Arrival Train Delays Prediction Based on Gradient Boosting Regression Tress

Delay prediction based on real-world train operation records is an essential issue to the delay management. In this paper, the authors present the first application of gradient boosting regression tress prediction model that can capture the relation between train delays and various characteristics of a railway system. Delayed train number, station code, scheduled time of arrival at a station, time travelled, distance travelled, and percent of journey completed distance-wise are selected as the explanatory variables, and the delay time is the target variable. The model can evaluate various impact factors on train delays, which can assist dispatchers to make decisions. The results demonstrate that the gradient boosting regression tress model has a higher prediction precision and outperforms the support-vector machine model and the random forest model.

• Record URL:
  • https://doi.org/10.1007/978-981-15-2914-6_29
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/isbn/9789811529146
• Supplemental Notes:
  • © Springer Nature Singapore Pte Ltd. 2020.
• Corporate Authors:

  Springer Singapore

  152 Beach Road
  Singapore,     189721
• Authors:
  • Shi, Rui
  • Wang, Jing
  • Xu, Xinyue
  • Wang, Mingming
  • Li, Jianmin
• Conference:
  • 4th International Conference on Electrical and Information Technologies for Rail Transportation (EITRT 2019)
  • Location: Qingdao , China
  • Date: 2019-10-25 to 2019-10-27
• Publication Date: 2020-4

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: pp 307-315
• Monograph Title: Proceedings of the 4th International Conference on Electrical and Information Technologies for Rail Transportation (EITRT) 2019: Rail Transportation Information Processing and Operational Management Technologies
• Serial:
  • Lecture Notes in Electrical Engineering
  • Publisher: Springer
  • ISSN: 1876-1100

Subject/Index Terms

• TRT Terms: Delays; Predictive models; Railroad operations; Regression analysis; Train operations
• Subject Areas: Operations and Traffic Management; Planning and Forecasting; Railroads;

Filing Info

• Accession Number: 01928522
• Record Type: Publication
• ISBN: 9789811529146
• Files: TRIS
• Created Date: Aug 23 2024 4:53PM