Institutional Repository of Vilnius University
Keleivinių traukinių vėlavimų prognozavimas taikant statistinius ir mašininio mokymosi metodus /
Abstract
dc:descriptionIncreasing the importance of passenger railway transport and the growing number of passengers, ensuring train punctuality has become an important task in railway traffic management. Train delays negatively affect passenger satisfaction, traffic management processes, and the reliability of the transportation system, therefore delay prediction has become an important research area. This bachelor thesis investigates passenger train delay prediction in the railway network using machine learning methods. The study analyzes train traffic operational data provided by „LTG Infra“ together with meteorological data. Random Forest and \textit{XGBoost} machine learning models are applied for delay prediction, while the impact of meteorological features on prediction accuracy is also examined. Considering the research trends discussed in the literature review, the study analyzes temporal, infrastructure-related, meteorological, and historical delay features.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2026
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Maskeliūnaitė, Ugnė,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD308334734&prefLang=en_US