KSCE Journal of Civil Engineering

, Volume 23, Issue 4, pp 1797–1805 | Cite as

Detecting Taxi Travel Patterns using GPS Trajectory Data: A Case Study of Beijing

  • Hui ZhangEmail author
  • Baiying Shi
  • Chengxiang Zhuge
  • Wei Wang
Transportation Engineering


GPS trajectory is a valuable source to understand the operational status of taxicabs and identify the traffic demand and congestions. This study attempts to use 24-hour taxi trajectory data to investigate the attributes of taxicabs such as the distance of occupied distance, number of active taxicabs in different hours, average trip speed in different hour, coverage area of a taxicab, average radius of a taxicab, occupied rate and service times. The results show that the highest speed of taxicabs occur in the 3:00 am when there is the smallest number of active taxicabs running on the road. Moreover, the average occupied rate is 0.59 and the average service times are 19.8 in a day. Finally, a latent class analysis model is used to make the segment of taxicabs by their attributes. Four operational patterns have been found including ‘downtown preference type’, ‘long-distance preference type’, ‘suburbs preference type’ and ‘free preference type’. This study can shed light on understanding the operational status of taxicabs and gives suggestions for operators and passengers for better managing and using taxicabs.


taxi travel pattern GPS trajectory data latent class analysis travel attributes big data analysis 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Akaike, H. (1974). “A new look at the statistical model identification,” IEEE Transactions on Automatic Control, Vol. 19, No. 6, pp. 716–723, DOI: 10.1109/TAC.1974.1100705.MathSciNetCrossRefzbMATHGoogle Scholar
  2. Beiró, M. G., Panisson, A., Tizzoni, M., and Cattuto, C. (2016). “Predicting human mobility through the assimilation of social media traces into mobility models.” EPJ Data Science, Vol. 5, p. 30, DOI: 10.1140/epjds/s13688-016-0092-2.CrossRefGoogle Scholar
  3. Chen, D. D., Zhang, Y., Gao, L. P., Geng, N. N., and Li, X. F. (2017). “The impact of rainfall on the temporal and spatial distribution of taxi passengers.” Plos One, Vol. 12, No. 9, p. e0183574, DOI: 10.1371/journal.pone.0183574.CrossRefGoogle Scholar
  4. Hu, X. W., An, S., and Wang, J. (2014). “Explored urban taxi drivers’ activity distribution based on GPS data.” Mathematical Problems in Engineering, Vol. 2014, p. 708482, DOI: 10.1155/2014/708482.Google Scholar
  5. Hu, X. W., An, S., and Wang, J. (2018). “Taxi driver’s operation behavior and passengers’ demand analysis based on GPS data.” Journal of Advanced Transportation, Vol. 2018, p. 6197549, DOI: 10.1155/2018/6197549.Google Scholar
  6. Jiang, S. X., Guan, W., Zhang, W. Y., Chen, X., and Yang, L. (2017). “Human mobility in space from three modes of public transportation.” Physica A, Vol. 483, pp. 227–238, DOI: 10.1016/j.physa.2017.04.182.CrossRefGoogle Scholar
  7. Kang, C. G. and Qin, K. (2016). “Understanding operation behaviors of taxicabs in cities by matrix factorization.” Computers, Environment and Urban Systems, Vol. 60, pp. 79–88, DOI: 10.1016/j.compenvurbsys.2016.08.002.CrossRefGoogle Scholar
  8. Li, X. L., Gang, P., Wu, Z. H., Qi, G. D., Li, S. J., Zhang, D. Q., Zhang, W. S., and Wang, Z. H. (2012). “Prediction of urban human mobility using large-scale taxi traces and its applications.” Frontiers of Computer Science, Vol. 6, No. 1, p. 111–121, DOI: 10.1007/s11704-011-1192-6.MathSciNetGoogle Scholar
