Predicting the next Pogačar: a data analytical approach to detect young professional cycling talents

Abstract

The importance of young athletes in the field of professional cycling has sky-rocketed during the past years. Nevertheless, the early talent identification of these riders largely remains a subjective assessment. Therefore, an analytical system which automatically detects talented riders based on their freely available youth results should be installed. However, such a system cannot be copied directly from related fields, as large distinctions are observed between cycling and other sports. The aim of this paper is to develop such a data analytical system, which leverages the unique features of each race and thereby focusses on feature engineering, data quality, and visualization. To facilitate the deployment of prediction algorithms in situations without complete cases, we propose an adaptation to the k-nearest neighbours imputation algorithm which uses expert knowledge. Overall, our proposed method correlates strongly with eventual rider performance and can aid scouts in targeting young talents. On top of that, we introduce several model interpretation tools to give insight into which current starting professional riders are expected to perform well and why.

360 Degrees rumor detection: When explanations got some explaining to do

“…Following the aforementioned discussion, we define explanation instability as the phenomenon where slight changes in the training data result into different global explanations. The possible existence of such instability is especially worrisome in studies who follow a cross-validated experimental set-up, where algorithmic interpretation is typically based upon one fold (Janssens et al, 2022). However, no prior study investigated whether global model explanations are stable across folds and whether different algorithms tend to deliver more stable interpretations compared to others.…”

Uncovering Success Patterns in Track Cycling: Integrating Performance Data with Coaches and Athletes’ Perspectives

“…The identification of reliable performance markers plays a crucial role in physiology research and applied studies, aiding in training planning and talent selection [6,7]. While many studies have focused on describing the physiological profiles and training responses of youth and elite cyclists of different disciplines [3,10,[27][28][29], track cycling remains an area with relatively limited investigation [2].…”

“…In this context, the examination of potential markers that can forecast future success among youth category cyclists has emerged as a concept of great significance [4][5][6]. The importance of this lies in the far-reaching implications for coaches and practitioners in their final decision-making processes, the opportunities presented to athletes by national and international federations, and the athletes themselves as they navigate their career paths [4,6,7]. The consideration of reliable or unreliable indicators could profoundly impact these stakeholders and shape the trajectory of a cyclist's journey.…”

Exploiting sensor data in professional road cycling: personalized data-driven approach for frequent fitness monitoring

“…Here, the main focus is on the exercise intensity and in particular on the produced power (Leo et al 2021). A frequently used feature is the so-called power duration curve (Hunter et al 2019). This curve gives the maximum power that can be maintained by the cyclist for any given time period.…”