Understanding match performance from a productivity perspective has become increasingly important in professional football. Although previous studies have examined technical and physical performance indicators, limited research has evaluated productivity-based efficiency across different competitive contexts in the Chinese Super League (CSL). This study aims to model and evaluate team match performance using a productivity-based analytical framework. Data from 1,899 matches across the 2012–2019 CSL seasons were analysed. A two-stage methodological approach was adopted, integrating canonical correlation analysis (CCA) and an input-oriented variable returns-to-scale (VRS) DEA–Malmquist model. Technical and running-performance indicators were treated as input variables, while average points per match were used as the output measure. Contextual factors, including match location and opponent strength, were incorporated. CCA revealed a strong association between the input and output variables (canonical correlation = 0.931, p < 0.001). Technical variables—particularly ball possession and passing accuracy—were strongly associated with match performance productivity. The contribution of physical and defensive indicators varied depending on situational conditions. Higher-ranked teams tended to exhibit higher efficiency through a combination of attacking and defensive execution, whereas lower-ranked teams were more closely associated with basic technical control and physical output. Additionally, defensive actions were more relevant in matches against stronger opponents, while attacking efficiency was more prominent when facing weaker teams. Productivity-related performance patterns in the CSL appeared to be context dependent and varied according to team level, match location, and opponent strength. The findings support the application of a DEA–Malmquist productivity framework for evaluating football performance and provide practical insights for performance monitoring and tactical decision-making.

This study examined the changes in physical, tactical, and technical performance during the most demanding passage of kinematic activity (MDPk) and immediately after (post-MDPk) in elite soccer players, with respect to their playing positions. The MDPk (≥ 15 km/h), was defined using a 1-min rolling average (n = 1016 observations), and was quantified as the distance covered at moderate-speed running (MSR), high-speed running (HSR), and sprinting (SPR). In addition, total distance covered (TD) was also included. Generalized linear mixed models were employed to assess mean changes in five physical, ten tactical, and six technical performance-related variables during the effective playing time from the onset of the MDPk to 1-min post-MDPk, across different playing positions. Across all positions, there was a significant decrease in all external load variables during the 1-min post-MDPk period (TD=-48

This study aimed to quantify changes in running performance-related parameters in U20 elite male soccer players across transitions between training at moderate-altitude and sea level. Nineteen players from a professional club were monitored across three stages: moderate altitude (2000 m), sea level (<500 m), and return to moderate altitude. Running performance was assessed using 10-Hz GPS, and generalized linear mixed models were applied with altitude stage as a fixed effect and player as a random effect. Results showed substantial reductions in distance per minute (DPM: mean change in percent; +/- 90% confidence intervals; -9%; +/- 3%), high-speed running distance (HSR: -55%; +/- 16%), sprint distance (SprintD: -78%; +/- 30%), explosive accelerations (EAcc: -32%; +/- 7%), and explosive decelerations (EDec: -29%; +/- 8%) from the first stage (moderate altitude) to the second stage (sea level). By contrast, DPM (7%; +/- 4%), HSR (60%; +/- 14%), SprintD (81%; +/- 28%), EAcc (28%; +/- 8%), and EDec (29%; +/- 8%) increased substantially when returning from the second stage (sea level) to the third stage (moderate altitude). These findings indicate that transitions between moderate altitude and sea level induce marked but reversible changes in training running performance, particularly in high-intensity actions. The results highlight the context-specific nature of altitude-related adaptations and may inform training load management in elite youth soccer.