  9. Li, D. W., Miwa, T., and Morikawa, T. (2016). “Modeling time-of-day car use behavior: A Bayesian network approach.” Transportation Research Part D, Vol. 47, pp. 54–66, DOI: 10.1016/j.trd.2016.04.011.CrossRefGoogle Scholar
  10. Liu, Y. C., Liu, C. R., Yuan, N. J., Duan, L., Fu, Y. J., Xiong, H., Xu, S. H., and Wu, J. J. (2017). “Intelligent bus routing with heterogeneous human mobility patterns.” Knowledge and Information Systems, Vol. 50, No. 2, pp. 383–415, DOI: 10.1109/ICDM.2014.138.CrossRefGoogle Scholar
  11. Luo, F. X., Cao, G. F., Mulligan, K., and Li, X. (2016). “Explore spatiotemporal and demographic characteristics of human mobility via Twitter: A case study of Chicago.” Applied Geography, Vol. 70, pp.11–25, DOI: 10.1016/j.apgeog.2016.03.001.CrossRefGoogle Scholar
  12. Mao, F., Ji, M. H., and Liu, T. (2016). “Mining spatiotemporal patterns of urban dwellers from taxi trajectory data.” Frontiers of Earth Science, Vol. 10, No. 2, pp. 205–221, DOI: 10.1007/s11707-015-0525-4.CrossRefGoogle Scholar
  13. Muthén, L. K. and Muthén, B. O. (1998-2010). “Mplus user’s guide.” Los Angeles, CA, USA.Google Scholar
  14. Naji, H. A. H., Wu, C. Z., and Zhang, H. (2017). “Understanding the impact of human mobility patterns on taxi drivers’ profitability using clustering techniques: A case study in Wuhan, China,” Information, Vol. 8, No. 2, p. 67, DOI: 10.3390/info8020067.CrossRefGoogle Scholar
  15. Qian, X. W. and Ukkusuri, S. V. (2015). “Spatial variation of the urban taxi ridership using GPS data.” Applied Geography, Vol. 59, pp. 31–42, DOI: 10.1016/j.apgeog.2015.02.011.CrossRefGoogle Scholar
  16. Qin, G. Y., Li, T. N., Yu, B., Wang, Y. P., Huang, Z. H., and Sun, J. (2017). “Mining factors affecting taxi drivers’ incomes using GPS trajectories.” Transportation Research Part C, Vol. 79, pp. 103–118, DOI: 10.1016/j.trc.2017.03.013.CrossRefGoogle Scholar
  17. Raftery, A. E. (1986). “A note on Bayes factors for log-linear contingency table models with vague prior information.” Journal of the Royal Statistical Society, Series B, Vol. 48, No. 2, pp. 249–250, DOI: 10.2307/2345720.MathSciNetzbMATHGoogle Scholar
  18. Shi, J., Tao, L., Li, X. Y., Xiao, Y., and Atchley, P. (2014). “A survey of taxi drivers’ aberrant driving behavior in Beijing.” Journal of Transportation Safety & Security, Vol. 6, No. 1, pp. 34–43, DOI: 10.1080/19439962.2013.799624.CrossRefGoogle Scholar
  19. Sila-Nowicka, K., Vandrol, J., Oshan, T., Long, J. A., Demsar, U., and Fotheringham, A. S. (2016). “Analysis of human mobility patterns from GPS trajectories and contextual information.” International Journal of Geographical Information Science, Vol. 30, No. 5, pp. 881–906, DOI: 10.1080/13658816.2015.1100731.CrossRefGoogle Scholar
  20. Soliman, A., Soltani, K., Yin, J. J., Padmanabhan, A., and Wang, S. W. (2017). “Social sensing of urban land use based on analysis of twitter users’ mobility patterns.” Plos One, Vol. 12, No. 7, p. e0181657, DOI: 10.1371/journal.pone.0181657.CrossRefGoogle Scholar
  21. Song, X., Zhang, Q. S., Sekimoto, Y., Shibasaki, R., Yuan, N. J., and Xie, X. (2017). “Prediction and simulation of human mobility following natural disasters.” ACM Transactions on Intelligent Systems and Technology, Vol. 8, No. 2, p. 29, DOI: 10.1145/2970819.Google Scholar
