Influence of Situational Variables, Team Formation, and Playing Position on Match Running Performance and Social Network Analysis in Brazilian Professional Soccer Players

The Influence of Playing Position on Physical, Physiological, and Technical Demands in Adult Male Soccer Matches: A Systematic Scoping Review with Evidence Gap Map

BACKGROUND

There has been an increase in studies examining the demands of soccer relative to each playing position in recent years. Understanding the physical, physiological, and technical demands on soccer players according to their positional role during competitive matches is necessary to understand match requirements and develop position-specific training practices. Thereby, there is a clear need to synthesize the information on the different profiles of each playing position.

OBJECTIVE

This review aimed to organize the literature investigating physical, physiological, and technical demands according to playing positions and provide a framework to identify gaps and suggestions for future studies.

METHODS

A systematic search was conducted in October 2023 using four electronic databases: Web of Science, SPORTDiscus, PubMed and Scopus. The review followed PRISMA 2020 guidelines and the PRISMA-ScR extension for Scoping Reviews. The studies were included if the sample comprised adult male soccer players categorized from Tier 3 to Tier 5 (i.e., highly trained/national level, elite/international level, or world class) and compared the physical, physiological, or technical parameters across playing positions.

RESULTS

A total of 178 studies met the inclusion criteria and were included in the review. The number of teams, players, and matches analyzed per study varied considerably. Although a range of classifications were reported across studies, 59% of studies classified players as central defenders, full-backs, central midfielders, wide midfielders, and forwards. The findings suggests that central and external midfielders, and external defenders cover greater total and high-speed distance than forwards or central defenders. Sprint distance was higher in external midfielders versus all other positions. Defenders and central midfielders perform more passes than external midfielders and forwards. Heart rate was the most commonly reported physiological variable across playing positions. When expressed as a percentage of maximal heart rate, midfielders presented higher mean values than all other playing positions.

CONCLUSION

This scoping review demonstrates that there are differences in the demands on players across playing positions in soccer. Training practices in soccer should be based on the specific requirements of each positional role to ensure players can fulfill their tactical responsibilities during the game.

Contextual factors and match-physical performance of international-level footballers with cerebral palsy

This study aimed to explore the match-physical response of international-level footballers with cerebral palsy (CP) according to contextual factors such as team ranking, the quality level of opposition, and match outcome. Eighty-two male outfield footballers with CP from top-ranked teams (n = 26) and bottom-ranked teams (n = 56) took part in this study. The match-player response was recorded using global positioning devices considering the total distance, distance covered at different velocities and number of short-term actions. Players from top-ranked teams covered more distance at low intensities compared to players from bottom-ranked teams (p < 0.05; 0.45 < ES < 0.49). Higher sprint distance, moderate and high accelerations/decelerations were found in players from top-ranked teams playing against teams of similar levels (p < 0.05; 0.73g< 0.86). When players from bottom-ranked teams played against teams of equivalent rank, more physical requirements were presented in total distance, running from medium to sprint intensities, and the number of short-term actions (p < 0.0.05; -0.55S < -0.89). Players from the top-ranking teams presented greater sprint demands in losing matches (p<0.05; dg=-1.01). Considering the bottom-ranking opposition, players presented more running demands in matches with losing results in moderate running, sprinting, and moderate-to-high deceleration (p < 0.05; -0.61 < dg < -0.64). The match-physical response of players with CP varies according to the contextual factors studied. The results provide advice for coaches and classifiers to understand more comprehensively the competing demands in CP football. This knowledge could help practitioners to prepare competition matches and planning training load or post-match recovery strategies, but also for the observation assessments of the classification process in this team para-sport.

High-Intensity GPS-Derived Parameters in Semi-Professional Soccer: Home vs. Away Roles of the Team and Their Relationship with the Match's Final Score

High-intensity activities are related to success in football. We looked at whether high-intensity activity differed between home and away matches and its impact on the final score. Thirty football players (20.3 ± 0.8 years) were recruited from a Spanish semi-professional team. Footballers wore a GPS device to monitor high-intensity parameters from competition matches. The final score of every match was also recorded. Playing at home showed greater total distance (TD) > 24 km/h, >27 km/h, >85% Vmax, and the number of sprints > 24 km/h (all p < 0.05) than playing away. Positive correlations were also found between the match score and high-speed running (HSR) distance covered by the team per minute (r = 0.401), TD > 21 km/h (r = 0.417), TD > 24 km/h (r = 0.343), number of sprints > 24 km/h (r = 0.337), and HSR per minute (r = 0.459) (all p < 0.05). The results suggest that playing at home is associated with greater high-intensity effort than playing away. Moreover, the volume of high-intensity effort influences the final score.

Non-linear trends using the generalized additive models in physical and technical performances of the Chinese Super League players

This study aimed to investigate the non-linear evolution of position-specific physical and technical performance indicators across different tactical formations in the Chinese Super League (CSL) from the 2015 to the 2021 seasons. Match data were collected from 800 games played in six common formations (3-5-2, 4-3-3, 4-2-3-1, 4-4-2, 3-4-3, and 4-1-4-1). Players were classified into five positions: central defenders (CD; match observations = 2,219), fullbacks (FB; match observations = 2,060), central midfielders (CM; match observations = 2,786), wide midfielders (WM; match observations = 1,587), and forwards (FW; match observations = 1,680). Generalized additive models (GAMs) were constructed to analyze the nonlinear evolution trends in position-specific physical and technical performance across seasons and formations. The results showed that the total distance covered by CDs in the 3-5-2 formation showed a non-linear upward trend from the 2015 to 2021 seasons (R2 = 0.3, p = 0.006); FBs in the 3-4-3, 4-1-4-1, and 3-5-2 formations exhibited non-linear upward trends in number of sprints and sprint distance from the 2015 to 2021 seasons (R2 = 0.189-0.448; P < 0.03, respectively); the high-speed running of FWs in the 4-2-3-1 formation displayed a non-linear decline trend from the 2015 to 2021 seasons (R2 = 0.477; P < 0.001); CMs in the 4-2-3-1 formation demonstrated a non-linear increasing trend in the ball retention percentage (R2 = 0.369; p = 0.001); WMs in the 4-4-2 formation showed a non-linear decreasing trend in ball retention percentage and passes from the 2015 to 2021 seasons (R2 = 0.259-0.29; P = 0.006, respectively). These findings revealed non-linear evolutionary trends in physical and technical performances across positions and formations, providing an in-depth understanding of the changing match demands placed on players during matches. This enables the optimization of training and tactics by developing targeted strategies tailored to meet the specific requirements of different formations and playing positions.

