Policy and Research Documents
Mar-2025
Study into the impact special and weather events have on urban transport demand, making use of smart card data from 13 municipal districts in 2021 and 2022. Research found that cultural and demographic factors heavily influenced demand, implying that passenger behaviour is intricate and localised. Additionally, weather events such as rain or snow fall caused demand reductions of 8% and 37% respectively.
Apr-2022
Study conducts a comprehensive literature review to understand the state of public transportation and to facilitate the development and implementation of automated fare collection solutions. In summary, the paper considers developing and implementing automated fare collection solutions to have a positive impact on customer experience, the emergence of new business models and the reduction of polluting emissions.
Oct-2024
Study makes use of smart card data from nearly 9 million subway users to examine the long term impacts of the pandemic on residential locations and subway users in Beijing. Research indicates a notable trend of residential relocation towards the city centre, it is also observed that those with longer commute times are increasingly attempting to reduce their commute times.
Jan-2024
Report highlights the importance of demand forecasting, noting that the public transport sector is particularly vulnerable to fluctuations in consumer demand for perishable commodities. The researchers propose a method of demand forecasting for passenger transport which attains a success rate of 98.45%.
Mar-2022
Study intends to identify distinctive market segments in terms of habitual temporal travel patterns of public transport users, making use of smart card data from more than 3 million smart card holders in Stockholm County, Sweden. The study classified 10 day-of-the-week comparisons, as well as 5 hour-by-hour weekly profiles.
Nov-2023
Paper makes use of smart card datasets to analyse factors that influence the behaviour in relation to bus line shift, focused on a case study of the public transport network in Belo Horizonte, Brazil. Research indicates that users are generally inclined to bus line shifts than using the same lines, with such changes ocurring more frequently during late hours and inter-peak periods compared to morning and afternoon peak hours. Additionally, regular users are more likely to change lines than occasional users, and trips with discounts and smart card usage for transfers on trips home tend to involve different lines. The study considers several policy measures for mitigating passenger discomfort associated with changing bus lines.
Jun-25
Comprehensive review of uses cases for leveraging smart cards for analytical studies applied to public transport research. Aims to provide insights into smart card data research and highlight potential knowledge gaps that warrant further research.
Dec-2024
Study makes use of smart card data and travel survey data to determine low-to-middle income residents' secondary activity patterns. Study finds that these users have very few secondary activities, and advocates for urban amenities to be made more accessible.
Sep-2019
Study investigating passengers' travel patterns through the lens of stability and mobility, developing a system for clustering transport users. The study also makes use of socioeconomic data to discuss the interdependence between stability and mobility.
Apr-2021
Study proposes new method, making use of smart card data, to determine the impact long-term planned disruptions have on passenger travel behaviour. The method was applied during a 3 month closure of a rail line in the Greater Copenhagen area. Results suggest that the number of passengers who commuted daily decreased after the disruption.
Dec-2016
Study makes use of smart card data to form a novel projection with the intention to reveal the underlying temporal pattern of public transit users.
Jul-2020
Study makes use of data from the Camp de Tarragona automated fare collection system to study tourist's use of public transportation in Costa Daurada in 2018. The study identifies different clusters of passengers based on their activity and spatial profiles. Differences between profiles are significant, and due to this, the study validated the method which can be used in other contexts.
Oct-2016
Study presents a method to estimate the user cost of crowding in terms of the equivalent travel time loss. The estimated standing penalty is 26.5% of uncrowded value of in-vehicle travel time. An additional passenger per square metre adds 11.9% to the travel time multiplier.
Nov-2018
Study investigates if policies and projects aimed at decentralizing urban structure and job-worker patterns have produced a more balanced spatial configuration of jobs and workers. The paper finds that only a temporary balance appears around a few stations, that job-worker rations tend to steepening, not flattening and that the polycentric configuration of Beijing can be seen from the spatial patterns of job centres identified.
Jul-2019
Study aims to identify and cluster commuting patterns by making use of smart card data and traditional household survey data in Nanjing, China. Research found that some socioeconomic attributes, as well as bus station density, metro lines, transfer mode and transfer distance can significantly impact commuting patterns.
