Predicting basketball game outcomes in elite competitions is a complex task influenced by multiple interacting performance factors. This study applied a supervised machine learning (ML) framework to predict EuroLeague game outcomes using team-level game-related statistics. Four algorithms—Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), and Naïve Bayes (NB)—were trained and compared following recursive feature elimination (RFE) to identify the most informative predictors. The dataset comprised comprehensive in-game statistics describing shooting efficiency, rebounding, ball security, and spatial shot distribution. Model performance was evaluated using accuracy, area under the receiver operating characteristic curve (AUC), precision, recall, and F1-score, ensuring both discrimination and calibration assessment. Among the four classifiers, SVM (AUC = 0.922, Accuracy = 0.841) and LR (AUC = 0.933, Accuracy = 0.818) achieved the highest predictive performance, outperforming RF and NB. Feature importance analysis using Shapley Additive Explanations (SHAP) on the best-performing SVM classifier revealed that true shooting percentage (TS%), defensive rebounds (DR), steals (ST), and turnovers (TO) were the most influential predictors of game outcomes. Teams that demonstrated higher shooting efficiency, greater rebounding control, and fewer turnovers showed a significantly higher probability of winning. These results confirm that well-validated and interpretable ML models can accurately predict game outcomes in professional basketball using readily available box-score statistics. The integration of RFE-based feature selection and SHAP interpretability provides transparent, evidence-based insights that can inform tactical decisions, enhance scouting accuracy, and support coaches in developing data-driven performance strategies within elite basketball environments.

Shooting is a fundamental basketball skill that critically influences game outcomes. The purpose of the present study was to compare the effectiveness of three-point shooting between the Euroleague and NCAA Division I during the 2020-21 season, evaluating factors such as shooting accuracy, player position, type of offense, and timing of shot execution. The analysis was based on the recording of 3,249 shots from 70 games. Results demonstrated higher shooting percentages in the Euroleague (38.4%) compared to the NCAA (35.1%). Differences were observed in the type of offense, with the NCAA exhibiting a higher proportion of fast-break (transition) plays, whereas the Euroleague primarily focuses on organized set plays. Shot execution timing emerged as the most significant differentiating factor between the two leagues. Player position also influenced effectiveness, with guards being the primary shooters, however, forwards in the Euroleague demonstrated higher efficiency compared to their NCAA counterparts. CHAID analysis confirmed the importance of shot timing, player position, and shooting effectiveness as critical discriminant factors, highlighting the Euroleague’s tendency towards more patient and tactically organized offenses in contrast to the faster and more intense style of play in the NCAA. These findings provide valuable insights for analysts and coaches to develop effective offensive tactics tailored to the specific characteristics of each competition.

The transition period in football can negatively affect players’ fitness indicators. However, if appropriate training programs are implemented during this period, these effects can be reversed. The purpose of this study was to investigate the effect of a high-frequency exercise program during the transition period on aerobic capacity, isokinetic torque of the lower limbs, jumping ability, and body composition. The transition period was divided into two phases: the first phase lasted two weeks and involved complete rest from exercise, and the second phase lasted four weeks during which the players completed three aerobic-focused training sessions and two maximum strength training sessions per week. A total of 13 young football players (age 17.8 ± 0.7 years, height 1.78 ± 0.07 m, weight 70.3 ± 8.4 kg) participated in the study. A paired samples t-test was applied, and statistical significance was set at p < 0.05. The results showed that players improved their maximal oxygen uptake (VO₂ max) after the program (p = 0.037, t = −2.348). The performance in countermovement jump performance and in the isokinetic torque of the right quadriceps showed a decline (p = 0.009, t = 3.112 & p = 0.004, t = 2.299, respectively), while no changes were observed in any other parameter (p > 0.05). The findings suggest that a program with these characteristics can counteract the negative effects typically observed during the transition period. Moreover, with specialized stimuli, improvement may also be observed during the transitional period.

