APPLYING THE PRINCIPLES OF JOHAN CRUYFF TO DATA SCIENCE
With such an ambitious goal, the Barça Innovation Hub has presented its research at this year’s world-renowned MIT Sloan Sports Analytics international conference.
Of all the variables provided by the systems that monitor and record our players’ activity, what is the most relevant information? This is a question that all coaches will probably face when they begin managing the large volumes of data generated in every training session. However, in most cases, the choice of variables does not actually follow a systematic process, but rather depends on the users’ personal preferences, which are sometimes haunted by trends in the use of variables that have not yet been sufficiently contrasted.
The high quantity of variables supplied by the technological tools available today has made it necessary to study and reduce the number of variables to be managed in the training process. This is why we must choose the most valid options available in order to understand the demands of the sports activity in question. We have to be practical and make this arduous recording process sustainable; in other words, we should take into account the available temporal, material, human and technological resources in such a way that the cost-benefit relationship is as efficient as possible.
Among other options, the implementation of principal components analysis makes it possible to identify the variables that supply the most information, differentiating between those that supply complementary information and those that supply redundant information. This drastically reduces the number of variables or dimensions to study. In the work being presented, the authors recorded different intensity measurements during training tasks and official soccer matches.
The main findings of this study indicate that three main components are needed to summarize the different intensity measurements, and these offer different weightings or degrees of importance depending on the game format being studied. Regardless of the game format being studied, the 1st component accounts for 40% to 45% of the variance, with average metabolic power being the variable with the greatest weight. The 2nd component accounts for between 20% and 25% of the variance, and this is represented by speed variables (e.g., distance covered at high speed, distance covered at sprint, and peak speed). Lastly, the 3rd component accounts for between 10% and 15% of the variance, in which the inertial variables (dynamic stress load, or DSL, and impact) are grouped.
Thus a practical application of this study indicates that in order to collect the majority of the external load information, regardless of the game format being studied, we need to consider locomotor or strength variables, speed variables, and inertial variables. In short, we would need to consider the following indicators:
Nevertheless, when game formats change, the importance of the variables within the main component also changes. In small positional play of 4 vs. 4 + 3 in a space of 13 x 17 m, the speed variable that provides the most information is peak speed, followed by distance covered at high speed. For example, in 10 vs 10 situations played in 105 x 65 m, the variable that provides the most information within the second main component is distance covered at sprint, followed by distance covered at high speed, and peak speed. Thus the weight of each variable changes depending on the game format being studied.
In the process of choosing variables for the subsequent management of training and competition loads, we must try not to duplicate information; only the indicators needed to obtain valid and applicable information should be chosen (Castellano and Casamichana, 2016).
David Casamichana – Strength and Conditioning Coach at Real Sociedad
Antonio Gomez – Strength and Conditioning Coach at FC Barcelona
Julen Castellano – Head of the Doctoral Program in Physical Activity and Sports at the University of the Basque Country (UPV/EHU)
Andrés Martin – Strength and Conditioning Coach at FC Barcelona
Gestión de carga de trabajo. Barca Innovation Hub. https://barcainnovationhub.com/es/product/certificado-en-gestion-de-la-carga-de-trabajo-en-futbol/
Castellano, J. and Casamichana, D. (2016). El arte de planificar en fútbol. Futboldelibro.
Mental abilities, although not yet fully appreciated, are already considered a relevant part of performance. But their importance could go beyond that: Do they also influence the injury risk, including recurrence, once the player returns to play?
Although several studies have tried to evaluate the characteristics of the risk of injury in handball players, they have been unable to reach sufficiently reliable conclusions. A new study of all the FC Barcelona handball categories has attempted to shed more light on the subject.
Although there are several studies on this topic, many of them have analyzed these demands by looking at just a few variables or using very broad timeframes. A new study completed by physical trainers from F.C. Barcelona has analyzed several of these details more closely.
An article published in The Orthopaedic Journal of Sports Medicine —in which members of the club’s medical services participated— now suggests to consider the detailed structure of the area affected, and treating the extracellular matrix as an essential player in the prognosis of the injury.
In this article, Tim Gabbett and his team provide a user-friendly guide for practitioners when describing the general purpose of load management to coaches.
For the first time, it has been demonstrated that it does not take months of training to significantly improve both muscle volume and strength; instead, two weeks of an appropriate exercise are enough.
The understanding of the modifying variables of the game, based on the degrees of freedom.
Training using eccentric exercises is important to prevent possible damage. However, intensive training can also cause muscle damage, so it is critical to be vigilant in order to keep injury risk to an absolute minimum.
The importance of building a game model in football.
Cardiovascular endurance manifests as a moderator of the load result to which the athlete is exposed.
Through the use of computer vision we can identify some shortcomings in the body orientation of players in different game situations.