Delay prediction based on real-world train operation records is an essential issue to the delay management. In this paper, we present the first application of gradient boosting regression tress (GBRT) prediction model that can capture the relation between train delays and various characteristics of a railway system. Delayed train number (DN), station code (SC), scheduled time of arrival at a station (ST), time travelled (TT), distance travelled (DT), and percent of journey completed distance-wise (PC) are selected as the explanatory variables, and the delay time (WD) 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 GBRT model has a higher prediction precision and outperforms the support-vector machine (SVR) model and the random forest (RF) model.
Arrival Train Delays Prediction Based on Gradient Boosting Regression Tress
Lect. Notes Electrical Eng.
International Conference on Electrical and Information Technologies for Rail Transportation ; 2019 ; Qingdao, China October 25, 2019 - October 27, 2019
Proceedings of the 4th International Conference on Electrical and Information Technologies for Rail Transportation (EITRT) 2019 ; Chapter : 29 ; 307-315
2020-04-02
9 pages
Article/Chapter (Book)
Electronic Resource
English
Arrival Train Delays Prediction Based on Gradient Boosting Regression Tress
British Library Conference Proceedings | 2020
|Analyzing passenger train arrival delays with support vector regression
Online Contents | 2015
|Real-time bus arrival delays analysis using seemingly unrelated regression model
Springer Verlag | 2024
|Train Arrival Delay Prediction Based on a CNN-LSTM Approach
TIBKAT | 2021
|