The rapid professionalization of women's soccer has increased match demands and interest in performance analytics at major tournaments such as the FIFA Women's World Cup. However, there remains a need for transparent and interpretable analyses linking multidimensional technical indicators with match outcome in elite women's soccer. This study analyzed 126 team–match observations from the 2023 FIFA Women's World Cup using publicly available aggregated SofaScore team–match statistics. A multidimensional technical-indicator framework covering attacking, possession,build-up, defensive, goalkeeping, and restart actions was established. Match tempo was quantified using Event Pace (technical events per minute of effective playing time), and matches were classified into fast- and slow-tempo groups using a median split. Correlation analysis, independent-samples t-tests, and an interpretable decision-tree model with ROC evaluation were applied. The tournament showed a heterogeneous tempo profile (2.05 ± 0.36 events·min −1 ). Fast-tempo matches involved more long passes, outside-box shots, successful crosses, and ground duels, whereas slow-tempo matches showed more aerial duels won and goalkeeper saves. The decision tree identified shots on target, dribbles won, possession, big chances, aerial duels won, and expected goals as key threshold-based split variables associated with winning versus not winning. The model showed high apparent discrimination (AUC = 0.969), but 10-fold cross-validation indicated more moderate performance (AUC = 0.703). The model should therefore be interpreted as a post-match explanatory classification model rather than a pre-match forecasting tool.

Understanding why teams win in professional basketball requires more than examining isolated statistics. Performance adapts under changing competitive constraints, and key performance indicators (KPIs) must therefore be interpreted within context. This study aimed to develop an explainable, multi-model machine learning (ML) framework to identify score-line dependent KPIs associated with winning outcomes in the Chinese Basketball Association (CBA). A total of 3,249 games from the 2018–2022 CBA regular seasons were analyzed. Based on final score margin, games were classified into close (1–9 points) and balanced (10–18 points) contexts using k-means clustering. For each context, game-related statistics and play-type variables were initially screened using conventional statistical procedures. A dual-stage feature selection process combining lasso and stepwise logistic regression retained indicators consistently selected by both models. Ten commonly used ML classifiers were then trained and evaluated using nested cross-validation. Rather than benchmarking predictive accuracy alone, a convergence-based strategy was adopted, treating KPI relevance consistently identified across classifiers as stronger structural evidence. Shapley Additive exPlanations (SHAP) were used to quantify the magnitude and direction of each KPI's contribution within the top-performing classifiers. Model performance differed across score-line contexts. In close games, the BP neural network, support vector machine, and logistic regression achieved the highest performance (accuracy: 71.2

This study aimed to identify cross-league differences in technical and tactical performance across Asian professional football leagues. Statistics of 14,115 matches from the 2015-2020 seasons of the Chinese Super League (CSL), J League 1 (J1), K League 1 (K1), Saudi Professional League (SPL), Qatar Stars League (QSL), and UAE Arabian Gulf League (AGL) were collected and analysed. Generalised mixed linear modelling was used to estimate mean league differences in 57 match performance-related parameters while controlling for game result, match location, and team and opponent strength. Results showed that differences in offensive outcome and performance-related parameters were generally trivial across leagues (ES ≤ 0.2). In contrast, possession- and progression-related parameters exhibited substantial between-league differences, with J1 demonstrating higher passing frequency and ball progression parameters than the other leagues (ES = 0.36-0.91). Conversely, SPL, CSL, QSL, and AGL recorded higher frequencies of defensive and disciplinary actions, including fouls and yellow cards, compared with J1 and K1 (ES = 0.46-1.33). Hence, it is concluded that technical and tactical performance is generally similar across major Asian professional football leagues, but notable stylistic differences remain. J1 tends to exhibit a possession-oriented and structured playing style, whereas SPL, CSL, QSL, and AGL are characterised by greater physical intensity and more confrontational play. These insights may inform performance analysis and coaching strategies across Asian professional football.

Elite soccer players increasingly live and train at moderate altitude, while inter-regional competition across different altitudes has become more frequent. However, evidence regarding whether transitioning from moderate altitude to sea-level competition influences match running performance remains limited. Twenty-three elite U20 male outfield players from a professional soccer club based at moderate altitude were monitored during friendly matches played at moderate altitude and sea level. Running performance was quantified using 10-Hz GPS devices, from which the following variables were derived: distance per minute (DPM), top speed (TS), high-speed running distance (HSR), sprint distance (SprintD), explosive accelerations (EAcc), and explosive decelerations (EDec). Generalized linear mixed models were used to examine the effect of competition altitude, with player names included as a random effect. Results showed that HSR (mean change; -32%; ES: -1.11), SprintD (-24%; -0.54), EAcc (-30%; -1.04), and EDec (-39%; -1.23) were substantially lower during matches played at sea level than during matches played at moderate altitude. These findings indicate that competing at sea level substantially influences match running performance in elite U20 male soccer players chronically trained at moderate altitude, particularly reducing high-intensity and explosive actions.