The physical demands of the match according to playing positions in a South African Premier Soccer League team

Background

Evidence indicates that international soccer players cover a total distance of between eight and 14 km in a match. Approximately 80 - 90% of this distance constitutes low-intensity actions, and about 10 - 20% is high-intensity. These data are influenced by playing position, formation, league standard, and national differences in different countries.

Objective

To quantify the physical demands of competitive matches on the different playing positions in a South African Premier Soccer League team.

Methods

A descriptive study design included 21 players on the same team. Data were collected over 23 official matches during the 2019/2020 season using PlayerTek GPS devices (10Hz). The data collected included total distance covered, high-intensity running distance, power plays, top-end speed, and distance per minute.

Results

Statistical differences were evident only in the high-intensity running distance and power plays. The centre-forwards (p<0.001), attacking central midfielders (p=0.006), and full-backs (p=0.01) covered the most high-intensity running distance (p<0.001) than centre-backs. The attacking central midfielders and centre-forwards recorded more power plays than the centre-backs. Total distance (p=0.01), power plays (p=0.004) and distance per minute (p=0.001) were lower in the second half than in the first half of the match.

Conclusion

Centre-forwards performed more high-intensity actions, whereas the centre-backs sprinted less than all the other positions. These data provide insight into the positional differences that exist and could help coaches to prescribe position-specific training programmes.

Comparing locomotor intensity indicators in soccer training and competition across contextual factors: a study of replaced coaches in a Portuguese professional 1st league team

This study aims to examine, for each head coach (HC) replaced, the association between training intensity and physical performances obtained in games. Furthermore, the study investigated how contextual factors influence locomotor and mechanical performance association. External load variables were collected using Global Positioning System (GPS) devices across the 4 weeks and 4 games before and after the replacement in a professional adult male soccer team. Six different HC records were analysed (48.8 ± 7.4 years of age; 11.2 ± 3.9 years as an HC) during a three-season span (2020/21-2022/2023). There were marked differences within player variability across the two coaching regimes. Game loads didn't reflect training-related performance, with differences ranging from -71.4% to -9.9%. Players under the outgoing coaches have greater coverage of meters per minute. Meters per minute, distance covered over 18 km/h and high-speed running (all in training) are found to be significant variables influenced by contextual factors. Within-subject and time, training loads did not reflect game-related loads/performances, with starters showing higher deficits (ranging from -79.0 to -14.5). The study suggests that changes in soccer HC can affect players' training intensity and game performance, influenced by various contextual factors and not directly correlated. This type of information might be very suitable to improve training load periodization and programming. For further research avenues, could be the study of the variation of the psychological states of the players at the time of the dismissal and hiring of the HCs, associating them with the physiological performance at the same moments.

Influence of contextual factors on match running performance of starters and non-starters in elite youth male soccer players

This study investigated the effects of match location, quality of opposition (classified into: strong [1st to 4th position]; intermediate [5th to 15th position]; weak [16th to 20th position]), and match outcome on the match running performance of starters and non-starters from a top elite Brazilian soccer team. Absolute measures were calculated using total distance, high-speed (19.8-25.2 km·h-1), sprinting (≥ 25.2 km·h-1), total distance high-acceleration (> 2m·s2), and deceleration (< -2m·s2) were recorded by GPS units from a sample of young soccer players (N = 25) in a total of 17 matches. Relative measures were calculated by dividing absolute measures by the total duration of the matches. Non-starters covered greater total distance (p = 0.02), sprinting (p = 0.02), high-acceleration and deceleration (p = 0.04), sprinting distance relative per minute played (p = 0.005), and high-acceleration and deceleration relative per minute played (p < 0.001) when the team plays at home, strong opponents, and wins the matches. Starters covered greater total distance in high-speed running (p = 0.04), high-acceleration and deceleration (p = 0.03), and high-speed running relative per minute played (p = 0.04) when the team plays strong opponents and wins the matches. These findings highlight the impact of contextual factors during matches on the locomotor performance of young soccer players.

Correlations of passes and playing formations with technical-tactical elements during the 2022 FIFA World Cup

BACKGROUND

This study on the 2022 Qatar FIFA World Cup examined: a) the existence of correlations between passes with other technical-tactical elements, b) the differences in technical-tactical elements in relation to team formation, and c) the characteristics of the key passes created during games.

METHODS

Sixty-four games were analyzed. Match-analysis data were collected using InStat database.

RESULTS

Spearman correlation revealed that the number of passes and key passes correlated with number of goals, chances and shots (P<0.05). Team ball possession was correlated with number of passes, key passes, chances, shots and the organized attacks (P<0.001). Kruskal-Wallis H non-parametric test revealed that the teams with the higher percentages of team ball possession, and the higher number of chances, shots and crosses used formations 1-4-2-3-1 and 1-4-3-3. Finally, most of the key passes performed in axis of the field and they were short low passes.

CONCLUSIONS

The ability of teams to keep the possession of the ball, looking for the key pass, and final action can be a factor in the team's success. A characteristic finding of the study was the preference of groups to manifest their attack from the axis. The equal distribution of attacks between the axis and the sides of the field makes the team's offensive function more unpredictable. Also, most formations concentrate several players on the axis, making it more difficult to complete an attack from this area.

