Spatio-Temporal Ensemble Method for Car-Hailing Demand Prediction

Accurate demand prediction plays a significant role in online car-hailing platforms. With ensemble learning, several models can be combined into a single demand predictive model, achieving low prediction error. Nevertheless, the existing ensemble methods are not intended for spatio-temporal data and thus cannot deal with it. In this article, a spatio-temporal data ensemble model is proposed to predict car-hailing demands. Treating the prediction results as various channels of an image, the proposed ensemble module first compresses and then restores the results using the fully convolutional network. Additionally, a skip connection is used to preserve both the fine-grained information in the shallow layers and the deep coarse information. Based on the principle of model as a service, any model can be plugged into the authors' framework as base models to improve the prediction accuracy. Experimental results demonstrate the effectiveness of the presented model.

• Record URL:
  • https://doi.org/10.1109/TITS.2019.2948790
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/oclc/41297384
• Supplemental Notes:
  • Copyright © 2020, IEEE.
• Authors:
  • Liu, Yang
  • Lyu, Cheng
  • Khadka, Anish
  • Zhang, Wenbo
  • Liu, Zhiyuan
• Publication Date: 2020-12

Language

• English

Media Info

• Media Type: Digital/other
• Features: Figures; References; Tables;
• Pagination: pp 5328-5333
• Serial:
  • IEEE Transactions on Intelligent Transportation Systems
  • Volume: 21
  • Issue Number: 12
  • Publisher: Institute of Electrical and Electronics Engineers (IEEE)
  • ISSN: 1524-9050
  • Serial URL: http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6979

Subject/Index Terms

• TRT Terms: Mathematical models; Neural networks; Ridesourcing; Spatial analysis; Time series analysis; Traffic data; Travel demand
• Identifier Terms: Didi Chuxing
• Geographic Terms: China
• Subject Areas: Highways; Passenger Transportation; Planning and Forecasting;

Filing Info

• Accession Number: 01761888
• Record Type: Publication
• Files: TLIB, TRIS
• Created Date: Dec 31 2020 4:59PM