Analysis of Taxi Drivers’ Working Characteristics Based on GPS Trajectory Data

  • Jing YouEmail author
  • Zhen-xian Lin
  • Cheng-peng Xu
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 891)


Using the large-scale taxi GPS trajectory data mining to analyze working characteristics of taxi drivers, it can provide reference help for those who want to work in taxis. This paper proposes a method for analyzing the working characteristics of taxi drivers based on Spark data processing platform. Firstly, the GPS trajectory data are cleaned and then imported into HDFS. Secondly, taxi drivers’ work indicators and taxis’ stop points are extracted. Then, the statistical method is applied to analyze the work indicators to obtain drivers’ work feature, and the K-Means algorithm is used to cluster the stay points to get the drivers’ three meals rest and then drivers’ rest feature can be get. The results show that the Spark platform can quickly and accurately analyze the working characteristics of taxi drivers.


Spark data processing platform Taxi GPS trajectory data Taxi drivers’ work characteristics 



This research was supported in part by Key Research and Application of Big Data Trading Market in Shaanxi Province (2016KTTSGY01-01).


  1. 1.
    Zhuang, L., Song, J., Duan, Z., et al.: Research on taxi operating characteristics based on floating car data mining. Urban Transp. 14(1), 59–64 (2016). Scholar
  2. 2.
    Zhuang, L., Wei, J., He, Z., et al.: Taxi operation and management characteristics based on floating car data. J. Chongqing Jiaotong Univ. 33(4), 122–127 (2014). Scholar
  3. 3.
    Lv, Z., Jianping, W., Yao, S., et al.: FCD-based analysis of taxi operation characteristics: a case of Shanghai. Nat. Sci. East China Norm. Univ. 3, 133–144 (2017). Scholar
  4. 4.
    Liu, L., Andris, C., Ratti, C.: Uncovering cabdrivers’ behavior patterns from their digital trace. Comput. Environ. Urban Syst. 34, 541–548 (2010). Scholar
  5. 5.
    Zhang, J., Chou, P., Du, M.: Mining method of travel characteristics based on spatio-temporal trajectory data. Transp. Syst. Eng. Inf. 14(6), 72–78 (2014).
  6. 6.
    Liu, H., Kan, Z., Sun, F., et al.: Taxis’ Short-Term out-of-service behaviors detection using big trace data. Geomat.S Inf. Sci. Wuhan Univ. 41(9), 1192–1198 (2016). Scholar
  7. 7.
    Xia, J., Wei, Z., Fu, K., et al.: Review of research and application on hadoop in cloud computing. Comput. Sci. 43(11), 6–11+48 (2016).
  8. 8.
    Karau, H.: Spark Fast Big Data Analysis, pp. 1–6. People Post Press (2015)Google Scholar
  9. 9.
    Duan, Z., Chen, Z., Chen, Z., et al.: Analysis of taxi passenger travel characteristics based on spark platform. Comput. Syst. Appl. 26(3), 37–43 (2017). Scholar
  10. 10.
    Zhou, Z.: Machine Learning, pp. 202–204. Tsinghua University Press, Beijing (2016)Google Scholar
  11. 11.
    Yang, Y., Yao, E., Pan, L., et al.: Research on taxi route choice behavior based on GPS data. J. Transp. Syst. Eng. Inf. Technol. 15(1), 81–86 (2015). Scholar
  12. 12.
    Chengdu Taxi Network. Taxi rental standard in Chengdu downtown area.,2018/06/11
  13. 13.
    Qi, X., Liang, W., Ma, Y.: Optimal path planning method based on taxi trajectory data. J. Comput. Appl. 37(7): 2106–2113 (2017).

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.School of Communication and Information EngineeringXi’an University of Posts and TelecommunicationsXi’anChina
  2. 2.School of ScienceXi’an University of Posts and TelecommunicationsXi’anChina
  3. 3.Institute of Internet of Things and IT-Based IndustrializationXi’an University of Posts and TelecommunicationsXi’anChina

Personalised recommendations