The impact of crowd effects on home advantage of football matches during the COVID-19 pandemic-A systematic review

This review aimed to (1) analyze whether the home advantage was diminished; (2) investigate the impact of the crowds' support on the match outcome and team performance; (3) explore the bias of the referee without crowds. Based on the PRISMA 2020 (Preferred Reporting Items for Systematic Reviews and Meta-analyses) guidelines, this systematic review searched of literature was conducted in December 2022. The keywords related to soccer, COVID-19 and home advantage were used. The search returned 135 articles. After screening the records against set criteria, 28 articles were analyzed. Results showed that the absence of crowds would reduce the home advantage of teams, but the findings varied by country. Most leagues have evidence that without the support of the spectators, their technical, tactical and physical performances would be worse. The referee seems likely to be fairer when the spectators are absent. Therefore, crowd supports is an important factor affecting home advantage, the clubs can at least try to strengthen the home advantage and increase the winning possibility by encouraging spectators to enter the stadium or reducing the ticket price.

Artificial Turf Increases the Physical Demand of Soccer by Heightening Match Running Performance Compared with Natural Grass

ABSTRACT

Modric, T, Esco, M, Perkovic, S, Basic, Z, Versic, S, Morgans, R, and Sekulic, D. Artificial turf increases the physical demand of soccer by heightening match running performance compared with natural grass. J Strength Cond Res 37(11): 2222-2228, 2023-This study aimed to determine differences in match running performance (MRP) of elite soccer players (n = 31) during matches played on artificial turf (AT) and natural grass (NG). The players' MRP (AT; 131 observations, NG; 135 observations) were collected during official matches (n = 32) using global positioning system and classified according to their playing positions as central defenders, central midfielders, fullbacks, forwards, and wingers. The MRP variables included total distance covered (TD), low-intensity running (LIR), moderate-intensity running (MIR), high-intensity running (HIR), total (Tacc) and high-intensity accelerations (Hacc), and total (Tdec) and high-intensity decelerations (Hdec). The influence of match outcome, location, and opponent quality was controlled for as contextual factors. Playing matches on AT resulted in (a) increased TD (Cohen's d (d) = 0.55, 0.61, and 0.28, respectively), MIR (d = 0.91, 0.79, and 0.49, respectively), and HIR (d = 0.67, 0.44, and 0.38, respectively) for central defenders, central midfielders, fullbacks; (b) increased Tacc (d = 0.38, 0.37, and 0.4, respectively) and Tdec (d = 0.31, 0.34, and 0.31, respectively) for central defenders, central midfielders, and wingers; and (c) decreased Hdec (d = -1.5) for forwards. These results show that playing on AT is more physically demanding for defensive and midfield players than playing on NG. Soccer coaches should consider implementing preparatory strategies that mitigate the increased demands of playing on AT for these players, especially before a competitive period when transitions between pitch surfaces routinely occur.

Evolution of Tactics in Professional Soccer: An Analysis of Team Formations from 2012 to 2021 in the Spanish LaLiga

The aim of this investigation was to explore the evolution of team formations (TFs) in a top national professional soccer league. A comparative analysis of a total of 3420 matches was performed in 32 professional soccer teams that competed from the 2012/13 to the 2020/21 season in the Spanish LaLiga. The frequency distribution of TFs across seasons presented a statistically significant change (p < 0.001). A 4.2-3.1 TF was most common from 2012/13 to 2016/17, while a 4.4.2 TF was most used from 2017/18 to 2020/2021. TFs such as 4.3.3 and 4.5.1 showed a relatively stable trend over the seasons. Overall, there was a reduction of TFs with 5 midfielders and an increase in the frequency of 2-forward formations (p < 0.001). When the ranking of teams was considered, a 4.3.3 TF was implemented with higher frequency by the Champion and teams that qualified for the Champions League (p < 0.05). However, a 4.2-3.1 TF was most frequent for teams qualified for the UEFA Europa League or teams that got relegated to an inferior category (p < 0.05). These findings highlight that teams competing in LaLiga evolved from the implementation of very few TFs led by the 4.2-3.1 TF, towards a more diverse scenario with a greater variety of tactical positional structures.

Match Load Physical Demands in U-19 Professional Soccer Players Assessed by a Wearable Inertial Sensor

BACKGROUND

Wearable inertial sensors are poorly used in soccer to monitor external load (EL) indicators. However, these devices could be useful for improving sports performance and potentially reducing the risk of injury. The aim of this study was to investigate the EL indicators (i.e., cinematic, mechanical, and metabolic) differences between playing positions (i.e., central backs, external strikers, fullbacks, midfielders, and wide midfielder) during the first half time of four official matches (OMs).

METHODS

13 young professional soccer players (Under-19; age: 18.5 ± 0.4 years; height: 177 ± 6 cm; weight: 67 ± 4.8 kg) were monitored through a wearable inertial sensor (TalentPlayers TPDev, firmware version 1.3) during the season 2021-2022. Participants' EL indicators were recorded during the first half time of four OMs.

RESULTS

significant differences were detected in all the EL indicators between playing positions except for two of them (i.e., distance traveled in the various metabolic power zones (<10 w) and the number of direction changes to the right >30° and with speed >2 m). Pairwise comparisons showed differences in EL indicators between playing positions.

CONCLUSIONS

Young professional soccer players showed different loads and performances during OMs in relation to playing positions. Coaches should consider the different physical demands related to playing positions in order to design the most appropriate training program.

