Search Results (285)

This paper examines the integration of machine learning (ML) techniques in professional football, focusing on two key areas: (i) player and team performance, and (ii) match outcome prediction. Using a systematic methodology, this study reviews 172 papers from a five-year observation period (2019–2024) to identify relevant applications, focusing on the analysis of game actions (free kicks, passes, and penalties), individual and collective performance, and player position. A predominance of supervised learning, deep learning, and hybrid models (which integrate several ML techniques) is observed in the ML categories. Among the most widely used algorithms are decision trees, extreme gradient boosting, and artificial neural networks, which focus on optimizing sports performance and predicting outcomes. This paper discusses challenges such as the limited availability of public datasets due to access and cost restrictions, the restricted use of advanced visualization tools, and the poor integration of data acquisition devices, such as sensors. However, it also highlights the role of ML in addressing these challenges, thereby representing future research opportunities. Furthermore, this paper includes two illustrative case studies: (i) predicting the date Cristiano Ronaldo will reach 1000 goals, and (ii) an example of predicting penalty shoots; these examples demonstrate the practical potential of ML for performance monitoring and tactical decision-making in real-world football environments. Full article

Transfers in professional football (soccer) are risky investments because of the large transfer fees and high risks involved. Although data-driven models can be used to improve transfer decisions, existing models focus on describing players’ historical progress, leaving their future performance unknown. Moreover, recent developments have called for the use of explainable models combined with methods for uncertainty quantification of predictions to improve applicability for practitioners. This paper assesses explainable machine learning models in a practitioner-oriented way for the prediction of the future development in quality and transfer value of professional football players. To this end, the methods for uncertainty quantification are studied through the literature. The predictive accuracy is studied by training the models to predict the quality and value of players one year ahead, equivalent to one season. This is carried out by training them on two data sets containing data-driven indicators describing the player quality and player value in historical settings. In this paper, the random forest model is found to be the most suitable model because it provides accurate predictions as well as an uncertainty quantification method that naturally arises from the bagging procedure of the random forest model. Additionally, this research shows that the development of player performance contains nonlinear patterns and interactions between variables, and that time series information can provide useful information for the modeling of player performance metrics. The resulting models can help football clubs make more informed, data-driven transfer decisions by forecasting player quality and transfer value. Full article

Digital technologies, including artificial intelligence (AI) and machine learning (ML), are reshaping the landscape of athletic training and performance assessment. Despite growing global interest, empirical research on AI adoption in sports remains limited in Central and Eastern Europe. This study investigates how Romanian sports professionals perceive and integrate AI-based applications and digital technologies into their training practices, and how these tools influence performance outcomes. Data were collected through a structured questionnaire distributed to 293 athletes, coaches, and sports academics. Using Partial Least Squares Structural Equation Modeling (PLS-SEM), we found that perceived AI benefits significantly predict the use of AI applications (β = 0.211, p < 0.001), which in turn strongly predicts the adoption of digital sports technologies (β = 0.708, p < 0.001). The use of digital technologies was positively associated with higher self-reported performance outcomes (β = 0.268, p < 0.001). Group comparisons using ANOVA revealed significant differences in AI adoption by sport (football > basketball, p < 0.05) and education level (p = 0.007). These findings contribute to the literature on sports technology adoption by offering one of Eastern Europe’s first empirical, model-based studies. The study provides practical insights for coaches, policymakers, and sports technologists aiming to foster AI integration and digital innovation in high-performance athletic environments. Full article

