Dr. Ulloa-Díaz, David

Background: This study aimed to explore whether a predictive model based on body composition and physical condition could estimate seasonal playing time in professional soccer players. Methods: 24 professional soccer players with 5–7 years of professional experience participated. Body composition and physical condition variables were assessed, and total minutes played during the season were recorded as the dependent variable. Correlations between variables were examined to reduce multicollinearity, followed by a principal component analysis (PCA) of the selected predictors. The first three components were used as inputs in a Gradient Boosting model. Model performance was evaluated using 5-fold cross-validation and leave-one-out cross-validation (LOOCV). Results: High intercorrelations among independent variables (r > 0.70) justified dimensionality reduction through PCA. The first three components explained 70% of the total variance. However, no direct correlations were observed between individual variables and minutes played, and the Gradient Boosting model did not achieve positive predictive performance under cross-validation (5-fold CV: R2 = −0.04; LOOCV: R2 < 0). Conclusion: In this small dataset, a multivariate approach combining PCA and Gradient Boosting did not yield predictive accuracy for playing time. Nonetheless, the PCA revealed meaningful structures in the players’ physical and body composition profiles, which may inform future research. Larger and more heterogeneous samples are required to determine whether component-based predictors can reliably estimate playing time in professional soccer.

The objectives of this revision were to identify game indicators, the references for evaluating tactical efficiency, and the types of data analysis used in invasion team sports for the analysis of tactical performance. A search of the principal electronic databases was carried out, the procedure was adjusted to the PRISMA-P 2015 protocol, and 62 non-experimental published articles were obtained from the years 2000–2016. The results showed the complimentary use of diverse types of indicators and the frequent elaboration of instruments ad hoc. The individual technical-tactical actions were widely used. The record of standardised team actions was scarce. The research lines with a sequential data record for their temporary analysis were significant. The transitory or final score and the results of game sequences were the most used references of performance. The big data tools of analysis, web analysis, and the detection of temporal patterns or the application of polar coordinates were emerging methods of analysis.