Activity; Google Popular Times; Point of interest; Transit station; Transport demand modeling; Trip purpose; Automotive Engineering; Civil and Structural Engineering
Abstract :
[en] Google Popular Times (GPT) data are a novel data source that is open to the public, accessible in real time and available in many cities around the world. We aim to explain and predict travel demand patterns for train stations in Kyoto city with these data. Stepwise multiple linear regression models are developed using popularity data to analyze the correlation of the station demand patterns and point of interest (POI) visitation rates in the station vicinity. Our linear regression models aim to identify POIs and POI types that have the highest impact on the demand at each station. To predict station demand, we compared different machine learning models with the multiple linear regression model and concluded that the best prediction performance is obtained by Gradient Boosting. We were able to identify influential POIs and quantify their impacts given that there are a sufficient number of POIs in the vicinity of the station. Our findings suggest that GPT data can enable transit planners and transit users to predict station demand in real time. City planners would also gain valuable insights into the activity types highly related to transit station demand. Moreover, the method can be scaled and applied to other types of transit stations in other cities.
Disciplines :
Civil engineering
Author, co-author :
VONGVANICH, Teethat ; University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Engineering (DoE) ; Department of Urban Management, Kyoto University, Kyoto, Japan
Sun, Wenzhe; Department of Urban Management, Kyoto University, Kyoto, Japan
Schmöcker, Jan-Dirk; Department of Urban Management, Kyoto University, Kyoto, Japan
External co-authors :
yes
Language :
English
Title :
Explaining and Predicting Station Demand Patterns Using Google Popular Times Data
This work was supported by the EIG CONCERT-Japan DARUMA project, Grant No. JPMJSC20C4 funded by JST SICORP (Japan Science and Technology Agency), Japan.
A. Aguilera V. Boutueil Using cell phone data to understand travel behavior and transportation Urban mobility and the smartphone: transportation Elsevier
R. Ahas A.R. Aasa U. Mark S. Silm Evaluating passive mobile positioning data for tourism surveys: an Estonian case study Tour Manage 29 6 469 486 10.1016/j.tourman.2007.05.014
Arnal RP, Conesa D, Alvarez-Napagao S, Suzumura T, Català M, Alvarez E, Garcia-Gasulla D (2020) Private sources of mobility data under COVID-19. arXiv preprint arXiv:2007.07095
F. Aschauer R. Hossinger K. Axhausen B. Schmid R. Gerike Implication of survey mothods on travel and non-travel activities: a comparison of the Austrian national travel survey and an innovative mobility-activity-expenditure diary (MAED) Transp Infrastruct Res 18 1 4 35
K. Axhausen T. Gärling Activity-based approaches to travel analysis: conceptual frameworks, models, and research problems Transp Rev 12 4 323 341 10.1080/01441649208716826
Balmer M, Meister K, Rieser M, Nagel K, Axhausen KW (2008) Agent-based simulation of travel demand: structure and computational performance of MATSim-T. Arbeitsberichte Verkehrs-und Raumplanung, 504
Bandeira JM, Tafidis P, Macedo E, Teixeira J, Bahmankhah B, Guarnaccia C, Coelho MC (2020) Exploring the potential of web based information of business popularity for supporting sustainable traffic management. Transp Telecommun J 21(1):47–60
A. Bassolas H. Barbosa-Filho B. Dickinson X. Dotiwalla Hierarchical organization of urban mobility and its connection with city livability Nat Commun 10 4817 10.1038/s41467-019-12809-y
