Pro-cycling team cyclist assignment for an upcoming race
- PMID: 38437185
- PMCID: PMC10911621
- DOI: 10.1371/journal.pone.0297270
Pro-cycling team cyclist assignment for an upcoming race
Abstract
Professional bicycle racing is a popular sport that has attracted significant attention in recent years. The evolution and ubiquitous use of sensors allow cyclists to measure many metrics including power, heart rate, speed, cadence, and more in training and racing. In this paper we explore for the first time assignment of a subset of a team's cyclists to an upcoming race. We introduce RaceFit, a model that recommends, based on recent workouts and past assignments, cyclists for participation in an upcoming race. RaceFit consists of binary classifiers that are trained on pairs of a cyclist and a race, described by their relevant properties (features) such as the cyclist's demographic properties, as well as features extracted from his workout data from recent weeks; as well additional properties of the race, such as its distance, elevation gain, and more. Two main approaches are introduced in recommending on each stage in a race and aggregate from it to the race, or on the entire race. The model training is based on binary label which represent participation of cyclist in a race (or in a stage) in past events. We evaluated RaceFit rigorously on a large dataset of three pro-cycling teams' cyclists and race data achieving up to 80% precision@i. The first experiment had shown that using TP or STRAVA data performs the same. Then the best-performing parameters of the framework are using 5 weeks time window, imputation was effective, and the CatBoost classifier performed best. However, the model with any of the parameters performed always better than the baselines, in which the cyclists are assigned based on their popularity in historical data. Additionally, we present the top-ranked predictive features.
Copyright: © 2024 Sagi et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Conflict of interest statement
The authors have declared that no competing interests exist.
Figures
![Fig 1](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/10911621/bin/pone.0297270.g001.gif)
![Fig 2](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/10911621/bin/pone.0297270.g002.gif)
![Fig 3](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/10911621/bin/pone.0297270.g003.gif)
![Fig 4](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/10911621/bin/pone.0297270.g004.gif)
![Fig 5](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/10911621/bin/pone.0297270.g005.gif)
![Fig 6](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/10911621/bin/pone.0297270.g006.gif)
![Fig 7](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/10911621/bin/pone.0297270.g007.gif)
![Fig 8](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/10911621/bin/pone.0297270.g008.gif)
![Fig 9](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/10911621/bin/pone.0297270.g009.gif)
Similar articles
-
Passing distance, speed and perceived risks to the cyclist and driver in passing events.J Safety Res. 2023 Dec;87:86-95. doi: 10.1016/j.jsr.2023.09.007. Epub 2023 Sep 16. J Safety Res. 2023. PMID: 38081726
-
Research on the Circumstances of a Car-Cyclist Collision, Based on the Trajectory of the Cyclist's Movement after the Collision.Sensors (Basel). 2022 Aug 23;22(17):6324. doi: 10.3390/s22176324. Sensors (Basel). 2022. PMID: 36080781 Free PMC article.
-
Are you an ambitious cyclist? Results of the cyclist profile questionnaire in Germany.Traffic Inj Prev. 2019;20(sup3):10-15. doi: 10.1080/15389588.2019.1702647. Epub 2020 Jan 6. Traffic Inj Prev. 2019. PMID: 31906722
-
Science and cycling: current knowledge and future directions for research.J Sports Sci. 2003 Sep;21(9):767-87. doi: 10.1080/0264041031000102097. J Sports Sci. 2003. PMID: 14579871 Review.
-
Applied physiology of cycling.Sports Med. 1984 May-Jun;1(3):187-204. doi: 10.2165/00007256-198401030-00003. Sports Med. 1984. PMID: 6390601 Review.
References
-
- Mignot JF. The history of professional road cycling. In: The Economics of Professional Road Cycling. Springer; 2016. p. 7–31.
-
- Sagi M, Saldanha P, Shani G, Moskovitch R. In: ECML PKDD 2022 Workshop on Machine Learning and Data Mining for Sports Analytics; 2022.
-
- Internationale UC. UCI Cycling Regulations Part I—General Organisation of Cycling as a Sport; 2022. Available from: https://assets.ctfassets.net/761l7gh5x5an/wQympSG6EWlKq6o6HKw9E/d4f7039c....
-
- Internationale UC. UCI Cycling Regulations Part II—Road Races; 2022. Available from: https://assets.ctfassets.net/761l7gh5x5an/7MLz0Fo06hpqNvEvrlXaf2/b5ffbf4....
-
- Training Peaks Fitness App. Available from: https://www.trainingpeaks.com.
MeSH terms
Grants and funding
LinkOut - more resources
Full Text Sources
Miscellaneous