The development of Global Positioning System (GPS) technology has contributed in various ways to improving the physical condition of modern football players by enabling the quantification of physical load. Previous studies have reported that the running demands of matches vary depending on playing position and formation. Over the past decade, despite the widespread use of GPS technology, studies that have investigated the running performance of young football players within the 1-4-3-3 formation are particularly limited. Therefore, the aim of the present study was to create the match running profile of playing positions in the 1-4-3-3 formation among high-level youth football players. An additional objective of the study was to compare the running performance of players between the two halves of a match. This study involved 25 football players (Under-19, U19) from the academy of a professional football club. Data were collected from 18 league matches in which the team used the 1-4-3-3 formation. Positions were categorized as Central Defenders (CDs), Side Defenders (SDs), Central Midfielders (CMs), Side Midfielders (SMs), and Forwards (Fs). The players’ movement patterns were monitored using GPS devices and categorized into six speed zones: Zone 1 (0.1–6 km/h), Zone 2 (6.1–12 km/h), Zone 3 (12.1–18 km/h), Zone 4 (18.1–21 km/h), Zone 5 (21.1–24 km/h), and Zone 6 (above 24.1 km/h). The results showed that midfielders covered the greatest total distance (p = 0.001), while SDs covered the most meters at high and maximal speeds (Zones 5 and 6) (p = 0.001). In contrast, CDs covered the least distance at high speeds (p = 0.001), which is attributed to the specific tactical role of their position. A comparison of the two halves revealed a progressive decrease in the distance covered by the players at high speed: distance in Zone 3 decreased from 1139 m to 944 m (p = 0.001), Zone 4 from 251 m to 193 m (p = 0.001), Zone 5 from 144 m to 110 m (p = 0.001), and maximal sprinting (Zone 6) dropped from 104 m to 78 m (p = 0.01). Despite this reduction, the total distance remained relatively stable (first half: 5237 m; second half: 5046 m, p = 0.16), indicating a consistent overall workload but a reduced number of high-speed efforts in the latter stages. The results clearly show that the tactical role of each playing position in the 1-4-3-3 formation, as well as the area of the pitch in which each position operates, significantly affects the running performance profile. This information should be utilized by fitness coaches to tailor physical loads based on playing position. More specifically, players who cover greater distances at high speeds during matches should be prepared for this scenario within the microcycle by performing similar distances during training. It can also be used for better preparing younger players (U17) before transitioning to the U19 level. Knowing the running profile of the next age category, the fitness coach can prepare the players so that by the end of the season, they are approaching the running performance levels of the next group, with the goal of ensuring a smoother transition. Finally, regarding the two halves of the game, it is evident that fitness coaches should train players during the microcycle to maintain high movement intensities even under fatigue. Full article

This study analyses the physical performance variables involved in different training tasks aimed at replicating the worst-case scenarios (WCSs) observed during official matches in professional football, with a focus on playing positions and occurrences within a 1 min period. Data were collected from 188 training sessions and 42 matches of a Spanish Second Division team during the 2021/2022 season. All data were reported on a per-player basis. GPS tracking devices were used to record physical variables such as total distance, high-speed running (HSR), sprints, accelerations, decelerations, and high metabolic load distance (HMLD). Players were grouped according to their match positions: central defenders, wide players, midfielders and forwards. The results showed that none of the training tasks fully replicated the physical demands of match play. However, task TYPEs 11 (Large-Sided Games) and 9 (small-sided games with orientation and transition) were the closest to match demands, particularly in terms of accelerations and decelerations. Although differences were observed across all variables, the most pronounced discrepancies were observed in sprint and HSR variables, where training tasksfailed to reach 60% of match demands. These findings highlight the need to design more specific drills that simulate the intensity of WCS, allowing for more accurate weekly training load planning. This study offers valuable contributions for optimising performance and reducing injury risk in professional footballers during the competitive period. Full article