Extended Energy-Expenditure Model in Soccer: Evaluating Player Performance in the Context of the Game

Every soccer game influences each player's performance differently. Many studies have tried to explain the influence of different parameters on the game; however, none went deeper into the core and examined it minute-by-minute. The goal of this study is to use data derived from GPS wearable devices to present a new framework for performance analysis. A player's energy expenditure is analyzed using data analytics and K-means clustering of low-, middle-, and high-intensity periods distributed in 1 min segments. Our framework exhibits a higher explanatory power compared to usual game metrics (e.g., high-speed running and sprinting), explaining 45.91% of the coefficient of variation vs. 21.32% for high-, 30.66% vs. 16.82% for middle-, and 24.41% vs. 19.12% for low-intensity periods. The proposed methods enable deeper game analysis, which can help strength and conditioning coaches and managers in gaining better insights into the players' responses to various game situations.

Effects of match contextual factors on internal and external load in elite Brazilian professional soccer players through the season

This study aimed to investigate the effects of contextual match factors (quality of opposition, match outcome, change of head coach or playing style) on internal and external load in elite Brazilian professional soccer players, considering the total and effective playing time. Twenty-two professional male outfield soccer players participated in this study (age 28.4 ± 4.9 years; height 1.78 ± 0.1 cm; body mass 72.9 ± 7.1 kg). The internal (rating of perceived exertion-based load [sRPE]) and external load (distance and accelerometry-based measures) were recorded during 38 matches, over the 2021 season of the Brazilian National 1st Division League using a global position system (10 Hz) integrated with an accelerometer (200 Hz). The main results were: (i) matches played against weak opponents presented greater values of sprinting distances compared to matches against intermediate and strong opponents; (ii) players covered greater high-intensity running distances when drawing than winning the matches; (iii) matches with assistant coaches presented higher mean speed relative to effective playing time (MSEPT) compared to coach 1 and coach 2 conditions. In addition, players covered greater MSEPT and high-acceleration in matches with coach 2 vs. coach 3; (iv) finally, small positive correlations were observed between positional attack sequences and MSTPT, total distance covered, and acceleration. Coaches and practitioners should consider these results when interpreting external load variables during elite Brazilian soccer matches.

Congested Period in Professional Youth Soccer Players Showed a Different High Decelerations Profile in the Group Performance and a Specific Positional Behaviour

Present soccer demands are increasing in terms of running requirements and the number of matches until youth soccer players experience several periods of fixture congestion during the season. Currently, congested periods have not been extensively studied in this population. For this reason, this study aimed to compare the running demands of professional youth soccer players in congested periods according to their specific playing positions. Twenty youth players were grouped according to their position: Central Defenders (CD), Fullbacks (FB), Midfielders (MF), Wide Midfielders (WM) and Strikers (ST). A GPS system was used to monitor the players during the first (M1), second (M2) and third (M3) matches played during a congested period, measuring their total distance covered (TDC), DC 18.0−20.9 km·h−1, DC 21.0−23.9 km·h−1, DC > 24.0 km·h−1, number of high accelerations (>2.5 m·s−2), number of high decelerations (<2.5 m·s−2) and peak speed (km·h−1). M1, M2 and M3 showed the same TDC, DC 18.0−20.9 km·h−1, DC 21.0−23.9 km·h−1, DC > 24.0 km·h−1, number of high accelerations, and peak speed (p > 0.05). The statistical analysis showed significant differences between M1, M2 and M3 in the decelerations recorded between M1 and M3 (p < 0.05). Likewise, each position showed specific behaviours during the congested period, with all showing at least one difference in DC 18.0−20.9 km·h−1, 21.0−23.9 km·h−1 or >24.0 km·h−1 between M1, M2 and M3 (p < 0.05). In conclusion, coaches should pay attention to the fatigue produced by the number of high decelerations. Secondly, an individualized training protocol should be considered according to the running requirements of each position when youth professional soccer players are involved in a congested period.

The influence of physical performance on technical and tactical outcomes in the UEFA Champions League

BACKGROUND

To clarify does physical performance affect success in highest-level soccer, the purpose of the present study was to identify differences in technical-tactical performance (TP) between teams covering high and low running performance (RP) during the UEFA Champions League (UCL) matches.

METHODS

The RP and TP data were collected from UCL group stage matches in the 2020/21 season. RP variables included total distance covered (TD), high intensity running (HIR), total distance when in ball possession (TDB), and high intensity running when in ball possession (HIRB). TP variables included goal chances, shots, shots on target, passes, accurate passes, key passes, key passes accurate, crosses, crosses accurate, counter attacks, counter attacks with a shot, high pressing, high pressing successful, low pressing, low pressing successful, tackles, tackles successful, entrances to the opponent's box, total actions, and successful actions. K-means cluster analysis method was used to classify teams covering (i) low and high TD, (ii) low and high HIR, (iii) low and high TDB, (iv) low and high and HIRB. Linear mixed models were used to identify differences in teams' TP according to their RP. Pearson's correlations were used to establish direct association between team TP and RP.

RESULTS

Similar TP were observed whether teams covering high or low TD/HIR. Teams covering greater TDB/HIRB had more goal chances, shots, shots on target, passes, accurate passes, key passes, accurate key passes, crosses, successful high pressing, entrances to the opponent's box, total actions, and successful actions were observed (all moderate to very large effect sizes. Significant association between specific TP variables and TDB/HIRB were evidenced (Pearson's r = 0.35-0.96, all p < 0.05).

CONCLUSION

Covering greater TDB and HIRB may allow more frequent execution of fundamental TP which are considered essential for match success, indicating that RP when team has ball in possession is important determinant of success in highest-level soccer. This study shows that physical performance affect success in highest-level soccer.

