Skip to main content
SpringerLink
Log in

Explaining and Predicting Station Demand Patterns Using Google Popular Times Data

  • Research
  • Published:
Data Science for Transportation Aims and scope Submit manuscript

Abstract

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.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Availability of Data and Materials

The authors do not have the permission to share the data.

References

  • Aguilera A, Boutueil V (2018) Using cell phone data to understand travel behavior and transportation. Urban mobility and the smartphone: transportation. Elsevier

    Google Scholar 

  • Ahas R, Aasa AR, Mark U, Silm S (2008) Evaluating passive mobile positioning data for tourism surveys: an Estonian case study. Tour Manage 29(6):469–486

    Article  Google Scholar 

  • 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

  • Aschauer F, Hossinger R, Axhausen K, Schmid B, Gerike R (2018) 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

    Google Scholar 

  • Axhausen K, Gärling T (1992) Activity-based approaches to travel analysis: conceptual frameworks, models, and research problems. Transp Rev 12(4):323–341

    Article  Google Scholar 

  • 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

  • Bassolas A, Barbosa-Filho H, Dickinson B, Dotiwalla X (2019) Hierarchical organization of urban mobility and its connection with city livability. Nat Commun 10:4817

    Article  Google Scholar 

  • 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

  • Cetin N, Nagel K, Raney B, Voellmy A (2002) Large-scale multi-agent transportation simulations. Comput Phys Commun 147(1–2):559–564

    Article  MATH  Google Scholar 

  • 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

  • Ding C, Cao X, Yu B, Ju Y (2021) 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

    Google Scholar 

  • Efthymiou D, Antoniou C (2012) Use of social media for transport data. Procedia Soc Behav Sci 48:775–785

    Article  Google Scholar 

  • Gao Y, Schmöcker J-D (2021) Estimation of walking patterns in a touristic area with Wi-Fi packet sensors. Transp Res Part C 128:103219

    Article  Google Scholar 

  • 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.

  • Golder SA, Macy MW (2014) Digital footprints: opportunities and challenges for online social research. Sociology 40(1):129

    Article  Google Scholar 

  • Google (2022) Popular times, wait times, and visit duration. Retrieved 1 11, 2022, from https://support.google.com/business/answer/6263531?hl=en

  • Horni A, Nagel K, Axhausen W (2016) The multi-agent transport simulation MATSim. Ubiquity Press, London

    Book  Google Scholar 

  • 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

  • Liu C, Erdogan S, Ma T, Ducca FW (2016) How to increase rail ridership in Maryland: direct ridership models for policy guidance. J Urban Plan Dev. https://doi.org/10.1061/(ASCE)UP.1943-5444.0000340

    Article  Google Scholar 

  • Longley PA, Singleton A, Cheshire J (2018) Smart card data and human mobility. Consumer data research. UCL Press, p 111

    Chapter  Google Scholar 

  • Lue G, Miller E (2019) Estimating a Toronto pedestrian route choice model using smartphone GPS data. Travel Behav Soc 14:34–42

    Article  Google Scholar 

  • Luo S, He SY, Grant-Muller S, Song L (2023) 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

    Article  Google Scholar 

  • MacKenzie D, Cho H (2020) Travel demand and emissions from driving dogs to dog parks. Transp Res Rec 2674(6):291–296

    Article  Google Scholar 

  • 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)

  • Mahajan V, Cantelmo G, Antoniou C (2021) Explaining demand patterns during COVID-19 using opportunistic data: a case study of the city of Munich. Eur Transp Res Rev 13:26

    Article  Google Scholar 

  • Miller EJ (2014) A framework for urban passenger data collection. In: 10th International conference on transport survey methods. Leura, Australia

  • Möhring M, Keller B, Schmidt R, Dacko S (2020) Google Popular Times: towards a better understanding of tourist customer patronage behavior. Tour Rev 76:533–569

    Article  Google Scholar 

  • 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

  • Ortúzar J, Willumsen L (2011) Modelling transport, 4th edn. Wiley, Hoboken

    Book  Google Scholar 

  • Osorio-Arjona J, Horak J, Svoboda R, García-Ruíz Y (2021) Social media semantic perceptions on Madrid metro system: using Twitter data to link complaints to space. Sustain Cities Soc 64:102530

    Article  Google Scholar 

  • Pelletier M-P, Trepanier M, Morency C (2011) Smart card data use in public transit: a literature review. Transp Res Part C 2011(19):557–568

    Article  Google Scholar 

  • Poom A, Järv O, Zook M, Toivonen T (2020) COVID-19 is spatial: ensuring that mobile big data is used for social good. Big Data Soc 7(2):2053951720952088

    Article  Google Scholar 

  • 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

  • Ryu S, Park B, El-Tawab S (2020) WiFi sensing system for monitoring public transportation ridership: a case study. KSCE J Civ Eng 24(10):3092–3104

    Article  Google Scholar 

  • 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

  • Sung H, Choi K, Lee S, Cheon S (2014) Exploring the impacts of land use by service coverage and station-level accessibility on rail transit ridership. J Transp Geogr 36:134–140

    Article  Google Scholar 

  • 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

  • Timokhin S, Sadrani M, Antoniou C (2020) Predicting venue popularity using crowd-sourced and passive sensor data. Smart Cities 3(3):42

    Article  Google Scholar 

  • 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

  • Wang F, Ross CL (2018) 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

    Article  Google Scholar 

  • 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

  • Zhang Y, Mohammadian A (2010) Bayesian updating of transferred household travel data. Transp Res Rec: J Transp Res Board 2049:111–118

    Article  Google Scholar 

  • Zhu Y, Chen F, Wang Z, Deng J (2019) Spatio-temporal analysis of rail station ridership determinants in the built environment. Transportation 46:2269–2289

    Article  Google Scholar 

Download references

Funding

This work was supported by the EIG CONCERT-Japan DARUMA project, Grant No. JPMJSC20C4 funded by JST SICORP (Japan Science and Technology Agency), Japan.

Author information

Authors and Affiliations

  1. Department of Urban Management, Kyoto University, Kyoto, Japan

    Teethat Vongvanich, Wenzhe Sun & Jan-Dirk Schmöcker

Authors
  1. Teethat Vongvanich
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Wenzhe Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jan-Dirk Schmöcker
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

TV: Content design, data analysis, and manuscript writing and editing. WS: Content design, data analysis, and manuscript writing and editing. J-DS: Content design, data analysis, and manuscript writing and editing.

Corresponding author

Correspondence to Wenzhe Sun.

Ethics declarations

Conflict of Interest

The authors declared that there is no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Vongvanich, T., Sun, W. & Schmöcker, JD. Explaining and Predicting Station Demand Patterns Using Google Popular Times Data. Data Sci. Transp. 5, 10 (2023). https://doi.org/10.1007/s42421-023-00072-z

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s42421-023-00072-z

Keywords

Search

Navigation