Optimizing recovery is crucial for maintaining performance and reducing fatigue and injury risk in youth football players. This study applied machine learning (ML) models to classify mental fatigue in U15, U17, and U19 male players using wearable signals, tracking data, and psychophysiological features. Over six weeks, training loads were monitored via GPS, psychophysiological scales, and heart rate sensors, analyzing variables such as total distance, high-speed running, recovery state, and perceived exertion. The data preparation process involved managing absent values, applying normalization techniques, and selecting relevant features. A total of five ML models were evaluated: K-Nearest Neighbors (KNN), Gradient Boosting (XGBoost), Support Vector Machine (SVM), Random Forest (RF), and Decision Tree (DT). XGBoost, RF, and DT achieved high accuracy, while KNN underperformed. Using a correlation matrix, average speed (AvS) was the only variable significantly correlated with the rating of perceived exertion (RPE) (r = 0.142; p = 0.010). After dimensionality reduction, ML models were re-evaluated, with RF and DT performing best, followed by XGBoost and SVM. These findings confirm that tracking and wearable-derived data are effectively useful for predicting RPE, providing valuable insights for workload management and personalized recovery strategies. Future research should integrate psychological and interpersonal factors to enhance predictive modeling in the individual long-term health and performance of young football players.

Background: This study examined training-to-match transferability of positional coordination in semi-professional football players, comparing responses between defensive and midfield/offensive positional sectors. Methods: Twenty-nine players were monitored during the 2023–2024 season. Positional data and external load were collected using global positioning system (GPS) technology. Technical–tactical key performance indicators (KPI) were obtained from SportsBase. Internal training load was assessed using the rating of perceived exertion (RPE), and wellness status was evaluated using the Hooper Index (HI). Results: Official matches were associated with greater total distance, average and maximum speed, speed events, acceleration and deceleration events, and mechanical power outputs (p < 0.001), with the largest effects for maximum speed (d = 1.25), deceleration events (d = 1.14), speed events (d = 1.13), and relative mechanical power (d = 1.05). Positional responses showed distinct training-to-match patterns. In the defensive sector, the official matches showed higher spread rate (SR; p = 0.031, d = −1.83) and contraction time (CT; p = 0.007, d = −2.20). In the midfield/offensive sector, matches showed greater effective playing space, width, length, longitudinal synchronization, distance to sector centroid, and stretch index (p = 0.005–0.017; d = 1.73–2.61), whereas dyadic-distance variability was greater during training (p < 0.001, d = 4.46). Linear mixed-effects models confirmed greater locomotor and high-intensity demands during matches, while positional differences were more selective. No statistically robust tactical-sector differences were observed for KPIs, internal load, or wellness after adjustment for multiple comparisons. Conclusions: Training-to-match transferability was positional sector-dependent, with greater spatial expansion and longitudinal coordination in offensive players and higher overall locomotor demands during matches.