AP-GRIP evaluation framework for data-driven train delay prediction models : Systematic literature review
Yong, Tiong Kah ; Ma, Zhenliang and Palmqvist, Carl William LU
(2025)
In European Transport Research Review
17(1).
- Abstract
The surging demand for Intelligent Transportation Systems (ITS) to deliver advanced train-related Information for dispatchers and passengers has spurred the development of advanced train delay prediction models. Despite considerable efforts devoted to developing methodologies that can be used to model train operation conditions and produce anticipated train delays, the evaluation strategies for train delay prediction models remain under-researched, particularly evident when accuracy is always found to be the only determinant in model selection. The absence of a standardised evaluation procedure for assessing the effectiveness of these prediction models has hindered the practical implementation of these models. To bridge this gap, the... (More)
The surging demand for Intelligent Transportation Systems (ITS) to deliver advanced train-related Information for dispatchers and passengers has spurred the development of advanced train delay prediction models. Despite considerable efforts devoted to developing methodologies that can be used to model train operation conditions and produce anticipated train delays, the evaluation strategies for train delay prediction models remain under-researched, particularly evident when accuracy is always found to be the only determinant in model selection. The absence of a standardised evaluation procedure for assessing the effectiveness of these prediction models has hindered the practical implementation of these models. To bridge this gap, the study conducted a systematic literature review on data-driven train delay prediction models and introduced the novel AP-GRIP (Accuracy, Precision, Generalisability, Robustness, Interpretability, Practicality) evaluation framework. The framework covers six key aspects across overall, spatial, temporal, and train-specific dimensions, providing a systematic approach for the comprehensive assessment of train delay prediction models. Each aspect and dimension is thoroughly discussed and synthesised with its definitions, measuring metrics, and important considerations. A critical discussion clarifies several interactions, such as predetermined objectives, desired outputs, model type, benchmark models, and data availability, resulting in a logical framework for assessing train delay prediction models. The proposed framework uncovers inadequate prediction patterns, offering insights on when, where, and why the prediction models excel and fall short, assisting end-users in determining model suitability for specific prediction tasks.
(Less)
- author
- Yong, Tiong Kah
; Ma, Zhenliang
and Palmqvist, Carl William
LU
- organization
- publishing date
- 2025-03-10
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Data-driven, Machine learning, Performance evaluation, Train delay prediction
- in
- European Transport Research Review
- volume
- 17
- issue
- 1
- article number
- 13
- publisher
- Springer
- external identifiers
-
- scopus:86000771629
- ISSN
- 1867-0717
- DOI
- 10.1186/s12544-024-00704-7
- project
- Utvärdering av ankomstprognoser för tåg
- language
- English
- LU publication?
- yes
- additional info
- Publisher Copyright: © The Author(s) 2025.
- id
- 8e8821ab-2c6b-453b-969d-06e8377c594d
- date added to LUP
- 2025-03-26 22:04:50
- date last changed
- 2025-04-04 14:47:04
@article{8e8821ab-2c6b-453b-969d-06e8377c594d,
abstract = {{<p>The surging demand for Intelligent Transportation Systems (ITS) to deliver advanced train-related Information for dispatchers and passengers has spurred the development of advanced train delay prediction models. Despite considerable efforts devoted to developing methodologies that can be used to model train operation conditions and produce anticipated train delays, the evaluation strategies for train delay prediction models remain under-researched, particularly evident when accuracy is always found to be the only determinant in model selection. The absence of a standardised evaluation procedure for assessing the effectiveness of these prediction models has hindered the practical implementation of these models. To bridge this gap, the study conducted a systematic literature review on data-driven train delay prediction models and introduced the novel AP-GRIP (Accuracy, Precision, Generalisability, Robustness, Interpretability, Practicality) evaluation framework. The framework covers six key aspects across overall, spatial, temporal, and train-specific dimensions, providing a systematic approach for the comprehensive assessment of train delay prediction models. Each aspect and dimension is thoroughly discussed and synthesised with its definitions, measuring metrics, and important considerations. A critical discussion clarifies several interactions, such as predetermined objectives, desired outputs, model type, benchmark models, and data availability, resulting in a logical framework for assessing train delay prediction models. The proposed framework uncovers inadequate prediction patterns, offering insights on when, where, and why the prediction models excel and fall short, assisting end-users in determining model suitability for specific prediction tasks.</p>}},
author = {{Yong, Tiong Kah and Ma, Zhenliang and Palmqvist, Carl William}},
issn = {{1867-0717}},
keywords = {{Data-driven; Machine learning; Performance evaluation; Train delay prediction}},
language = {{eng}},
month = {{03}},
number = {{1}},
publisher = {{Springer}},
series = {{European Transport Research Review}},
title = {{AP-GRIP evaluation framework for data-driven train delay prediction models : Systematic literature review}},
url = {{http://dx.doi.org/10.1186/s12544-024-00704-7}},
doi = {{10.1186/s12544-024-00704-7}},
volume = {{17}},
year = {{2025}},
}