Decline in Running Performance in Highest-Level Soccer: Analysis of the UEFA Champions League Matches

It is widely recognized that there is a decline in match running performance (MRP) towards the end of matches. To clarify whether it is primarily a consequence of fatigue, pacing or situational influences, this study aimed to examine MRP across 15-min match periods for players on different playing positions. Players’ MRP (n = 244) were examined from the UEFA Champions League matches (n = 20) using a semiautomatic optical tracking system. Linear mixed models for repeated measures were adjusted to analyze MRP over the six 15-min match periods while controlling the influence of situational factors. No effects of match outcome, match location, team, and opponent quality on total distance (TD) and high-intensity running (HIR) for players in all playing positions were found (F = 0.03−2.75; all p > 0.05). Significant differences in TD (F = 17.57−53.01; η2 = 0.39−0.52, all large effect sizes) and HIR (F = 3.67−7.64; η2 = 0.05−0.19, small to medium effect sizes) among six 15-minute match periods were found for players in all playing positions. In addition, players in all playing positions covered less TD (d = 1.41−2.15, large to very large effect sizes) and HIR (d = 0.16−0.6, trivial to medium effect sizes) in the last compared to the first 15-min match period. No differences in TD and HIR between the last two match periods in the second half were observed. This study confirmed that soccer players reduce MRP towards the end of matches, and suggest that the decline of MPR in highest-level soccer may be a consequence of pacing strategies.

Contextual variables affect peak running performance in elite soccer players: A brief report

The current brief research report aimed to investigate the influence of contextual variables on peak running performance in male elite soccer players. We analyzed 29 matches of an elite soccer team during the Brazilian Serie A 2019. Twenty players were tracked using GPS units. Peak physical performance was determined using moving average running values with different time windows (1, 3, and 5-min periods). The variables analyzed were total distance covered, total distance covered in high-intensity running (≥19.8 km·h-1), and the distance in accelerations (≥2 m·s-2) and decelerations ( ≤-2 m·s-2). Four contextual variables were considered: 1) positional status; 2) match location; 3) match outcome; and 4) match status. Central defenders showed a lower 1-min peak total distance in relation to all other positions (p = 0.001-0.03). Peak physical performance was higher in away matches for high-intensity running, acceleration, and deceleration (p = 0.01-0.03). In matches that ended in losses, peak values for high-intensity running and acceleration were higher compared to draws and wins (p = 0.01-0.04). Regarding the match status, higher values were observed in draws than wins and losses (p = 0.01). Peak running performance vary according to contextual variables of the match in male elite soccer players. Positional differences were found for peak periods, and physical performance was higher in away matches.

Transfering Targeted Maximum Likelihood Estimation for Causal Inference into Sports Science

Although causal inference has shown great value in estimating effect sizes in, for instance, physics, medical studies, and economics, it is rarely used in sports science. Targeted Maximum Likelihood Estimation (TMLE) is a modern method for performing causal inference. TMLE is forgiving in the misspecification of the causal model and improves the estimation of effect sizes using machine-learning methods. We demonstrate the advantage of TMLE in sports science by comparing the calculated effect size with a Generalized Linear Model (GLM). In this study, we introduce TMLE and provide a roadmap for making causal inference and apply the roadmap along with the methods mentioned above in a simulation study and case study investigating the influence of substitutions on the physical performance of the entire soccer team (i.e., the effect size of substitutions on the total physical performance). We construct a causal model, a misspecified causal model, a simulation dataset, and an observed tracking dataset of individual players from 302 elite soccer matches. The simulation dataset results show that TMLE outperforms GLM in estimating the effect size of the substitutions on the total physical performance. Furthermore, TMLE is most robust against model misspecification in both the simulation and the tracking dataset. However, independent of the method used in the tracking dataset, it was found that substitutes increase the physical performance of the entire soccer team.

Impact of absent crowds on technical and physical performances in the Chinese Soccer Super League

Purpose

Spectators have a significant impact on match performances in soccer, but to what extent crowd support contributes to the technical and physical performances remains unclear. This study aimed to (1) investigate the differences in terms of technical and physical performances with and without spectators; and (2) identify the key factors differentiating between win and loss when playing with and without the presence of an audience.

Methods

Our study examined 794 performance records from 397 matches during the 2019-2020 seasons in the Chinese Soccer Super League. The least absolute shrinkage and selection operator (LASSO)-logistic regression was utilized to select significant predictors. Using an independent t-test and the Mann-Whitney non-parametric test explores the difference between matches with and without spectators. Key factors between win and loss were explored using univariate and multivariate logistic regression analyses.

Results

Our study found that cross (p < 0.01, ES = -0.24), shots (p < 0.001, ES = -0.25), and shot accuracy (p < 0.05, ES = -0.18) displayed decreasing trends whereas sprint distances (p < 0.05, ES = 0.16) presented an increasing trend without spectators comparing with the crowd support. Moreover, the above three technical variables were the main factors differentiating between wins and losses. Similarly, team and opponent quality remained important potential factors affecting the match outcome.

Conclusion

Match outcome or team performance is determined by a myriad of factors, but there are clear differences in technical and physical performances between matches with and without the presence of an audience. Similarly, our study provides a better explanation for the impact of crowd support on match performances whereby coaches can deploy players and adjust match strategies for ultimate success.

How Coaches Can Improve Their Teams' Match Performance-The Influence of In-Game Changes of Tactical Formation in Professional Soccer

The tactical formation has been shown to influence the match performance of professional soccer players. This study aimed to examine the effects of in-game changes in tactical formation on match performance and to analyze coach-specific differences. We investigated three consecutive seasons of an elite team in the German Bundesliga which were managed by three different coaches, respectively. For every season, the formation changes that occurred during games were recorded. The match performance was measured on a team level using the variables "goals," "chances," and "scoring zone" entries (≙successful attacking sequence) for the own/opposing team. Non-parametric tests were used to compare the 10 min before with the 10 min after the formation change, as well as games with and without formation change. In the 10 min after the formation change, the team achieved more goals/chances/scoring zone entries than in the 10 min before the formation change (mean ES = 0.52). Similarly, the team conceded fewer opposing goals/chances/scoring zone entries in the 10 min after the formation change (mean ES = 0.35). Furthermore, the results indicate that the success of the respective formation change was dependent on the responsible coach. Depending on the season, the extent of the impacts varied (season 1: mean ES = 0.71; season 2: mean ES = 0.26; and season 3: mean ES = 0.22). Over all three seasons, the formation changes had a positive effect on the match performance of the analyzed team, highlighting their importance in professional soccer. Depending on the season, formation changes had varying impacts on the performance, indicating coach-specific differences. Therefore, the quality of the formation changes of the different coaches varied. The provided information can support coaches in understanding the effects of their in-game decisions.