OBJECTIVES:The purpose of this study was to investigate the developmental activities of Chinese female national and professional football players. DESIGN AND METHODS:A total of 193 players (62 national-level, 131 professional-level) completed the Participation History Questionnaire (PHQ), which included demographic information (birthdate, birthplace), milestones across childhood (6-12 years), adolescence (13-17 years), and adulthood (>18 years), engagement in football-specific activities, participation in other sports, and social support factors. RESULTS:Chi-square tests revealed a significant relative age effect (RAE) among professional players (Q1: 36.6%, 48/131; χ2 (3) = 10.832, P = 0.013), but not among national players (χ2(3) = 3.419, P = 0.331), and no significant between-group difference in birth-quarter distribution (χ2(3) = 0.256, P = 0.968, Cramer's V = 0.036). With respect to birthplace, both national and professional players were predominantly born in economically developed and densely populated cities, with 37.2% (64/172) originating from (emerging) first-tier cities and 46.5% (80/172) from megacities. Chi-square tests indicated no significant between-group differences in birthplace distributions across either economic tiers (χ2 (4) = 3.038, P = 0.55, Cramer's V = 0.113) or population-size categories (χ2 (3) = 0.715, P = 0.87, Cramer's V = 0.064). Milestone analyses demonstrated that national players initiated football participation (8.6 ± 1.6 vs. 10.8 ± 1.9 years, Z = -7.042, P < 0.001), commenced coach-led practice (10.3 ± 2.1 vs. 11.2 ± 1.9 years, Z = -3.380, P = 0.001), and reached the first team of senior professional clubs (17.9 ± 1.1 vs. 18.6 ± 1.4 years, Z = -3.845, P < 0.001) at significantly younger ages than professional players. Only 7.8% of players (15/193) (National: N = 10, Professional: N = 5) reported engagement in other sports. No significant between-group differences were observed in perceived social support. CONCLUSIONS:These findings characterize the developmental profiles of Chinese female football players and provide a basis for refining talent identification systems and informing evidence-based strategies for long-term athlete development and differentiated training programmes.

Warm-up intensity is considered a key factor influencing acute physical performance, yet its specific effects on explosive power and agility in university football players remain unclear. This study compared the acute effects of low-, moderate-, and high-intensity warm-up on lower-limb explosive power and agility. Twenty male university football athletes completed three 15-min warm-up protocols differing in intensity. Performance was assessed using the standing triple jump (STJ), 10 m sprint, 505 test, and T-test at pre-, post-, and post-10. Generalized mixed linear models were applied to evaluate the effects of intensity and time, with results reported as standardized effect sizes (ES) and 90

This review synthesizes the keynote presentations delivered at the 2024 International Conference on Sports Technology and Performance Analysis (ICSTPA 2024), highlighting advances in the interdisciplinary development of science and technology applied to health promotion, sports performance and physical education. Real-time physiological monitoring via AI-powered wearable technologies (e.g., wearable ECG shirts and cuffless blood pressure systems) enables personalized health and metabolic management. Measurement techniques for athletic performance (i.e., vertical jumps) have evolved from traditional jump mats to advanced automated systems based on deep neural networks, significantly improving accuracy and applicability in diverse environments. Additionally, machine learning-driven analyses of extensive match datasets in sports such as squash and soccer have identified hidden tactical patterns, thus providing quantitative foundations for tactical and training optimizations. Moreover, interactive educational innovations have emerged from the integration of wearable devices, mobile applications, and observational coaching tools. A novel psychological-fatigue threshold (PFT) concept has also been introduced, which incorporates psychological factors into the evaluation of decision-making and tactical performance of soccer players under high-intensity conditions. The ICSTPA 2024 conference demonstrated that technology-driven innovations are profoundly reshaping sports performance enhancement, health management, and motor skill development. Future research directions highlighted include expanding the application of AI-driven tools for real-time feedback, further refinement of psychological assessment frameworks, and enhanced integration of technology within practical sports training environments.