Background and Objectives: This study explored the lived experiences of individuals with post-COVID condition (PCC) who participated in a 12-week exercise rehabilitation and recovery programme (PCCRRP) delivered by a professional football club community trust (FCCT). The aim was to understand the effects of the programme on physical function and quality of life (QoL). This study aims to address the gap in the literature of a lack of qualitative research exploring the experiences and perspectives of individuals engaging in exercise and physical activity as part of their recovery from PCC. Furthermore, it seeks to provide in-depth participant accounts to better understand outcome-level data. Methods: A qualitative approach was employed, involving semi-structured interviews with seven participants (mean age of 52 ± 8.54 years, with ages ranging from 45 to 60 years) following the 12-week PCCRRP to explore perceived changes in physical function and QoL. Thematic analysis was used to analyse the interview data, including participants’ narratives on their QoL experiences. Results: Participants reported improvements in exercise capacity, fatigue, and breathlessness, leading to enhanced physical function and QoL. They also experienced improvements in emotional well-being, including increased confidence and reduced anxiety. The programme’s focus on tailored exercise plans empowered participants to manage their symptoms and regain control over their lives. Conclusions: The PCCRRP delivered by an FCCT had positive effects on the physical function and QoL of individuals with PCC. This highlights the potential of FCCTs in providing effective rehabilitation and support for individuals with PCC. Full article

Background: The incidence of anterior cruciate ligament ruptures in football has experienced a marked increase in recent years, affecting both professional and amateur players. This injury is characterised by being highly disabling, causing the player to withdraw from the field of play for prolonged periods and there is no clear consensus on how to carry out the different phases of rehabilitation, which poses a major challenge for health professionals. Case presentation: This study followed a semi-professional player who suffered an anterior cruciate ligament tear following two forced valgus actions without direct contact in the same match. Outcome and follow-up: The patient underwent surgery using an autologous hamstring graft. He followed a progressive rehabilitation programme consisting of one preoperative phase and six phases after the operation. After a 12-month follow-up, with exercises aimed at perfecting step-by-step basic and specific physical skills, the player showed a complete functional recovery, achieving the desired parameters. Conclusions: This case highlights the importance of structured rehabilitation adapted to the specific needs of the football player through an approach with coherent progressions, which considers the muscle chains that determine the movements performed on the football pitch. Full article

There have been some studies investigating the effects of air pollutants on male football players, but few have examined the gender-specific impact of air pollution on the athletic performance of female football players. This research gap limits the development of tailored training and competition strategies. Here, generalized mixed modeling was employed to assess the effects of main ambient air pollutants, i.e., particulate matter less than 2.5 μm (PM_2.5), ozone (O₃), sulfur dioxide (SO₂), nitrogen dioxide (NO₂), and carbon monoxide (CO), on athletic performance indicators (total movement distance (TMD), jogging distance (JD), and walking distance (WD)) among 14 female football players during 16 matches in the 2020 season of the Chinese Football Association Women’s Super League. Our findings indicate a significant negative association between the O₃ concentration and athletic performance, with fixed effect coefficients of −22.426 ± 8.889 for TMD, −10.817 ± 3.697 for JD, and −6.943 ± 3.265 for WD. The NO₂ concentration was significantly correlated with both TMD and JD, while PM_2.5, SO₂, and CO concentrations had minimal or negligible effects. Additionally, aerobic fitness was reduced as the O₃ concentration increased. These results provide valuable insights for optimizing gender-specific training and competition strategies under varying air quality conditions, offering a basis for more targeted health and performance interventions in professional female football players. Full article

This study aimed to examine whether managerial changes and their training methodology influence the physical attributes of soccer players and determine if these changes significantly impact the overall physical performance of the team. Twenty-seven male elite-level football players competing in the Eastern Mediterranean region (age: 28.12 ± 5.5 years, height: 179.3 ± 6.25 cm, body mass: 75.8 ± 6.6 kg) participated in this study. To analyze the impact of managerial changes on elite football players’ physical performance, this study evaluated and compared physical attributes during weekly microcycles and official games across three different coaching regimes over an entire season. Data were collected using a 10 Hz GPS tracking technology and included the following external load (EL) parameters: total distance, high metabolic load distance, high-speed running, sprint distance, accelerations, and decelerations. A one-way Analysis of Variance (ANOVA) was utilized to assess differences in physical performance across the three coaching methods. Significant differences were evident in high metabolic load distance during games [F(2,27) = 7.59, p < 0.05]. High-speed running distance also varied significantly across the three coaching regimes, both during training sessions [F(2,27) = 5.89, p < 0.05] and games [F(2,27) = 4.31, p < 0.05]. Furthermore, sprint distance showed significant differences during training [F(2,27) = 4.62, p < 0.05] and games [F(2,27) = 3.37, p < 0.05]. The findings of this study suggest that managerial changes can have a significant effect on the physical performance of soccer players. The results highlight the importance of aligning coaching strategies with physical conditioning techniques for optimizing performance. These findings provide a deeper understanding of the potential benefits and risks associated with managerial changes in professional soccer. Nevertheless, a limitation in this study is that all metrics of EL were interpreted as absolute values rather than relative-based threshold values, which may affect the interpretation of the players’ physical capacities. Full article

