This study proposes an assessment approach for analyzing the influence when substituting a flat-fare policy with a distance-based fare policy, using smart card data. The method can be used to analyze the impact of fare change on demand, riding distances, as well as price elasticity of demand at different time and distance intervals. Taking the fare change of Beijing Metro implemented in 2014 as a case study, we analyze the change of network demand at various levels, riding distances, and demand elasticity of different distances on weekdays and weekends, using the method established and the smart card data a week before and after the fare change. The policy implication of the fare change was also addressed. The results suggest that the fare change had a significant impact on overall demand, but not so much on riding distances. The greatest sensitivity to fare change is shown by weekend passengers, followed by passengers in the evening weekday peak time, while the morning weekday peak time passengers show little sensitivity. A great variety of passengers’ responses to fare change exists at station level because stations serve different types of land usage or generate trips with distinct purposes at different times. Rising fares can greatly increase revenue, and can shift trips to cycling and walking to a certain extent, but not so much as to mitigate overcrowding at morning peak times. The results are compared with those of the ex ante evaluation that used a stated preference survey, and the comparison illustrates that the price elasticity of demand extracted from the stated preference survey significantly exaggerates passengers’ responses to fare increase.     

Modelling travellers’ risky choice in a revealed preference context: a comparison of EUT and non-EUT approaches

Recent work on risky choice modelling has sought to address the shortcomings of expected utility theory (EUT) by using non-expected utility theoretic (non-EUT) approaches. However, to date these approaches have been merely tested on stated choice data which is flexible and cheap. In this study, we empirically investigate the feasibility and validity of non-EUT approaches in a revealed preference (RP) context in which travel time distribution is extracted from observed historical travel time data, and subsequently present systematic comparisons between EUT, weighted utility theory, rank-dependent expected utility theory, and prospect theory (PT). The empirical evidence indicates that each non-EUT model has important behavioural insights to offer, moreover, EUT as well as non-EUT models can be applied to the RP context. However, the EUT and non-EUT model fits are generally similar with only PT providing a marginally improved model fit over EUT. The key findings presented in this study reinforce the importance of exploring non-EUT models within a revealed preference context before they can be applied reliably to modelling risky choices in the real world.     

Estimating the most likely space–time paths,dwell times and path uncertainties from vehicle trajectory data: A time geographic method

Global Positioning System and other location-based services record vehicles’ spatial locations at discrete time stamps. Considering these recorded locations in space with given specific time stamps, this paper proposes a novel time-dependent graph model to estimate their likely space–time paths and their uncertainties within a transportation network. The proposed model adopts theories in time geography and produces the feasible network–time paths, the expected link travel times and dwell times at possible intermediate stops. A dynamic programming algorithm implements the model for both offline and real-time applications. To estimate the uncertainty, this paper also develops a method based on the potential path area for all feasible network–time paths. This paper uses a set of real-world trajectory data to illustrate the proposed model, prove the accuracy of estimated results and demonstrate the computational efficiency of the estimation algorithm.