EUROPT 2024
Abstract Submission

124. Formulation of an ML-based model for the Assessment of Maximum Sprint Capability in Elite Soccer Players

Invited abstract in session WD-7: Optimization applications II, stream Optimization applications.

Wednesday, 11:25 - 12:40
Room: M:I

Authors (first author is the speaker)

1. Edoardo Cesaroni
Department of Computer, Control, and Management Engineering Antonio Ruberti, Università di Roma "La Sapienza"

Abstract

In recent years, machine learning techniques have gained widespread popularity, fueled by the availability of vast amounts of data across various industries.
The sports industry, including football, has also embraced these techniques to gain a competitive edge.
In our work, we focus on estimating and analyzing the maximum acceleration
capability of football players using tracking data, which defines the player’s position on the field at each frame during a match. This information can contribute to more precise tactical preparation and personalized training strategies.
We then develop a regression-based model that reconstructs a profile per player, capturing the relationship between acceleration and speed during a maximum sprint when the athlete performs at their peak capability.
By applying this model to data sampled at regular intervals during a match, we can identify variations in this profile, which reflect changes in the player’s physical condition. It also allows us to evaluate how the time it takes for a player to cover specific distances at a certain initial speed varies over 90 minutes.
Furthermore, we employ clustering, to identify players with similar athletic characteristics and performance. This approach deepens our understanding of player capabilities and enables data-driven decision-making in sports analysis and training. It provides a deeper level of insight into player performance, facilitating player evaluation.

Keywords

Status: accepted

Back to the list of papers