Match Running Performance in UEFA Champions League: Is There a Worthwhile Association with Team Achievement?

Although running performance (RP) is considered an important factor of success in soccer, there is a lack of studies to examine this issue in highest-level soccer competition, such as UEFA Champions League (UCL). Therefore, the main objective of this study was to analyse players' RP according to the achievement of their teams in UCL. In addition, position specific RP of the players who competed in the UCL was evaluated. The players' RPs (n = 244) were collected during UCL group stage matches (n = 20) in the 2020/21 season using semiautomatic optical system InStat Fitness. A team's achievement was defined by qualification of the team from the group stage into the knockout stage of the UCL, and by total group points earned at the end of the UCL group stage. Linear mixed models and Pearson's correlation were used to examine differences in players' RP according to the achievement of their teams. Results indicated (i) similar values of RP irrespective of whether the teams qualified from the group stage into the knockout stage of the UCL, and (ii) trivial-to-small correlations between RP and total group points. Such findings show that players' RP was poorly related to the achievement of their teams in the UCL group stage, indicating trivial influence of RP on success in elite-level soccer.

Does Technical Match Performance in Professional Soccer Depend on the Positional Role or the Individuality of the Player?

The aim of the study was to examine the impact of the positional role and the individuality on the technical match performance in professional soccer players. From official match data of the Bundesliga season 2018/19, technical performance [short (<10 m)/medium (10–30 m)/long (>30 m) passes, dribblings, ball possessions] of all players who played during the season were analyzed (normative data). Five playing positions (center back, full back, central midfielder, wide midfielder and forward) were distinguished. As the contextual factor tactical formation is known to influence match performance, this parameter was controlled for. Further, those players who played at minimum four games in at least two different playing positions were included in the study sample (n = 13). The technical match performance of the players was analyzed in relation to the normative data regarding the extent to which the players either adapted or maintained their performance when changing the playing position. When switching playing positions, positional role could explain 3–6% of the variance in short passes and ball possessions and 27–44% of the variance in dribblings, medium passes, and long passes. Moreover, we observed large interindividual differences in the extent to which a player changed, adapted, or maintained his performance. In detail, five players clearly adapted their technical performance when changing playing positions, while five players maintained their performance. Coaches can use these findings to better understand the technical match performance of single players and further, to estimate the impact of a change in the positional role on the technical performance of the respective player.

Center backs work hardest when playing in a back three: The influence of tactical formation on physical and technical match performance in professional soccer

The purpose of this study was to investigate whether tactical formation affects the physical and technical match performance of professional soccer players in the first German Bundesliga. From official match data of the Bundesliga season 2018/19, physical (total distance, high-intensity distance, sprinting distance, accelerations, maximum velocity) and technical performance (short/middle/long passes, dribblings, ball-possessions) of players were analyzed. Players were categorized into five playing positions (center back, full back, central midfielder, wide midfielder, forward) and teams into eight different tactical formations (4-4-2, 4-4-2 diamond, 4-2-2-2, 4-3-3, 4-5-1, 4-2-3-1, 3-4-3, 3-5-2). Results revealed that the degree to which tactical formation affects match performance is position dependent. In terms of physical performance, center backs and full backs showed highest sprinting distances when playing in a formation with only three defenders in the back row (3-4-3, 3-5-2) compared to all other formations (ES range: 0.13≤ES≤1.27). Regarding technical performance, all positions except forwards displayed fewer short passes, middle passes and ball-possessions in the formations 4-3-3 and 4-2-3-1 compared to all other formations (0.02≤ES≤1.19). In conclusion, physical and technical performance of center backs, full backs and wide midfielders differed markedly between the tactical formations. Conversely, the physical and technical performance of central midfielders and forwards only showed small differences between the different tactical formations. These findings can help coaches scheduling their practice. For example, if a coach wants to change the playing formation, he can anticipate the physical and technical match performance changes depending on the respective playing position.

External Match Load in Amateur Soccer: The Influence of Match Location and Championship Phase

Assessment of the physical dimension implicit in the soccer match is crucial for the improvement and individualization of training load management. This study aims to: (a) describe the external match load at the amateur level, (b) analyze the differences between playing positions, (c) verify whether the home/away matches and if (d) the phase (first or second) of the championship influence the external load. Twenty amateur soccer players (21.5 ± 1.9 years) were monitored using the global positioning system. The external load was assessed in 23 matches, where 13 were part of the first phase of the competition (seven home and six away matches) and the other 10 matches belonged to the second (and final) phase of the championship (five home and five away matches). A total of 173 individual match observations were analyzed. The results showed significant differences between playing positions for all the external load measures (p < 0.001). There were higher values observed in the total distance covered for central defenders (p = 0.037; ES = 0.70) and in high-intensity decelerations for forwards (p = 0.022; ES = 1.77) in home matches than in away matches. There were higher values observed in the total distance (p = 0.026; ES = 0.76), relative distance (p = 0.016; ES = 0.85), and moderate-intensity accelerations (p = 0.008; ES = 0.93) for central defenders, in very high-speed running distance for forwards (p = 0.011; ES = 1.97), and in high-intensity accelerations (p = 0.036; ES = 0.89) and moderate-intensity decelerations (p = 0.006; ES = 1.11) for wide midfielders in the first phase than in the second phase of the championship. Match location and championship phase do not appear to be major contributing factors to influence the external load while the playing position should be used as the major reference for planning the external training load.