Bi M, Sun W, Schmöcker J-D, Ma Y, Moya-Gomez B, Nakao S, Yamada T (2023) Using geo-tagged tweets for understanding temporal and spatial activity distribution in Kyoto. In: 15th international conference of Eastern Asia Society for Transportation Studies (EASTS), Kuala Lumpur, Malaysia, 4–7 September
Breyer N, Rydergren C, Gundlegård D (2022) Semi-supervised mode classification of inter-city trips from cellular network data. J Big Data Anal Transp 4:23–39
Capponi A, Vitello P, Fiandrino C, Cantelmo G, Kliazovich D, Sorger U, Bouvry P (2019) Crowdsensed data learning-driven prediction of local businesses attractiveness in smart cities. IEEE symposium on computers and communications
N. Cetin K. Nagel B. Raney A. Voellmy Large-scale multi-agent transportation simulations Comput Phys Commun 147 1–2 559 564 10.1016/S0010-4655(02)00353-3 1019.90014
Cramer H, Rost M, Holmquist L (2011) Performing a check-in: emerging practices, norms and conflicts' in location-sharing using foursquare. In: 13th International Conference on Human Computer Interaction with Mobile Devices and Services
C. Ding X. Cao B. Yu Y. Ju Non-linear associations between zonal built environment attributes and transit commuting mode choice accounting for spatial heterogeneity Transp Res Part A: Policy Pract 148 22 35
D. Efthymiou C. Antoniou Use of social media for transport data Procedia Soc Behav Sci 48 775 785 10.1016/j.sbspro.2012.06.1055
Y. Gao J.-D. Schmöcker Estimation of walking patterns in a touristic area with Wi-Fi packet sensors Transp Res Part C 128 10.1016/j.trc.2021.103219 103219
Gao Y, Schmöcker J-D (2023) Inferring travel patterns and the attractiveness of touristic areas based on fusing Wi-Fi sensing data and GPS traces with a Kyoto Case study. Transportation Research Board. Washington D.C.
S.A. Golder M.W. Macy Digital footprints: opportunities and challenges for online social research Sociology 40 1 129 10.1146/annurev-soc-071913-043145
Google (2022) Popular times, wait times, and visit duration. Retrieved 1 11, 2022, from https://support.google.com/business/answer/6263531?hl=en
A. Horni K. Nagel W. Axhausen The multi-agent transport simulation MATSim London Ubiquity Press 10.5334/baw
Jee H, Sun W, Schmöcker J-D (2021) Estimation of bus line specific waiting times using Wi-Fi signal data. In: 7th International symposium on the use of public transit automated data for planning and operations (TransitData2021). Held online
Jee H, Schmöcker J-D, Barbeau S, Lozano W, Watkins KE (2022) Constructing passenger trips and tours using data from an experiment with the “OneBusAway” application. CASPT, Tel Aviv, Israel
Kurauchi F, Schmöcker JD (eds) (2017) Public transport planning with smart card data. CRC Press
C. Liu S. Erdogan T. Ma F.W. Ducca How to increase rail ridership in Maryland: direct ridership models for policy guidance J Urban Plan Dev 10.1061/(ASCE)UP.1943-5444.0000340
P.A. Longley A. Singleton J. Cheshire Smart card data and human mobility Consumer data research UCL Press 111 10.2307/j.ctvqhsn6
G. Lue E. Miller Estimating a Toronto pedestrain route choice model using smartphone GPS data Travel Behav Soc 14 34 42 10.1016/j.tbs.2018.09.008
S. Luo S.Y. He S. Grant-Muller L. Song Influential factors in customer satisfaction of transit services: using crowdsourced data to capture the heterogeneity across individuals, space and time Transp Policy 131 173 183 10.1016/j.tranpol.2022.12.011
D. MacKenzie H. Cho Travel demand and emissions from driving dogs to dog parks Transp Res Rec 2674 6 291 296 10.1177/0361198120918870
Maghrebi M, Abbasi A, Rashidi TH, Waller ST (2015) Complementing travel diary surveys with Twitter data: application of text mining techniques on activity location, type and time. In: IEEE 17th International Conference on Intelligent Transportation Systems (ITSC)
V. Mahajan G. Cantelmo C. Antoniou Explaining demand patterns during COVID-19 using opportunistic data: a case study of the city of Munich Eur Transp Res Rev 13 26 10.1186/s12544-021-00485-3