Background: High-intensity actions like accelerations and decelerations, often performed unilaterally, are crucial in elite female football but increase the risk of interlimb asymmetries and injury. Flywheel resistance training enhances eccentric strength, yet limited research has assessed how different inertial loads affect mechanical outputs in unilateral exercises. Purpose: This study investigated how two inertial loads (0.107 kg·m² and 0.133 kg·m²) influence power, acceleration, speed, and asymmetry during unilateral hip extensions in elite female footballers. Methods: Eighteen professional players (27 ± 4 years, 59.9 ± 6.5 kg, 168.2 ± 6.3 cm, BMI 21.2 ± 1.8) completed unilateral hip extensions on a conical flywheel under both inertia conditions. A rotary encoder measured peak/average power, acceleration, speed, and eccentric-to-concentric (E:C) ratios. Bilateral asymmetries between dominant (DL) and non-dominant (NDL) limbs were assessed. Paired t-tests and Cohen’s d were used for analysis. Results: Higher inertia reduced peak and mean acceleration and speed (p < 0.001, d > 0.8). Eccentric peak power significantly increased in the NDL (p < 0.001, d = 3.952). E:C ratios remained stable. Conclusions: Greater inertial loads reduce movement velocity but increase eccentric output in the NDL, offering potential strategies to manage neuromuscular asymmetries in elite female football players. Full article

Environmental consciousness has become increasingly important in the professional sports industry as it often hosts large-scale events that have significant environmental impacts. While the economic benefits of locating stadiums in city centers have been discussed, especially in terms of neighborhood revitalization, there has been limited empirical research on whether stadium relocation affects the transportation choices of spectators and reduces carbon dioxide emissions. Through a case study of a Japanese professional football club that relocated its home stadium from the suburb to the city center, this study quantitatively elucidated the change in spectators’ transportation choices and resulting reductions in carbon emissions achieved by the stadium relocation. Analysis indicated variations in behavioral changes among groups based on their loyalty levels to the club. It also highlighted the varying influence of the different residential areas within the metropolitan area on the modal choice. This study demonstrates the potential contribution of stadium relocation to sustainable urban planning by providing empirical evidence of these behavioral changes and policy implications for restructuring the urban public transportation network. Full article

This study aimed to compare the external peak physical demands (PDs) of under-19-year-old (U19) and professional male football players according to playing position. Positional data derived from Global Positioning System (GPS) tracking during 15 matches in the 2023/24 season for both groups were analyzed. The following variables were measured: total distance, high-intensity running distance, sprint distance, acceleration count, and high-intensity actions. A linear mixed-effects model was employed, with category and playing position included as fixed effects to compare these metrics at the player level. The results revealed only a few significant differences in physical demands between the U19 and professional players. Notably, central defenders and central midfielders exhibited lower performance in HSR distance compared to other positions, with the professional players registering higher values than their U19 counterparts. However, no significant differences were observed for total and relative sprint distances, the number of accelerations, high intensity and relative sprint running efforts. These findings highlight the overall similarity in physical demands between U19 players and professional players, suggesting that elite youth athletes may be adequately prepared to meet the physical challenges of professional competition, with the exception of HSR distance. These conclusions have practical implications for coaches and performance staff, supporting the development of position-specific training programs, optimizing workload management through GPS monitoring, improving microcycle planning, and enhancing injury prevention strategies. Full article

