The aims of this study were to analyse the physical responses of professional soccer players during training considering the contextual factors of match location, season period, and quality of the opposition; and to establish prediction models of physical responses during training sessions. Training data was obtained from 30 professional soccer players from Spanish La Liga using global positioning technology (N=1365 performances). A decreased workload was showed during training weeks prior to home matches, showing large effects in power events, equivalent distance, total distance, walk distance and low-speed running distance. Also, the quality of the opposition also affected the training workload (p<0.05). All regression-models showed moderate effects, with an adjusted R2 of 0.37 for metabolic-work, 0.34 for total distance covered, 0.25 for high-speed running distance (18–21 km·h−1), 0.29 for very high-speed running distance (21–24 km·h−1), 0.22 for sprint running distance (>24 km·h−1) and 0.34 for equivalent distance. The main finding of this study was the great association of match location, season period and quality of opposition on the workload performed by players in the training week before the match; and the development of workload prediction-models considering these contextual factors, thus proposing a new and innovative approach to quantify the workload in soccer.

The aim of this study was to examine whether match physical output can be predicted from the workload applied in training by professional soccer players. Training and match load records from two professional soccer teams belonging to the Spanish First and Second Division were collected through GPS technology over a season ( N = 1678 and N = 2441 records, respectively). The factors playing position, season period, quality of opposition, category and playing formation were considered into the analysis. The level of significance was set at p ≤ .05. The prediction models yielded a conditional R-squared in match of 0.51 in total distance (TD); 0.58 in high-intensity distance (HIRD, from 14 to 24 km · h−1); and 0.60 in sprint distance (SPD, >24 km·h−1). The main finding of this study was that the physical output of players in the match was predicted from the training-load performed during the previous training week. The training-TD negatively affected the match physical output while the training-HIRD showed a positive effect. Moreover, the contextual factors – playing position, season period, division and quality of opposition – affected the players’ physical output in the match. Therefore, these results suggest the appropriateness of programming lower training volume but increasing the intensity of the activity throughout the weekly microcycle, and considering contextual factors within the load programming.

Previous studies investigating running distance in high performance soccer have led to contradictory evidence, potentially due to ignoring contextual information during match phases. The present study therefore examined the relationship between running performance and goal scoring in a football match for a standardised score line. In a sample of 302 matches from the first German Bundesliga, the first goal was modelled as a function of the teams’ running performance and team strength using logistic regression. Goodness of fit was assessed by the prediction accuracy of the model utilising cross-validation. The best model showed a mean accuracy of 77%, reflecting a strong relationship between running performance and the probability of scoring the first goal. This relationship was strongest for total running distance compared to high-speed, sprint or in-possession running distance. We propose two different potential mechanisms to explain the relationship between running performance and goal-scoring found in the present study. These are (1) better ability to reach tactical aims or (2) accumulation of fatigue in the opponent. Future studies should build on these results by further examining the relationship between running performance and success using a more granular segmentation of matches.