Miller EJ (2014) A framework for urban passenger data collection. In: 10th International conference on transport survey methods. Leura, Australia
M. Möhring B. Keller R. Schmidt S. Dacko Google Popular Times: towards a better understanding of tourist customer patronage behavior Tour Rev 76 533 569 10.1108/TR-10-2018-0152
Namulindwa S (2023) Crowd estimation and prediction using wi-fi sensor data: an experiment on katsura campus. Master’s Thesis, Department of Urban Management, Kyoto University
Nishigaki T, Schmöcker JD, Yamada T, Nakao S (2023) Estimating the number of tourists in Kyoto based on GPS traces and aggregate mobile statistics. In: Proceedings of the 12th international scientific conference on mobility and transport: mobility innovations for growing megacities. Springer Nature, Singapore, pp 221–243
J. Ortúzar L. Willumsen Modelling transport 4 Hoboken Wiley 10.1002/9781119993308
J. Osorio-Arjona J. Horak R. Svoboda Y. García-Ruíz Social media semantic perceptions on Madrid metro system: using Twitter data to link complaints to space Sustain Cities Soc 64 10.1016/j.scs.2020.102530 102530
M.-P. Pelletier M. Trepanier C. Morency Smart card data use in public transit: a literature review Transp Res Part C 2011 19 557 568 10.1016/j.trc.2010.12.003
A. Poom O. Järv M. Zook T. Toivonen COVID-19 is spatial: ensuring that mobile big data is used for social good Big Data Soc 7 2 2053951720952088 10.1177/2053951720952088
Rajput P, Chaturvedi M (2019) Automatic detection of bus-stops and bus-crowdedness using crowdsourced data. In: IEEE Intelligent Transportation Systems Conference. Auckland, New Zealand. pp 740–745
S. Ryu B. Park S. El-Tawab WiFi sensing system for monitoring public transportation ridership: a case study KSCE J Civ Eng 24 10 3092 3104 10.1007/s12205-020-0316-7
Sun W, Schmöcker JD (2021) Demand estimation for public transport network planning. In: The Routledge handbook of public transport (Chapter 21). Routledge, pp 289–305
H. Sung K. Choi S. Lee S. Cheon Exploring the impacts of land use by service coverage and station-level accessibility on rail transit ridership J Transp Geogr 36 134 140 10.1016/j.jtrangeo.2014.03.013
Tafidis P, Teixeira J, Bahmankhah B, Macedo E, Coelho MC, Bandeira J (2017) Exploring crowdsourcing information to predict traffic-related impacts. In: IEEE International Conference on Environment and Electrical Engineering and 2017 IEEE Industrial and Commercial Power Systems Europe, pp 1–6
Tasse D, Hong J (2014) Using social media data to understand cities. In: Proceedings of NSF Workshop on Big Data and Urban Informatics
S. Timokhin M. Sadrani C. Antoniou Predicting venue popularity using crowd-sourced and passive sensor data Smart Cities 3 3 42 10.3390/smartcities3030042
Vitello P, Fiandrino C, Connors R, Viti F (2023) Exploring the potential of Google Popular Times for transit demand estimation. Transportation Research Board (TRB) 102nd Annual Meeting
F. Wang C.L. Ross Machine learning travel mode choices: comparing the performance of an extreme gradient boosting model with a multinomial logit model Transp Res Rec 2672 47 35 45 10.1177/0361198118773556
Willumsen L (2021) Use of big data in transport modelling. In: International Transport Forum Discussion, 2021(5)
Wu L, Kand J, Chung Y, Nikolaev A (2019) Monitoring multimodal travel environment using automated fare collection data: data processing and reliability analysis. J Big Data Anal Transp 1:123–146
Y. Zhang A. Mohammadian Bayesian updating of transferred household travel data Transp Res Rec: J Transp Res Board 2049 111 118 10.3141/2049-13
Y. Zhu F. Chen Z. Wang J. Deng Spatio-temporal analysis of rail station ridership determinants in the built environment Transportation 46 2269 2289 10.1007/s11116-018-9928-x