Variations in the physical demands and technical performance of professional soccer teams over three consecutive seasons

The purpose of this study was twofold: (i) to analyze the seasonal variations in the physical demands of Turkish Super League teams considering their status in the final rankings and (ii) to analyze the seasonal variations in the technical performance of Turkish Super League teams considering their status in the final rankings. This study followed an observational analytic retrospective design. In the last three seasons of the Turkish Super League (2015-2016, 2016-2017 and 2017-2018), 918 football matches, 54 teams, 25,029 observations were made. The Sentio Sports optical tracking system was used to quantify the physical demands and technical execution of players in all matches. No significant differences of external load were found between seasons analyzed (p > 0.05). The number of lost balls, ball touches in the central corridor, and goals from set pieces increased from season one to the others (p < 0.05), while the number of successful dribbles reduced over time (p < 0.05). As conclusion, it seems not occurred a progressive change in external load over the seasons, while an evolutionary trends regarding technical variables were observed.

Impact of COVID-19 lockdown on professional soccer players' match physical activities

AIM

The COVID-19 pandemic forced the 2019-20 Italian Serie A competition to stop and players went into lockdown. During lockdown, players only trained at home, likely having a detrimental effect on players' physical fitness and capacity. This study investigated the effect of the COVID-19 lockdown on professional soccer players' match physical activities.

METHODS

Match activities of 265 male professional soccer players were assessed in two periods prior to (PRE1 and PRE2) and one period following the lockdown (POST) using a video tracking system. Linear mixed models were used to examine differences between-periods in total (TD), very high-speed (VHS), sprint (SPR), high-acceleration (ACC) and high-deceleration (DEC) distances, considering full match data and data from six 15-min intervals.

RESULTS

TD and VHS during POST were lower than the two other competitive periods (p < 0.001, d small-moderate). SPR did not show differences between periods (p > 0.636). ACC and DEC during POST were lower than PRE2 (p < 0.015, d small). Declines in most 15-min intervals after lockdown were observed in TD and VHS.

CONCLUSIONS

There were small differences in the temporal distribution of SPR, ACC and DEC at POST. After the COVID-19 lockdown, soccer players' higher-intensity running activities were similar to those of games played before the lockdown, but TD and VHS decreased, both considering the entire match and 15-min intervals. The temporal distribution of running activities was mostly stable throughout the season.

Contextual Variables Affect Running Performance in Professional Soccer Players: A Brief Report

This study aimed to investigate the effects of contextual variables on running performance in Brazilian professional soccer players. Twenty male players from one club participating in the 1st Division of the Brazilian soccer championship were analyzed during 35 matches. Global Positioning System was used to determine total distance (TD) covered, distance covered and actions in high intensity and sprinting, and the number of accelerations, and decelerations. The independent variables used were match location, match outcome, opposition ranking, change of head coach, and distance traveled to play the matches. Total distance was higher in a way than home matches (9,712 vs. 9,533 m; p ≤ 0.05), and losses than draws and wins (9,846 vs. 9,400 vs. 9,551 m; p ≤ 0.05), whereas distance in sprinting was higher in draws than losses (203 vs. 175 m; p ≤ 0.01). Changing the head coach during the season resulted in overall lower distance covered in high intensity, sprinting, high-intensity actions (p ≤ 0.01), and decelerations (p ≤ 0.05). Higher values for distance covered in sprinting and high intensity were found in matches without travel compared to those with long-travel (p ≤ 0.05). Overall, running performance was affected by the location, match outcome, change of head coach, and distance traveled during the season.

Influence of contextual factors on physical demands and technical-tactical actions regarding playing position in professional soccer players

Background

The aim of this study was to analyse the physical demands and technical-tactical actions for each playing position according to game location and final outcome in professional soccer players.

Methods

A convenience sample was obtained from twenty-one professional male soccer players, belonged to same soccer team of the Spanish Second Division. Players’ physical demands were monitored during each match using a portable 18 Hz GPS unit and 600 Hz triaxial accelerometer. These analysed demands were total distance, moderate speed running distance (>14.4 km·h^-1), high-speed running distance (>19.8. km·h-1), sprint distance (>25.0 km·h^-1), number of accelerations between 2 and 4 m·s^-2 and above 4 m·s^-2, and number of decelerations between 2 and 4 m·s^-2 and above 4 m·s^-2. The data related to technical-tactical actions were obtained from WyScout®, a computerized multiple-camera tracking system based on the OPTA® track analysis tool. The obtained indicators were general, defensive and offensive.

Results

For all players, higher total distance (p = 0.045; effect size [ES] = 0.24, small effect) was covered and greater deceleration 2-4 m·ss^-2 (p = 0.001; ES = 0.68, medium effect) was performed when the team plays at home and lose and for all players, playing at home and winning demanded higher defensive volume (p =0.014; ES = − 1.49, large effect) and nº interceptions (p =0.031; ES = − 1.40, large effect) in comparison to playing at home and losing.

Conclusions

The physical demands and technical-tactical actions vary when contextual game factors (i.e., match location and final outcome) are considered. We can confirm that, although the training of physical demands does not influence the final result of the match, the training of technical tactical actions could help to achieve an optimal performance of the team to win matches.