This study examines positional differences in physical and technical performance during the extremely demanding passage (EDP) in the Chinese Super League (CSL), using a 5-minute time window and a high-intensity running (HIR) threshold of ≥ 19.8 km/h. Data from 176 matches (n = 109 players, 438 observations) in the 2019 season were analysed using generalised mixed linear models. Results showed that: (1) The mean HIR distance during the EDP was 50

This study examined offensive tactical patterns in professional basketball and their relationships with scoring performance under varying contextual factors. Data from 982 games in the 2023-2024 Chinese Basketball Association regular season were analyzed. A k-means clustering procedure identified three offensive archetypes: Individual Creation Style (ICS), Pick-and-Roll Variation Style (PNRS), and Screen-Post Synergy Style (SPSS); random forest classifiers with Shapley Additive exPlanations confirmed cluster separations. Correlation analyses showed that isolations and pick-and-roll (PnR) handler plays in ICS were moderately associated with two-point shots made (r = 0.31) and accuracy (r = 0.30); hand-off actions in PNRS weakly correlated with two-point shot accuracy (r = 0.12); and off-ball screens in SPSS were moderately related to three-point shots made (r = 0.31). Poisson regression models revealed contextual effects. Specifically, PnR handler plays increased against stronger opponents (p < 0.001), isolations occurred more frequently in faster-paced games (p = 0.002); hand-off completions were greater in wins (p = 0.034) and against stronger than weaker opponents (p = 0.034); and off-ball screens increased against medium-level opponents (p = 0.011) and after longer travel distances (p = 0.033). These findings provide a scalable analytical framework connecting tactical structures, scoring outcomes, and situational constraints in professional basketball.

This study aims to investigate the changes in physical and technical performance of professional soccer players during effective playing time after the worst-case scenario (WCS) identified by the high-intensity running (HIR) distance using rolling average. A total of 576 matches (n = 13,298 observations) from the 2019 to 2021 season of the Chinese Super League (CSL) were analyzed by a video tracking system. Generalized mixed linear models were established to determine the mean changes in the value of 7 physical and 24 technical performance-related parameters in the effective playing time from the 5 min of WCS (Peak5) to the initial 5 minutes post-WCS (Post5). Results showed that: (1) For all the players in the Post5 total distance, HIR distance, and Sprint decreased by 16.6% (ES; ± 99%CL: 0.57; ± 0.04), 77.2% (2.78; ± 0.06), and 86.1% (2.11; ± 0.08), respectively. The number of efforts, average duration, average speed, and average length of HIR declined by 70.8% (2.26; ± 0.06), 31.7% (0.78; ± 0.05), 3.1% (0.52; ± 0.05), and 22.9% (0.83; ± 0.05), respectively; (2) In the Post5, a substantial decrement in the number (0.23; ± 0.03), average speed (0.32; ± 0.06) and average length (0.37; ± 0.06) of running with the ball, and average speed receiving the ball (0.5; ± 0.05) was observed for all players. While only trivial changes were detected in all the other technical performance-related parameters. It can be concluded that, in the Post5, there is a temporary decline in physical output and the physical-related technical parameters for players, however, there are no meaningful changes in other technical performancerelated parameters.

