Capturing complexity over space and time via deep learning: An application to real-time delay prediction in railways

Léon Sobrie, Marijn Verschelde, Veerle Hennebel and Bart Roets
Additional contact information
Léon Sobrie: UGENT - Universiteit Gent = Ghent University = Université de Gand
Marijn Verschelde: LEM - Lille économie management - UMR 9221 - UA - Université d'Artois - UCL - Université catholique de Lille - Université de Lille - CNRS - Centre National de la Recherche Scientifique
Veerle Hennebel: Department of Economics [Leuven] - KU Leuven - Catholic University of Leuven = Katholieke Universiteit Leuven
Bart Roets: Infrabel, Brussels

Post-Print from HAL

Abstract: Predictive analytics is an increasingly popular tool for enhancing decision-making processes but is in many business settings based on rule-based models. These rule-based models reach their limits in complex settings. This study compares the performance of a rule-based system with a customised LSTM encoder-decoder deep learning model for predicting train delays. For this, we use a purposefully built real-world dataset on railway transportation, where trains' interdependence over the network makes delay prediction more difficult. Results show that the deep learning model, which incorporates rich spatiotemporal interdependency information in real-time, outperforms the rule-based system by 18%, with the difference increasing to above 23% with higher complexity. The study also dissects the performance difference across different settings: dense versus rural areas, peak versus off-peak hours, low versus high delay, and before versus during the COVID-19 pandemic. The deep learning model is implemented as a proof of concept for decision support within Belgium's railway infrastructure company Infrabel.

Date: 2023-11
References: Add references at CitEc
Citations: View citations in EconPapers (1)

Published in European Journal of Operational Research, inPress, 310 (3), pp.1201-1217. ⟨10.1016/j.ejor.2023.03.040⟩

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:journl:hal-04136284

DOI: 10.1016/j.ejor.2023.03.040

Access Statistics for this paper

More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD ().