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

Body Mass Index Trends for the Top Five Finishers in Men's Grand Tour and Monument Cycling Events from 1994-2023: Implications for Athletes and Sporting Stakeholders

Weight-related issues can be prevalent in elite-level sports, especially in men's road cycling, where riders may exhibit harmful behaviours, with potentially adverse outcomes for mental and physical health. This study investigated Body Mass Index (BMI) values amongst the top five finishers in the three Grand Tours and the five Monuments races between 1994 and 2023 to assess longitudinal patterns. Publicly available height and weight figures were sourced from ProCyclingStats and BMI scores were calculated for n = 154 and n = 255 individual athletes for the Grand Tours and Monuments, respectively. Two analyses were conducted with correlations and ANOVAs: the first included the BMIs of all top-five finishes and the second focussed on the BMIs of new top-five entrants. The results from both analyses revealed consistent mean BMI decreases over the years and larger effect sizes were apparent in the Grand Tours compared to the Monuments. Although lower BMIs are associated with certain performance advantages, these declining trajectories suggest a need for enhanced awareness in the cycling community and possible regulatory measures and educational programmes to promote the sustainable wellbeing of riders. This may be particularly pertinent given the wider evidence of unhealthy weight-related attitudes and behaviours throughout the sport.

Ultra-Cycling- Past, Present, Future: A Narrative Review

BACKGROUND

Ultra-endurance events are gaining popularity in multiple exercise disciplines, including cycling. With increasing numbers of ultra-cycling events, aspects influencing participation and performance are of interest to the cycling community.

MAIN BODY

The aim of this narrative review was, therefore, to assess the types of races offered, the characteristics of the cyclists, the fluid and energy balance during the race, the body mass changes after the race, and the parameters that may enhance performance based on existing literature. A literature search was conducted in PubMed, Scopus, and Google Scholar using the search terms 'ultracycling', 'ultra cycling', 'ultra-cycling', 'ultra-endurance biking', 'ultra-bikers' and 'prolonged cycling'. The search yielded 948 results, of which 111 were relevant for this review. The studies were classified according to their research focus and the results were summarized. The results demonstrated changes in physiological parameters, immunological and oxidative processes, as well as in fluid and energy balance. While the individual race with the most published studies was the Race Across America, most races were conducted in Europe, and a trend for an increase in European participants in international races was observed. Performance seems to be affected by characteristics such as age and sex but not by anthropometric parameters such as skin fold thickness. The optimum age for the top performance was around 40 years. Most participants in ultra-cycling events were male, but the number of female athletes has been increasing over the past years. Female athletes are understudied due to their later entry and less prominent participation in ultra-cycling races. A post-race energy deficit after ultra-cycling events was observed.

CONCLUSION

Future studies need to investigate the causes for the observed optimum race age around 40 years of age as well as the optimum nutritional supply to close the observed energy gap under consideration of the individual race lengths and conditions. Another research gap to be filled by future studies is the development of strategies to tackle inflammatory processes during the race that may persist in the post-race period.

Pro-cycling team cyclist assignment for an upcoming race

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.

Quantitative analysis of the dominant external factors influencing elite speed Skaters' performance using BP neural network

Introduction

Speed skating, being a popular winter sport, imposes significant demands on elite skaters, necessitating their effective assessment and adaptation to diverse environmental factors to achieve optimal race performance.

Objective

The aim of this study was to conduct a thorough analysis of the predominant external factors influencing the performance of elite speed skaters.

Methods

A total of 403 races, encompassing various race distances and spanning from the 2013 to the 2022 seasons, were examined for eight high-caliber speed skaters from the Chinese national team. We developed a comprehensive analytical framework utilizing an advanced back-propagation (BP) neural neural network model to assess three key factors on race performance: ice rink altitude, ice surface temperature, and race frequency.

Results

Our research indicated that the performance of all skaters improves with higher rink altitudes, particularly in races of 1,000 m and beyond. The ice surface temperature can either enhance or impaire performance and varies in its influences based on skaters' technical characteristics, which had a perceptible or even important influence on races of 1,500 m and beyond, and a negligible influence in the 500 m and 1,000 m races. An increase in race frequency generally contributed to better performance. The influence was relatively minor in the 500 m race, important in the 3,000 m race, and varied among individuals in the 1,000 m and 1,500 m races.

Conclusion

The study results offer crucial guidelines for speed skaters and coaches, aiding in the optimization of their training and competition strategies, ultimately leading to improved competitive performance levels.

Age of peak performance in professional road cycling

In this study, we investigated the relationship between age and performance in professional road cycling. We considered 1864 male riders present in the yearly top 500 ranking of ProCyclingStats (PCS) since 1993 until 2021 with more than 700 PCS Points. We applied a data-driven approach for finding natural clusters of the rider's speciality (General Classification, One Day, Sprinter or All-Rounder). For each cluster, we divided the riders into the top 50% and bottom 50% based on their total number of PCS points. The athlete's yearly performance was defined as the average number of points collected per race. Age-performance models were constructed using polynomial regression and we obtained that the top 50% of the riders in each cluster have a statistically significant (p < 0.05) higher peak performance age. Considering the best 50% of the riders, general classification riders peak at an older age than the other rider types (p < 0.05). For those top riders, we found ages of peak performance of 26.3, 26.5, 26.2 and 27.5 years for sprinters, all-rounders, one day specialists and general classification riders, respectively. Our findings can be used for scouting purposes, assisting coaches in designing long-term training programmes and benchmarking the athletes' performance development.

Construction of Women’s All-Around Speed Skating Event Performance Prediction Model and Competition Strategy Analysis Based on Machine Learning Algorithms

Introduction

Accurately predicting the competitive performance of elite athletes is an essential prerequisite for formulating competitive strategies. Women’s all-around speed skating event consists of four individual subevents, and the competition system is complex and challenging to make accurate predictions on their performance.

Objective

The present study aims to explore the feasibility and effectiveness of machine learning algorithms for predicting the performance of women’s all-around speed skating event and provide effective training and competition strategies.

Methods

The data, consisting of 16 seasons of world-class women’s all-around speed skating competition results, used in the present study came from the International Skating Union (ISU). According to the competition rules, distinct features are filtered using lasso regression, and a 5,000 m race model and a medal model are built using a fivefold cross-validation method.

Results

The results showed that the support vector machine model was the most stable among the 5,000 m race and the medal models, with the highest AUC (0.86, 0.81, respectively). Furthermore, 3,000 m points are the main characteristic factors that decide whether an athlete can qualify for the final. The 11th lap of the 5,000 m, the second lap of the 500 m, and the fourth lap of the 1,500 m are the main characteristic factors that affect the athlete’s ability to win medals.

Conclusion

Compared with logistic regression, random forest, K-nearest neighbor, naive Bayes, neural network, support vector machine is a more viable algorithm to establish the performance prediction model of women’s all-around speed skating event; excellent performance in the 3,000 m event can facilitate athletes to advance to the final, and athletes with outstanding performance in the 500 m event are more likely competitive for medals.