IntroductionFootball success is defined as the achievement of a team in the game, which is measured by the combination of winning championship, higher ranking and better performance. This study reviews the factors influencing the football success in women's football from macro (economy, politics, culture), meso (geographical environment, football tradition, talent development, gender equality, league prosperity), and micro (technical/tactical, physical performance, situational factors) perspectives.MethodsA systematic search was carried out in the Web of Science, Scopus, and Pub Med database, the search strategy included the terms for the population (“women” OR “female”), the sport (“football” OR “soccer”), the variables (determinant', “success”, “ranking”).ResultsA total of 62 studies were included in the analysis. The findings suggest that at the macro dimension, economic development positively correlates with FIFA rankings, and policy support influences football success. Culturally, a culture that emphasizes creativity and strength can facilitate the success in women's football, while a culture of conservatism and humility hinders it. Regarding meso factors, geographical and climatic conditions, football tradition, the quality of talent development, and the degree of gender equality also emerged as important determinants. At the micro dimension, factors such as scoring first, high-intensity running, ball possession, home advantage, and playing weaker teams are closely associated with match success.ConclusionThese insights offer evidence-based recommendations for policymakers to promote women's football through increased economic investment, infrastructure development, and prioritized support policies, while coaches are encouraged to optimize training processes and incorporate situational factors to enhance team performance.

This study examines the impact of socio-cultural constraints on women's participation in sports in Khyber Pakhtunkhwa, Pakistan, with a specific focus on their effects on sexual and reproductive health. We used a qualitative research design. The data were collected from 20 urban and semi-urban women using purposive sampling techniques, gathering information through interviews, focus group discussions, and field observations. We present the findings using thematic analysis. The findings reveal that socio cultural norms often portray sports as a male-dominated activity, although physical activity is accepted for its health benefits. Women adapt to sports by perceiving them as health-related, usually balancing family and community expectations with their personal goals. The research demonstrates the need for policies that encourage women's participation in sports, ensure access to safe transportation, promote female coaching, and address socio-cultural barriers to enhance women's reproductive health and overall well-being.

This study examined Extremely Demanding Passages (EDP) in professional football, which statistically extend the Most Demanding Passage (MDP) framework by applying an extreme threshold to capture peak physical demands. Additionally, it analysed the differences in technical, tactical, and conditional performance between the MDP and EDP phases. A total of 3,679 observations (3,463 MDP,216 EDP) from 176 matches of the 2021 Chinese Super League were analysed. The results revealed significant differences, specifically in the number of clearances (p <.05), number and success of lateral passes (p <.05), number (p <.001) and success (p < .001) of long passes, number (p <.05) and success (p <.005) of short passes, and average forward pass length (p <.005). The SHAP results reinforced these findings, EDP segments, showed an increased reliance on long and lateral passes, with higher frequencies and success rates, longer forward pass length, and prolonged individual ball possession duration. In contrast, MDP was related to a higher number and success of short passes, indicating an ordered, possession-oriented playing style. The results highlight that EDP, derived from MDP through a statistical threshold, provides a stricter approach to quantifying peak physical demand, involving increased physical effort and tactical changes, underlining the necessity of including both physical and technical factors in training strategies.

This study developed a predictive model to identify offensive possession sequences culminating in successful entries into the opponent's penalty area. Event data, comprising 1859 structured attacking possessions, were extracted from matches of a Chinese Super League club over two full seasons (2023 and 2024). A Bi-LSTM model incorporating an attention mechanism was employed to classify these sequences based on spatio-temporal and tactical features preceding the final event. The model achieved a recall of 0.77 and an F1-score of 0.24 for predicting successful penalty-area entries. Crucially, this recall significantly exceeded that of comparative baseline models (RNN: 0.05, LSTM: 0.33, GRU: 0.14), demonstrating robust performance in identifying pertinent possession sequences and underscoring its utility as a diagnostic instrument. SHAP analysis revealed that spatial features, including proximity to goal, advanced passing positions, and central field targeting, constituted the most influential predictors. Furthermore, successful possessions were characterised by forward-oriented passes, greater cumulative territorial gain, and accelerated ball movement. These findings indicate that rapid, vertical play through central areas enhances the probability of penalty-area penetration. The proposed framework offers a practical tool for assessing offensive organisation and holds potential for broader tactical analysis in applied football research.