Over the past 20 years, the use of the global positioning system (GPS) in football has become widespread. This technology has facilitated the tracking of external load both during training sessions and matches. Creating an external load profile for each playing position within specific formations can assist the coaching staff in shaping the training load of the microcycle according to the demands of each position. The purpose of this study was to create the running performance profile for high-level young football players based on their playing position in the 1-4-2-3-1 formation and to investigate potential differences between positions. Additionally, the study aimed to compare the players’ running performance across the two halves of the match. The study involved 22 Under-19 players from the academy of a professional football team. Only matches where the team used the 1-4-2-3-1 formation were analyzed (10 matches). The playing positions were categorized as: Central Defensive Fielders (CDFs), Central Midfielders (CMFs), Forwards (FWDs), Wide Defensive Fielders (WDFs), and Wide Midfielders (WMFs). Player movement was tracked using GPS devices and categorized into four velocity zones: (Zone 1: 3.6–10.8 km/h, Zone 2: 10.9–18.0 km/h, Zone 3: 18.1–25.2 km/h, Zone 4: >25.2 km/h). Depending on whether normality was present in our data, either a one-way analysis of variance (ANOVA) or a Kruskal–Wallis test was conducted. A subsequent analysis was performed to compare the performance between the first and second halves of the match, using either the independent samples t-test or the Mann–Whitney U test. The results showed that CMF players covered the greatest total distance and had the highest movement velocity (distance/min) compared to all other positions (p = 0.001). In high-speed running (>18 km/h), CMF again covered the greatest distance, followed by WDF. In sprinting, CDF covered the shortest distance and reached the lowest maximum speed (p = 0.001). CMF performed the most accelerations and decelerations across all positions (p = 0.001). As for the entire team, total distance, movement rate, and the number of accelerations and decelerations decreased in the second half. All players except the WDF also showed a decrease in total distance, while midfielders experienced a notable drop in sprint distance. In conclusion, this study underscores the positional specificity of physical demands in elite football and the systematic decline in physical output as matches progress. While all positions demonstrated some level of second-half performance deterioration, midfielders experienced the most significant decreases in both volume and intensity-related metrics. These insights offer valuable implications for position-specific physical condition, recovery planning, and substitution strategies, helping to optimize performance and manage player load in elite football environments. It should be reiterated that the results of the present study apply exclusively to the 1-4-2-3-1 formation. Full article

Blockchain technology is reshaping the sports industry by enhancing transparency, data security, and fan engagement through applications such as smart contracts, tokenized sponsorships, and decentralized ticketing. This study investigates blockchain adoption in Romanian team sports, specifically football and basketball, through a comparative analysis based on a survey of 293 sports professionals (213 from football and 80 from basketball). Using structural equation modeling (SEM) with SmartPLS and cluster analysis in SPSS, the study explores the perceived benefits of blockchain and its relationship with athlete performance. The findings reveal distinct adoption patterns: football shows higher use of blockchain in ticketing and fan engagement, while basketball leads in performance analytics and financial support mechanisms. Statistically significant differences were confirmed through MANOVA, and clustering revealed varied stakeholder perceptions across professional roles. Benchmarking against sectors like finance and healthcare highlights transferable best practices for blockchain integration in sports. Full article

The financial valuation of professional football players is influenced by multiple factors that evolve throughout a player’s career. This study examines these determinants using Gradient Boosting Machine Learning models, segmented by three age categories and three playing positions to capture the dynamic nature of player valuation. K-fold cross-validation is applied to measure accuracy, with results indicating that incorporating a player’s projected future potential improves model precision from an average of 74% to 84%. The findings reveal that the relevance of valuation factors diminishes with age, and the most influential features vary by position—shooting for attackers, passing for midfielders, and defensive skills for defenders. The study adopts a dynamic segmentation approach, providing financial insights relevant to club managers, investors, and stakeholders in sports finance. The results contribute to sports analytics and financial modeling in sports, with applications in contract negotiations, talent scouting, and transfer market decisions. Full article