Detecting home location and trip purposes for cardholders by mining smart card transaction data in Beijing subway

Automatic fare collection (AFC) system archives massive and continuous trip information for each cardholder. Mining the smart card transaction data from AFC system brings new opportunities for travel behavior and demand modeling. This study focuses on detecting the home location and trip purposes for subway passengers (cardholders), based on the internal temporal–spatial relationship within multi-day smart card transaction data. A center-point based algorithm is proposed to infer the home location for each cardholder. In addition, a rule-based approach using the individual properties (home location and card type) of cardholders and the travel information (time and space) of each trip is established for trip purpose identification. The smart card data from Beijing subway in China is used to validate the effectiveness of the proposed approaches. Results show that 88.7% of passengers’ home locations and four types of trip purposes (six subtypes) can be detected effectively by mining the card transaction data in one week. The city-wide home location distribution of Beijing subway passengers, and travel behavior with different trip purposes are analyzed. This study provides us a novel and low-cost way for travel behavior and demand research.

[1]  Adam Rahbee,et al.  Origin and Destination Estimation in New York City with Automated Fare System Data , 2002 .

[2]  Jinhua Zhao,et al.  Estimating a Rail Passenger Trip Origin‐Destination Matrix Using Automatic Data Collection Systems , 2007, Comput. Aided Civ. Infrastructure Eng..

[3]  Peter Widhalm,et al.  Discovering urban activity patterns in cell phone data , 2015, Transportation.

[4]  Bruno Agard,et al.  Measuring transit use variability with smart-card data , 2007 .

[5]  Stefano Spaccapietra,et al.  SeMiTri: a framework for semantic annotation of heterogeneous trajectories , 2011, EDBT/ICDT '11.

[6]  Randall Guensler,et al.  Elimination of the Travel Diary: Experiment to Derive Trip Purpose from Global Positioning System Travel Data , 2001 .

[7]  Howard Slavin,et al.  Use of Entry-Only Automatic Fare Collection Data to Estimate Linked Transit Trips in New York City , 2009 .

[8]  Harry Timmermans,et al.  Semiautomatic Imputation of Activity Travel Diaries , 2010 .

[9]  Alex Lu,et al.  Entry-Only Automated Fare-Collection System Data Used to Infer Ridership, Rider Destinations, Unlinked Trips, and Passenger Miles , 2009 .

[10]  Emilio Frazzoli,et al.  A review of urban computing for mobile phone traces: current methods, challenges and opportunities , 2013, UrbComp '13.

[11]  Marcela Munizaga,et al.  Estimation of a disaggregate multimodal public transport Origin-Destination matrix from passive smartcard data from Santiago, Chile , 2012 .

[12]  Michel Bierlaire,et al.  Inferring the Activities of Smartphone Users from Context Measurements Using Bayesian Inference and Random Utility Models , 2009 .

[13]  Martin Trépanier,et al.  Individual Trip Destination Estimation in a Transit Smart Card Automated Fare Collection System , 2007, J. Intell. Transp. Syst..

[14]  Yue Wang,et al.  Home and Work Place Prediction for Urban Planning Using Mobile Network Data , 2014, 2014 IEEE 15th International Conference on Mobile Data Management.

[15]  Peter R. Stopher,et al.  Search for a global positioning system device to measure person travel , 2008 .

[16]  Nigel H. M. Wilson,et al.  Analyzing Multimodal Public Transport Journeys in London with Smart Card Fare Payment Data , 2009 .

[17]  Davy Janssens,et al.  Semantic Annotation of Global Positioning System Traces , 2013 .

[18]  Keemin Sohn,et al.  Activity imputation for trip-chains elicited from smart-card data using a continuous hidden Markov model , 2016 .

[19]  Catherine Morency,et al.  Smart card data use in public transit: A literature review , 2011 .

[20]  Alexander Erath,et al.  Activity identification and primary location modelling based on smart card payment data for public transport , 2012 .

[21]  Patrick Tracy McGowen,et al.  Evaluating the Potential To Predict Activity Types from GPS and GIS Data , 2007 .

[22]  Mark Hickman,et al.  Trip purpose inference using automated fare collection data , 2014, Public Transp..

[23]  O. Järv,et al.  Using Mobile Positioning Data to Model Locations Meaningful to Users of Mobile Phones , 2010 .

[24]  R. Kitamura,et al.  Traveler Destination Choice Behavior: Effects of Time of Day, Activity Duration, and Home Location , 1998 .

[25]  Christian Schneider,et al.  Spatiotemporal Patterns of Urban Human Mobility , 2012, Journal of Statistical Physics.

[26]  Peter White,et al.  The Potential of Public Transport Smart Card Data , 2005 .

[27]  M. Trépanier,et al.  Detection of Activities of Public Transport Users by Analyzing Smart Card Data , 2012 .

[28]  Nicholas Jing Yuan,et al.  Reconstructing individual mobility from smart card transactions: a collaborative space alignment approach , 2014, Knowledge and Information Systems.

[29]  Wei Wu,et al.  Predicting Home and Work Locations Using Public Transport Smart Card Data by Spectral Analysis , 2015, 2015 IEEE 18th International Conference on Intelligent Transportation Systems.