analiza aiqbench
This study applies interpretable tree-based ensemble methods to analyze delay prediction on the Dutch railway network, offering a rigorous evaluation of how environmental volatility and feature instability impact long-term forecasting robustness. By moving beyond opaque deep learning architectures, the research highlights that richer feature sets alone cannot resolve temporal decay without dynamic, season-aware models anchored in operational boundaries. The findings provide critical insights for applying machine learning techniques to complex, real-world logistical systems where explainability and stability are paramount.
Predicting Delayed Train Trajectories on the Dutch Railway Network: Explainable AI Evaluation of Topological, Operational and Weather Features with Tree Based Ensemble Methods
arXiv:2609.34692v1 Announce Type: new Abstract: The reliable prediction of passenger train delays is a critical component of railway management. While contemporary research frequently attempts to maximize absolute accuracy by deploying opaque deep learning architectures, the underlying data mechanics driving longitudinal predictive decay remain underexplored. Consequently, this study provides an explainable temporal robustness analysis of network-wide railway delay prediction. Focusing on the Dutch railway network, this research utilizes interpretable tree-based ensembles to integrate granular topological, environmental, and operational features. The overarching finding establishes that while feature-rich tree-based models improve simultaneous (within-month) prediction, predictive performance systematically degrades when evaluated across non-simultaneous (future) months. Furthermore, multi-horizon SHAP and dispersion analyses explicitly link this degradation to environmental feature volatility and instability within the statistical target definition. Ultimately, this thesis demonstrates that richer feature sets alone are insufficient to resolve long-term forecasting constraints, underscoring the necessity to transition toward dynamic, season-aware architectures anchored by absolute operational boundaries.
Abstract:The reliable prediction of passenger train delays is a critical component of railway management. While contemporary research frequently attempts to maximize absolute accuracy by deploying opaque deep learning architectures, the underlying data mechanics driving longitudinal predictive decay remain underexplored. Consequently, this study provides an explainable temporal robustness analysis of network-wide railway delay prediction. Focusing on the Dutch railway network, this research utilizes interpretable tree-based ensembles to integrate granular topological, environmental, and operational features. The overarching finding establishes that while feature-rich tree-based models improve simultaneous (within-month) prediction, predictive performance systematically degrades when evaluated across non-simultaneous (future) months. Furthermore, multi-horizon SHAP and dispersion analyses explicitly link this degradation to environmental feature volatility and instability within the statistical target definition. Ultimately, this thesis demonstrates that richer feature sets alone are insufficient to resolve long-term forecasting constraints, underscoring the necessity to transition toward dynamic, season-aware architectures anchored by absolute operational boundaries.
Machine Learning (cs.LG)
arXiv:2609.34692 [cs.LG]
(or arXiv:2609.34692v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.34692 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 241 cuvinte
Subiecte conexe
Toward Reliable Railway-Bogie Response Prediction Using Multifidelity TDNN and Physics-Informed Residual Learning
arXiv · 14 sept. 2026
A Theoretical Analysis of Generalization Dynamics in Neural Networks under Gradient Descent with Weight Decay
arXiv · 9 sept. 2026
Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident
METR · 26 aug. 2026
Returning to ARC
AI Alignment Forum · 4 aug. 2026