PerfoRank : cluster-based performance ranking for improved performance evaluation and estimation in professional cycling
- Author
- Bram Janssens (UGent) and Matthias Bogaert (UGent)
- Organization
- Project
- Abstract
- Current cycling analytics solutions do not account for the race course profle or the level of the competition. Therefore, this paper develops a unique two-stage clustering-based ranking approach for rider evaluation. Initially, races are segmented into coherent clusters based upon elevation and road surface type. Subsequently, underlying skill levels are determined per cluster through the observed race results using the TrueSkill algorithm which allows to model multi-entrant competitions. The results indicate that our approach uncovers clusters which match the commonly known specializations in road cycling. The ranking methodology generates skill ratings which enable the identifcation of specialization and can be used in downstream tasks. Our results show that the proposed rankings drastically improve race outcome estimation when adding these rankings as features to the current prediction models.
- Keywords
- Sports analytics, Cycling analytics, Performance evaluation, Ranking algorithms, Statistically enhanced learning
Downloads
-
(...).pdf
- full text (Published version)
- |
- UGent only
- |
- |
- 1.84 MB
-
Janssens B et al Accepted Manuscript.docx
- full text (Accepted manuscript)
- |
- open access
- |
- Word
- |
- 1.25 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-01JNN9709MJD53BDVZ7CXYKQXC
- MLA
- Janssens, Bram, and Matthias Bogaert. “PerfoRank : Cluster-Based Performance Ranking for Improved Performance Evaluation and Estimation in Professional Cycling.” MACHINE LEARNING, vol. 114, no. 1, 2025, doi:10.1007/s10994-024-06716-7.
- APA
- Janssens, B., & Bogaert, M. (2025). PerfoRank : cluster-based performance ranking for improved performance evaluation and estimation in professional cycling. MACHINE LEARNING, 114(1). https://doi.org/10.1007/s10994-024-06716-7
- Chicago author-date
- Janssens, Bram, and Matthias Bogaert. 2025. “PerfoRank : Cluster-Based Performance Ranking for Improved Performance Evaluation and Estimation in Professional Cycling.” MACHINE LEARNING 114 (1). https://doi.org/10.1007/s10994-024-06716-7.
- Chicago author-date (all authors)
- Janssens, Bram, and Matthias Bogaert. 2025. “PerfoRank : Cluster-Based Performance Ranking for Improved Performance Evaluation and Estimation in Professional Cycling.” MACHINE LEARNING 114 (1). doi:10.1007/s10994-024-06716-7.
- Vancouver
- 1.Janssens B, Bogaert M. PerfoRank : cluster-based performance ranking for improved performance evaluation and estimation in professional cycling. MACHINE LEARNING. 2025;114(1).
- IEEE
- [1]B. Janssens and M. Bogaert, “PerfoRank : cluster-based performance ranking for improved performance evaluation and estimation in professional cycling,” MACHINE LEARNING, vol. 114, no. 1, 2025.
@article{01JNN9709MJD53BDVZ7CXYKQXC,
abstract = {{Current cycling analytics solutions do not account for the race course profle or the level of
the competition. Therefore, this paper develops a unique two-stage clustering-based ranking approach for rider evaluation. Initially, races are segmented into coherent clusters based
upon elevation and road surface type. Subsequently, underlying skill levels are determined
per cluster through the observed race results using the TrueSkill algorithm which allows to
model multi-entrant competitions. The results indicate that our approach uncovers clusters
which match the commonly known specializations in road cycling. The ranking methodology generates skill ratings which enable the identifcation of specialization and can be
used in downstream tasks. Our results show that the proposed rankings drastically improve
race outcome estimation when adding these rankings as features to the current prediction
models.}},
articleno = {{20}},
author = {{Janssens, Bram and Bogaert, Matthias}},
issn = {{0885-6125}},
journal = {{MACHINE LEARNING}},
keywords = {{Sports analytics,Cycling analytics,Performance evaluation,Ranking algorithms,Statistically enhanced learning}},
language = {{eng}},
number = {{1}},
pages = {{30}},
title = {{PerfoRank : cluster-based performance ranking for improved performance evaluation and estimation in professional cycling}},
url = {{http://doi.org/10.1007/s10994-024-06716-7}},
volume = {{114}},
year = {{2025}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: