Passenger Demographic Attributes Prediction for Human-Centered Public Transport

  • Can LiEmail author
  • Lei Bai
  • Wei Liu
  • Lina Yao
  • S. Travis Waller
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 1142)


This study examines the potential of the smart card data in public transit systems to infer passengers’ demographic attributes, thereby enabling a human-centered public transport service design while reducing the use of expensive and time-consuming travel surveys. This is challenging since travel behaviors vary significantly over the population, space and time and developing meaningful links between them and passengers’ demographic attributes are not trivial. To achieve this, we conduct an extensive analysis of spatio-temporal travel behavior patterns using smart card data from the Greater Sydney area, based on which we develop an end-to-end Hybrid Spatial-Temporal Neural Network. In particular, we first empirically analyze passenger movement and mobility travel patterns from both spatial and temporal perspectives and design a set of discriminative features to characterizing the patterns. We then propose a novel Product-based Spatial-Temporal module which encodes the relationships across a variety of features and harnesses them collectively under an Auto-Encoder Compression module, in order to predict passengers’ demographic information. The experiments are conducted using a large-scale real-world public transportation dataset covering 171.77 million users. The experimental results demonstrate the effectiveness of the proposed method against a number of established tools in the literature.


Passenger attribute classification Public transport system Deep neural networks 


  1. 1.
    Shiftan, Y., Outwater, M.L., Zhou, Y.: Transit market research using structural equation modeling and attitudinal market segmentation. Transp. Policy 15(3), 186–195 (2008)CrossRefGoogle Scholar
  2. 2.
    Mohamed, K., et al.: Clustering smart card data for urban mobility analysis. IEEE Trans. Intell. Transp. Syst. 18(3), 712–728 (2016)Google Scholar
  3. 3.
    Hagenauer, J., et al.: A comparative study of machine learning classifiers for modeling travel mode choice. Expert Syst. Appl. 78, 273–282 (2017)CrossRefGoogle Scholar
  4. 4.
    Bai, L., Yao, L., Kanhere, S.S., Yang, Z., Chu, J., Wang, X.: Passenger demand forecasting with multi-task convolutional recurrent neural networks. In: Yang, Q., Zhou, Z.-H., Gong, Z., Zhang, M.-L., Huang, S.-J. (eds.) PAKDD 2019. LNCS (LNAI), vol. 11440, pp. 29–42. Springer, Cham (2019). Scholar
  5. 5.
    Bai, L., et al.: Stg2seq: Spatial-temporal graph to sequence model for multi-step passenger demand forecasting. In: IJCAI (2019)Google Scholar
  6. 6.
    He, X., et al.: Outer product-based neural collaborative filtering. In: IJCAI, pp. 2227–2233. AAAI Press (2018)Google Scholar
  7. 7.
    Chen, T., et al.: Xgboost: a scalable tree boosting system. In: SIGKDD, pp. 785–794. ACM (2016)Google Scholar
  8. 8.
    Jahangiri, A., Rakha, H.A.: Applying machine learning techniques to transportation mode recognition using mobile phone sensor data. IEEE Trans. Intell. Transp. Syst. 16(5), 2406–2417 (2015)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Can Li
    • 1
    Email author
  • Lei Bai
    • 1
  • Wei Liu
    • 1
    • 2
  • Lina Yao
    • 1
  • S. Travis Waller
    • 2
  1. 1.Computer Science and Engineering, University of New South WalesSydneyAustralia
  2. 2.Civil and Environmental Engineering, University of New South WalesSydneyAustralia

Personalised recommendations