Taxi Travel Time Prediction Using Ensemble-Based Random Forest and Gradient Boosting Model

  • Bharat Gupta
  • Shivam Awasthi
  • Rudraksha Gupta
  • Likhama Ram
  • Pramod Kumar
  • Bakshi Rohit Prasad
  • Sonali Agarwal
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 645)

Abstract

Proposed work uses big data analysis and machine learning approach to accurately predict the taxi travel time for a trip based on its partial trajectory. To achieve the target, ensemble learning approach is used appropriately. Large dataset used in this work consists of 1.7 million trips by 442 taxis in Porto over a year. Significant features are extracted from the dataset, and Random Forest as well as Gradient Boosting is trained on those features and their performance is evaluated. We compared the results and checked the efficiency of both in this regard. Moreover, data inferences are done for trip time distribution, taxi demand distribution, most traversed area, and trip length distribution. Based on statistics, errors, graphs, and results, it is observed that both the methods predict time efficiently, but Gradient Boosting is slightly better than Random Forest.

Keywords

Taxi travel time Ensemble Random Forest Gradient Boosting 

References

  1. 1.
    Lam, H.T., Diaz-Aviles, E., Pascale, A., Gkoufas, Y., Chen, B.: Taxi destination and trip time prediction from partial trajectories. IBM Research—Ireland (2015)Google Scholar
  2. 2.
    Tang, J., Zou, Y., Ash, J., Zhang, S., Liu, F., Wang, Y.: Travel time estimation using freeway point detector data based on evolving fuzzy neural inference (2016)Google Scholar
  3. 3.
    Dong, H., Zhang, X., Dong, Y., Chen, C., Rao, F.: Recommend a profitable cruising route for taxi drivers (2014)Google Scholar
  4. 4.
    Yuan, N.J., Zheng, Y., Zhang, L., Xie, X.: T-Finder: a recommender system for finding passengers and vacant taxis (2013)Google Scholar
  5. 5.
    Miwa, T., Sakai, T., Morikawa, T.: Route identification and travel time prediction using probe-car data (2004)Google Scholar
  6. 6.
    Hunter, T., Herring, R., Abbeel, P., Bayen, A.: Path and travel time inference from GPS probe vehicle data (2009)Google Scholar
  7. 7.
    Cathey, F.W., Dailey, D.J.: A prescription for transit arrival/departure prediction using automatic vehicle location data. Trans Res Part C: Emerg Technol 11(3–4) (2013)Google Scholar
  8. 8.
    Luhang, X.: The research of data mining in traffic flow data. Shandong University (2015)Google Scholar
  9. 9.
    Cavar, I., Kavran, Z., Bosnjak, R.: Estimation of travel times on signalized arterials (2013)Google Scholar
  10. 10.
    Oluwatobi, A.N.: A GPS based automatic vehicle location (AVL) system for bus transit (2014)Google Scholar
  11. 11.
    Zhan, X., Hasan, S., Ukkusuri, S.V., Kamga, C.: Urban link travel time estimation using large-scale taxi data with partial information (2013)Google Scholar
  12. 12.
    Froehlich, J., Krumm, J.: Route prediction from trip observations (2008)Google Scholar
  13. 13.
    Yang, W.: Recommending Profitable Taxi Travel Routes based on Big Taxi Trajectory Data (2015)Google Scholar
  14. 14.
    Hoch, T.: An ensemble learning approach for the Kaggle taxi travel time prediction challenge (2015)Google Scholar
  15. 15.
    Wong, R.C.P., Szeto, W.Y., Wong, S.C.: A two-stage approach to modelling vacant taxi movements (2015)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  • Bharat Gupta
    • 1
  • Shivam Awasthi
    • 1
  • Rudraksha Gupta
    • 1
  • Likhama Ram
    • 1
  • Pramod Kumar
    • 1
  • Bakshi Rohit Prasad
    • 1
  • Sonali Agarwal
    • 1
  1. 1.Indian Institute of Information TechnologyAllahabadIndia

Personalised recommendations