No abstract

One of the great challenges for football coaches is to choose the football line-up that gives more guarantees of success. Even though there are several dimensions to analyse the problem, such as the opposing team characteristics. The objective of this study is to identify, based on the players’ physiological variables collected using Global Positioning Systems (GPS), which players are the most suitable to be part of the starting team/line-up. The work was developed in two stages, first with the choice of the most important variables using the Recursive Feature Elimination algorithm, and then using logistic regression on these chosen variables. The logistic regression resulted in an index, called the line-up preparedness index, for the following player positions: Fullbacks, Central Midfielders and Wingers. For the other players’ positions, the model results were not satisfactory.

Ensuring adequate levels of training and recovery to maximize player performance is critical; however, there are methodological challenges in designing a periodized training program for soccer teams. This study aims to describe and characterize the daily and weekly external load in an amateur soccer team and based on the weighting factors determined by the match reference, compare the external loads between playing positions. Twenty-four amateur soccer players (22.3 ± 1.7 years) were monitored using a global positioning system. Data collected comprises 19 competitive microcycles with a standard structure composed of 3 training sessions (matchday-5, matchday-3, and matchday-2) and one match. Match-reference values were calculated as the mean of the five best values recorded during official matches. The results show, on matchday-5 session, the existence of significant differences between playing positions to relative total distance covered (p = 0.050), relative sprint distance (p = 0.001), relative moderate-intensity accelerations (p < 0.001), relative high-intensity accelerations (p = 0.003), relative moderate-intensity decelerations (p < 0.001), and relative high-intensity decelerations (p = 0.017). On matchday-3 session, there are significant differences to relative very high-speed running distance (p = 0.017) and relative moderate-intensity decelerations (p = 0.014). On matchday-2 session, there are significant differences to relative high-speed running distance (p = 0.025), relative very high-speed running distance (p = 0.008), and relative moderate-intensity decelerations (p < 0.001). Weekly significant differences are observed between the playing positions to relative moderate-intensity accelerations (p = 0.002), relative high-intensity accelerations (p < 0.001), and relative moderate-intensity decelerations (p < 0.001). The weekly load is characterized by a greater weighting on accelerations and decelerations, compared to distances at very-high speed and sprint. The training loads must respect a standard training model that contemplates the individualization of the physical demands of the match, for each playing position, as for each individual.