The annual soccer training cycle consists of preparatory, competitive, and transition periods. The transition phase is usually characterized by a decrease in training volume, which may lead to detraining and declines in physical fitness. The aim of this study was to examine the effects of a structured transitional training program on anthropometric characteristics, aerobic capacity, and jumping performance in young soccer players. Twenty-three under-17 players participated in the study and, following a two-week period of training cessation, completed a three-week program that included aerobic training three times per week (continuous and interval running sessions) and strength progressive resistance training twice per week. Pre- and post-intervention measurements were analyzed using paired-samples t-tests, with statistical significance set at p < 0.05. The results revealed significant reductions in body fat percentage (p = 0.016, d = 0.547), body fat mass (p = 0.018, d = 0.535), and resting systolic blood pressure (p = 0.024, d = 0.507). Additionally, time to reach the anaerobic threshold (p = 0.022, d = −0.515) and movement speed at the anaerobic threshold (p = 0.029, d = −0.487) significantly increased. No significant changes were observed in the remaining variables. These findings indicate that a three-week transition-period training program combining structured aerobic running drills with progressive resistance training can induce favorable adaptations in selected anthropometric and physiological parameters in youth soccer players. However, the lack of a control group should be considered when interpreting the magnitude of the program’s effects.

Home advantage (HA) remains a persistent phenomenon in elite basketball. This study quantified HA across eight EuroLeague seasons (2016–2025) and examined how team quality (TQ) and competitive balance (CB) influence it. Data from 2,154 regular-season games were obtained from the official EuroLeague website. HA% and home win percentage (HW%) were calculated, while CB was measured using the Standard Deviation Ratio (SDR). TQ was determined using a Two-Step Cluster Analysis based on win percentage (W%), classifying teams into high, medium, or low-quality groups. One-way ANOVA examined seasonal and TQ variation, while Spearman's correlation and multiple regression assessed relationships among the variables. The results showed that EuroLeague teams won 62.9% of home games on average. HA% peaked in 2021–2022 and dropped in 2020–2021, reflecting the impact of pandemic-related spectator restrictions. CB fluctuated moderately, with a notable imbalance in 2018–2019 (CB = 2.17). Regression results showed that TQ significantly predicted HA% (p < .01), with lower-quality teams exhibiting greater HA% effects (B = 10.06, SE = 2.15), whereas CB was not a significant predictor (p = .088). HA remains a consistent structural phenomenon in EuroLeague basketball, more likely due to psychological and situational factors, resilient to changes in league parity.

This study evaluated shoulder rotator muscle strength, conventional and functional external/internal rotation (ER/IR) strength ratios, and fatigue responses in competitive male artistic gymnasts, compared to a control group consisting of physical education (PE) students. Twenty-six participants were included: 13 competitive gymnasts (22.7 ± 2.3 years) and 13 PE students (22.6 ± 1.5 years), free of shoulder disorders. Shoulder rotator muscle strength was assessed isometrically and isokinetically (60°·s⁻¹ and 180°·s⁻¹) before and after a fatigue protocol comprising 50 maximal concentric internal and external rotations at 240°·s⁻¹. Gymnasts demonstrated significantly higher body mass-normalized peak torque than PE students across the key strength conditions. Before fatigue, conventional and functional strength ratios were generally comparable between groups. Following fatigue, condition-specific changes in ER/IR strength ratios were observed, with gymnasts generally maintaining their pre-fatigue values. Normalized peak torque progressively declined across the 50-repetition protocol in both groups, with no significant between-group difference in the pattern or rate of torque decline. Exploratory analyses of derived fatigue-related measures showed limited and condition-specific between-group differences. Overall, competitive gymnasts demonstrated greater shoulder rotator strength capacity than PE students, whereas the findings did not support a generalized between-group difference in fatigue-related responses. Comprehensive assessment of shoulder strength, ER/IR strength ratios, and fatigue responses may provide useful information for performance monitoring and individualized training.