Determinants of Cycling Performance: a Review of the Dimensions and Features Regulating Performance in Elite Cycling Competitions

Phillips, Kathryn E.; Hopkins, William G.

doi:10.1186/s40798-020-00252-z

Cited by 47 publications

(42 citation statements)

References 96 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For ranked results, this [2000,2005,2010] can for example be done by calculating Kendell's tau (Kendall, 1938) or Spearman's rho (Spearman, 1987) to the real result of the race. However, in many sports and specifically in road cycling, there are multiple external factors (e.g., crashes, weather, and injuries) that influence the results and cannot be captured in a data-driven approach (Phillips and Hopkins, 2020). Thus, for a fair evaluation, the performance of sports prediction algorithms is usually compared to a benchmark prediction.…”

Section: Resultsmentioning

confidence: 99%

A Learn-to-Rank Approach for Predicting Road Cycling Race Outcomes

Kholkine

Servotte

Leeuw

et al. 2021

Front. Sports Act. Living

View full text Add to dashboard Cite

Professional road cycling is a very competitive sport, and many factors influence the outcome of the race. These factors can be internal (e.g., psychological preparedness, physiological profile of the rider, and the preparedness or fitness of the rider) or external (e.g., the weather or strategy of the team) to the rider, or even completely unpredictable (e.g., crashes or mechanical failure). This variety makes perfectly predicting the outcome of a certain race an impossible task and the sport even more interesting. Nonetheless, before each race, journalists, ex-pro cyclists, websites and cycling fans try to predict the possible top 3, 5, or 10 riders. In this article, we use easily accessible data on road cycling from the past 20 years and the Machine Learning technique Learn-to-Rank (LtR) to predict the top 10 contenders for 1-day road cycling races. We accomplish this by mapping a relevancy weight to the finishing place in the first 10 positions. We assess the performance of this approach on 2018, 2019, and 2021 editions of six spring classic 1-day races. In the end, we compare the output of the framework with a mass fan prediction on the Normalized Discounted Cumulative Gain (NDCG) metric and the number of correct top 10 guesses. We found that our model, on average, has slightly higher performance on both metrics than the mass fan prediction. We also analyze which variables of our model have the most influence on the prediction of each race. This approach can give interesting insights to fans before a race but can also be helpful to sports coaches to predict how a rider might perform compared to other riders outside of the team.

show abstract

Section: Resultsmentioning

confidence: 99%

A Learn-to-Rank Approach for Predicting Road Cycling Race Outcomes

Kholkine

Servotte

Leeuw

et al. 2021

Front. Sports Act. Living

View full text Add to dashboard Cite

show abstract

“…air and rolling resistance) that influence cycling power output, velocity, and winning probability. For a general overview of these factors we refer to Atkinson et al (2003), Faria et al (2005b, a) and Phillips and Hopkins (2020), and we refer to Lucia et al (2003) for an overview of the physiological aspects in the Tour de France. For scouts, these studies could be of interest since they could help to identify the relevant physiological measures that are required to excel at a later age (Svendsen et al 2018;Menaspà et al 2010), or to orient cyclists towards their best discipline (see Mostaert et al 2020).…”

Section: Related Literaturementioning

confidence: 99%

Result-based talent identification in road cycling: discovering the next Eddy Merckx

2021

View full text Add to dashboard Cite

In various sports large amounts of data are nowadays collected and analyzed to help scouts with identifying talented young athletes. In contrast, the literature on result-based talent identification in road cycling is remarkably scarce. The purpose of this paper is to provide insight into the possibilities of the use of publicly available data to discover new talented Under-23 (U23) riders via statistical learning methods (linear regression and random forest techniques). At the same time, we try to find out the main determinants of success for U23 riders in their first years of professional cycling. We collect results for more than 25000 road cycling races from 2007–2018 and consider more than 2500 riders from over 80 countries. We use the data from 2007 to 2017 to train and validate our models, and use the data from 2018 to predict how well U23 riders will perform in their first three elite years. Our results reveal that past U23 race results appear to be important predictors of future cycling performance.

show abstract

“…This review focuses heavily on the physical data obtained from a cycling power metre. However, a comprehensive model of cycling also involves the technical, tactical and psychological event demands and rider physiological characteristics [ 21 ]. The outcome should enhance the ability to use power meter data and physiological measures to model sprint-cycling, to guide coaching and optimise performance.…”

Section: Introductionmentioning

confidence: 99%

Using Field Based Data to Model Sprint Track Cycling Performance

2021

View full text Add to dashboard Cite

Cycling performance models are used to study rider and sport characteristics to better understand performance determinants and optimise competition outcomes. Performance requirements cover the demands of competition a cyclist may encounter, whilst rider attributes are physical, technical and psychological characteristics contributing to performance. Several current models of endurance-cycling enhance understanding of performance in road cycling and track endurance, relying on a supply and demand perspective. However, they have yet to be developed for sprint-cycling, with current athlete preparation, instead relying on measures of peak-power, speed and strength to assess performance and guide training. Peak-power models do not adequately explain the demands of actual competition in events over 15-60 s, let alone, in World-Championship sprint cycling events comprising several rounds to medal finals. Whilst there are no descriptive studies of track-sprint cycling events, we present data from physiological interventions using track cycling and repeated sprint exercise research in multiple sports, to elucidate the demands of performance requiring several maximal sprints over a competition. This review will show physiological and power meter data, illustrating the role of all energy pathways in sprint performance. This understanding highlights the need to focus on the capacity required for a given race and over an event, and therefore the recovery needed for each subsequent race, within and between races, and how optimal pacing can be used to enhance performance. We propose a shift in sprint-cyclist preparation away from training just for peak power, to a more comprehensive model of the actual event demands.

show abstract

Determinants of Cycling Performance: a Review of the Dimensions and Features Regulating Performance in Elite Cycling Competitions

Cited by 47 publications

References 96 publications

A Learn-to-Rank Approach for Predicting Road Cycling Race Outcomes

A Learn-to-Rank Approach for Predicting Road Cycling Race Outcomes

Result-based talent identification in road cycling: discovering the next Eddy Merckx

Using Field Based Data to Model Sprint Track Cycling Performance

Contact Info

Product

Resources

About