  22. Tang, J. J., Liu, F., Wang, Y. H., and Wang, H. (2015). “Uncovering urban human mobility from large scale taxi GPS data.” Physica A, Vol. 438, pp. 140–153, DOI: 10.1016/j.physa.2015.06.032.CrossRefGoogle Scholar
  23. Vij, A., Carrel, A., and Walker, J. L. (2013). “Incorporating the influence of latent modal preference types on travel mode choice behavior.” Transportation Research Part A, Vol. 54, pp. 164–178, DOI: 10.1016/j.tra.2013.07.008.Google Scholar
  24. Wang, Q. and Taylor, J. E. (2016). “Patterns and limitations of urban human mobility resilience under the influence of multiple types of natural disaster.” Plos One, Vol. 11, No. 1, p. e0147299, DOI: 10.1371/journal.pone.0147299.CrossRefGoogle Scholar
  25. Wong, R. C. P., Szeto, W. Y., and Wong, S. C. (2015). “Behavior of taxi customers in hailing vacant taxis: A nested logit model for policy analysis.” Journal of Advanced Transportation, Vol. 49, pp. 867–883, DOI: 10.1002/atr.1307.CrossRefGoogle Scholar
  26. Xiao, H., Qiao, Y. Y., Jian, J., and Chang, Y. F. (2014). “Using smart phone sensors to detect transportation modes.” Sensors, Vol. 14, No. 11, pp. 20843–20865, DOI: 10.3390/s141120843.CrossRefGoogle Scholar
  27. Yang, X. P., Zhao, Z. Y., and Lu, S. W. (2016). “Exploring spatialtemporal patterns of urban human mobility hotspots.” Sustainability, Vol. 8, No. 2, p. 674, DOI: 10.3390/su8070674.CrossRefGoogle Scholar
  28. Yazdanpanah, M. and Hosseinlou, M. H. (2016). “The influence of personality trait on airport public transport access mode choice: A hybrid latent class choice modeling approach.” Journal of Air Transport Management, Vol. 55, pp. 147–163, DOI: 10.1016/j.jairtraman.2016.04.010.CrossRefGoogle Scholar
  29. Zhang, F. Z., Yuan, N. J., Wilkie, D., Zheng, Y., and Xie, X. (2015). “Sensing the pulse of urban refueling behavior: A perspective from taxi mobility.” ACM Transactions on Intelligent Systems and Technology, Vol. 6, No. 3, p. 37, DOI: 10.1145/2644828.Google Scholar
  30. Zheng, Z., Rasouli, S., and Timmermans, H. (2016). “Two-regime pattern in human mobility: Evidence from GPS taxi trajectory data.” Geographical Analysis, Vol. 48, No. 2, pp. 157–175, DOI: 10.1111/gean.12087.CrossRefGoogle Scholar
  31. Zheng, L. J., Xia, D., Zhao, X., Tan, L. Y., Li, H., Chen, L., and Liu, W. N. (2018). “Spatial-temporal travel pattern mining using massive taxi trajectory data.” Physica A, Vol. 501, pp. 24–41, DOI: 10.1016/j.physa.2018.02.064.CrossRefGoogle Scholar
  32. Zhou, Z. J., Dou, W. C., Jia, G. C., Hu, C. H., Xu, X. L., Wu, X. T., and Pan, J. G. (2016). “A method for real-time trajectory monitoring to improve taxi service using GPS big data.” Information and Management, Vol. 53, No. 8, p. 964–977, DOI: 10.1016/ Scholar
  33. Zong, F., Sun, X., Zhang, H. Y., Zhu, X. M., and Qi, W. T. (2015). “Understanding taxi drivers’ multi-day cruising patterns.” Promet-Traffic and Transportation, Vol. 27, No. 6, pp. 467–476, DOI: 10.7307/ptt.v27i6.1641.CrossRefGoogle Scholar

Copyright information

© Korean Society of Civil Engineers 2019

Authors and Affiliations

  • Hui Zhang
    • 1
    Email author
  • Baiying Shi
    • 1
  • Chengxiang Zhuge
    • 2
  • Wei Wang
    • 3
  1. 1.School of Transportation EngineeringShandong Jianzhu UniversityJinanChina
  2. 2.Centre for Environmental Policy Faculty of Natural SciencesImperial College LondonLondonUK
  3. 3.School of EconomicsOcean University of ChinaQingdaoChina

Personalised recommendations