A Decision Tree Ensemble Model for Predicting Bus Bunching. (8th May 2021)

• Record Type: Journal Article
• Authors: Borges Santos, Veruska; S Pires, Carlos Eduardo; Cassimiro Nascimento, Dimas; de Queiroz, Andreza Raquel M
• Is Part Of: Computer journal. Volume 65:Number 8(2022)
• Page Start: 2044
• Page End: 2062
• Publication Date: 2021-05-08
• Subjects: public transportation -- bus bunching -- real-time prediction -- machine learning; Computers -- Periodicals; 005.1
• DOI: 10.1093/comjnl/bxab045
• Languages: English
• ISSNs: 0010-4620

Abstract

Abstract: Travel delays and bus overcrowding are some of the daily dissatisfactions of public transportation users. These problems may be caused by bus bunching, an event that occurs when two or more buses are running the same route together, i.e. out of schedule. Due to the stochastic nature of the traffic, a static schedule is not effective to avoid the occurrence of these events; thus, preventive actions are necessary to improve the reliability of the public transportation system. In this context, we propose a decision tree ensemble model to predict bus bunching. We use an ensemble of Random Forest, eXtreme Gradient Boosting and Categorical Boosting models applied to Global Positioning System, General Transit Feed Specification, weather and traffic situation data. The efficacy of the proposed model has been demonstrated using real data sets and has been compared with four baselines: Linear Regression, Logistic Regression, Support Vector Machine and Relevance Vector Machine. According to the results, the proposed model can achieve an efficacy between 74 and 80% and can be used to predict bus bunching in real time up to 10 stops before its occurrence.