Mar-2021
Study develops a method to analyse the elasticity of travel demand in relation to public transport fares. The study made use of a fare policy introduced by the regional administration of Stockholm county in January 2017, which replaced a zonal fare system, with a flat fare. The study used smart card data to determine that lower socioeconomic groups seemed to be less sensitive. Additionally, the simplification and unification of the fare scheme seemed to substantially increased the attractiveness of public transport use.
Apr-2019
Study makes use of a method for revealing the structure of cities via clustering analysis using a new similarity measure. Researchers apply the method to data for Seoul, South Korea, revealing that the proposed clustering process divides the city in relatively homogenous areas in terms of land use.
Jun-2023
Study intends to contribute to the measurement of activity-based social segregation between multiple groups using smart card data. Study was conducted in Stockholm county in Sweden, showing a slight decrease in segregation between 2017 and 2020.
Sep-2020
Study proposes new method to extract travel patterns from different public transport systems, based on a temporal motif. Researchers then developed a scalable algorithm to recognize temporal motifs from daily trips sub-sequence from two smart card datasets.
Nov-2025
Study develops a framework for investigating physical encounters of individuals in urban metro systems using smart card data in Shenzhen, China.
Apr-2021
Study investigates public transport usage by older adults in Shizuoka, Japan, using smart card data to develop user-monthly profiles to explore seasonal variability and day-to-day variability. Research finds that older adults in the younger group (65-74) and in highly developed areas were more likely to frequently use public transport, with little seasonal variation. Additionally, day-to-day variability seems to increase with age and level of area development.
Sep-2020
Study addresses the applicability of the temporal segmented data identified in 18 clusters for measuring the stability of users' temporal habits as well as conducting descriptive analysis of the clusters, fare types and dates of the week to support their findings.
Sep-2021
Study makes use of smart card data mining to compare the urban transit movements of low income residents with middle/high income residents. Research finds that most lower income residents start their journey between 05:00 - 07:00, whilst higher income residents start between 07:00 - 09:00. Paper suggests that the empirical evidence from this paper shows the potential of smart card data to infold low employment spatial and temporal patterns.
Aug-2021
Study develops a method to mine metro commuting mobility patterns via massive smart card data. Study found that metro commuters accounted for 41% of morning peak traffic in Chongqing, discovering three typical job-housing function patterns and three commute efficiency patterns are discovered, with the characteristics of each being mined.
Dec-2020
Study intended to examine how urban spatial structures evolve, specifically focusing on incentives behind movement dynamics. The study makes use of network community detection and smart card data from the years 2013, 2015, and 2017 from Greater London. Study found that London's urban structure has become more polycentric and compact, that Greater London can be clustered into five distinct communities based on characteristics of passengers' travel patterns, and that the dynamics of structural change in different urban clusters differ in both changing intensity and potential motivation.
Jan-2018
Study intends to develop a system of prediction for determining if a transport user will make another trip, and if so, the attributes of said trip. The researchers tested their methodology using smart card records from over 10,000 users in London, over two years. The model was able to achieve median accuracy levels of over 80%, with the study finding the first trip of the day hardest to predict. The study also found significant variations found across individuals, implying diverse travel behaviour patterns.
Feb-2016
Study investigates regularities in human mobility, questioning if the detected regularities are stable, explicable and sustainable. The study makes use of 1 week of smart card data from three world cities (London, Singapore and Beijing), intending to contribute to a deeper understanding of regularities in patterns of transport use, establishing a general analytical framework for comparative studies using urban mobility data.
Nov-2015
Study analyses data from 512 questionnaires conducted in Belfast to determine the influence that perceived bus quality has upon the perceptions of both current and potential users. Research identifies 11 significant indicators that are reported to have a significant influence on the perception of bus users. The study uses these indicators to suggest optimisations that could be made to improve quality of bus services with the perceptions of current and potential users.
Jun-2023
Study aiming to identify passenger profiles using smartcard in Santiago, Chile by studying their recovery post pandemic. The study identified two groups: those who returned to their pre-pandemic patterns, and those who adapted their mobility patterns.
May-2022
Study intends to improve short -term forecasting of public transport demand, using AI-based deep learning models for prediction of bus passenger demands based on real patronage data obtained from the smartcard ticketing system in Melbourne. Study found that the models were able to predict passenger demand with over 90% accuracy.