Guardiola, Klopp, and Pochettino: The Purveyors of What? The Use of Passing Network Analysis to Identify and Compare Coaching Styles in Professional Football

We applied social networks analysis to objectively discriminate and describe interpersonal interaction dynamics of players across different top-coaching styles. The aim was to compare metrics in the passing networks of Jürgen Klopp, Pep Guardiola, and Mauricio Pochettino across the UEFA Champions League seasons from 2017 to 2020. Data on completed passes from 92 games were gathered and average passing networks metrics were computed. We were not only able to find the foundations on which these elite coaches build the passing dynamics in their respective teams, but also to determine important differences that represent their particular coaching signatures. The local cluster coefficient was the only metric not significantly different between coaches. Still, we found higher average shortest-path length for Guardiola's network (mean ± std = 3.00 ± 0.45 a.u.) compared to Klopp's (2.80 ± 0.52 a.u., p = 0.04) and Pochettino's (2.70 ± 0.39 a.u., p = 0.01). Density was higher for Guardiola's (64.16 ± 20.27 a.u.) than for Pochettino's team (51.42 ± 17.28 a.u., p = 0.008). The largest eigenvalue for Guardiola's team (65.95 ± 16.79 a.u.) was higher than for Klopp's (47.06 ± 17.25 a.u., p < 0.001) and Pochettino's (42,62 ± 12.01 a.u., p < 0.001). Centrality dispersion was also higher for Guardiola (0.14 ± 0.02 a.u.) when compared to Klopp (0.12 ± 0.03 a.u., p = 0.008). The local cluster coefficient seems to build the foundation for passing work, however, cohesion characteristics among players in the three teams of the top coaches seems to characterize their own footprint regarding passing dynamics. Guardiola stands out by the high number of passes and the enhanced connection of the most important players in the network. Klopp and Pochettino showed important similarities, which are associated to preferences toward more flexibility of interpersonal linkages synergies.

Impact of Possession and Player Position on Physical and Technical-Tactical Performance Indicators in the Chinese Football Super League

The purpose of this study was to investigate the impact of high (HPBPT) and low percentage ball possession teams (LPBPT) on physical and technical-tactical performance indicators in the Chinese Football Super League (CSL). Eight physical performance indicators and 26 technical-tactical performance indicators from all 240 matches from season 2018 were analyzed, as well as three contextual variables (team strength, quality of opposition, and match location). Players were divided according to five positions: fullbacks, central defenders, wide midfielders, central midfielders, and attackers. A k-means cluster analysis was conducted to classify all match observations into two groups: HPBPT (n = 229) and LPBPT (n = 251). A mixed linear model was fitted with contextual variables as covariates. When significant interactions or main effects were detected, a post hoc comparison was used to compare physical and technical/tactical differences between HPBPT and LPBPT. Results showed that central defenders and fullbacks covered more high-intensity and sprint running distance in the high possession teams, while wide midfielders and forward covered more high-intensity and sprint running distance in the low possession teams. Meanwhile, players from high ball possession teams were strong in technical indicators, especially in attacking organization. These results may help coaches to understand current football development trends and develop suitable training plans and tests for elite football players.

The Influence of Time Winning and Time Losing on Position-Specific Match Physical Demands in the Top One Spanish Soccer League

The aim of the present study was to analyze the influence of time winning and time losing on position-specific match physical demands with and without ball possession in the top Spanish professional soccer league. All matches played in the First Spanish soccer league over four consecutive seasons (from 2015/16 to 2018/19) were recorded using an optical tracking system (i.e., ChyronHego), and the data were analyzed via Mediacoach®. Total distance (TD), and TD > 21 km·h-1 covered with and without ball possession were analyzed using a Linear Mixed Model, taking into account the contextual variables time winning and losing. Results showed that TD and TD > 21 km·h-1 covered by central midfielders (0.01 and 0.005 m/min, respectively), wide midfielders (0.02 and 0.01 m/min, respectively), and forwards (0.03 and 0.02 m/min, respectively) significantly increased while winning (p < 0.05). By contrast, TD and TD > 21 km·h-1 covered by central defenders (0.01 and 0.008 m/min, respectively) and wide defenders (0.06 and 0.008 m/min, respectively) significantly increased while losing (p < 0.05). In addition, for each minute that teams were winning, total distance with ball possession (TDWP) decreased, while, for each minute that teams were losing, TDWP increased. Instead, TDWP > 21 km·h-1 obtained opposite results. Total distance without ball possession increased when teams were winning, and decreased when teams were losing. Therefore, the evolution of scoreline significantly influences tactical-technical and physical demands on soccer matches.

Match-related physical performance in professional soccer: Position or player specific?

The purpose of this study was to examine to what extent the physical match performance of professional soccer players is both position and player specific. First, official match data from the 2019/20 German Bundesliga season was used to search for players that met the inclusion criteria of playing a minimum of four entire matches in at least two different playing positions. Overall, 25 players met the criteria prior to the COVID-19 induced break, playing a minimum of eight matches. Second, the physical match performance of these players was analyzed separately for each position they played. The following four parameters were captured: total distance, high-intensity distance, sprinting distance, and accelerations. Third, the 25 players’ physical match performance data was then compared to normative data for each position they played to understand whether players adapted their physical performance (position dependent), or maintained their performance regardless of which position they were assigned to (position independent). When switching the position, the change in physical match performance of the respective players could be explained by 44–58% through the normative positional data. Moreover, there existed large individual differences in the way players adapted or maintained their performance when acting in different positions. Coaches and practitioners should be aware that some professional soccer players will likely incur differences in the composition of physical match performance when switching positions and therefore should pay special consideration for such differences in the training and recovery process of these players.

Physical Activity of the Right- and Left-Footed Professional Soccer Players from Symmetrical Defensive Positions

The main purpose of this study was to compare the physical match performance of right- and left-footed external defenders during official matches of Polish Ekstraklasa. The sample comprised 991 individual observations from 296 matches during the 2019/2020 season. Variables such as total distance, distance covered in high-speed running and sprinting, and number of high-intensity runs were analysed. Additionally, the data were presented in relation to match duration and effective playing time. Right external defenders (right ED) covered significantly longer total distance (p < 0.001, 1.5%), high-speed running distance (p < 0.001, 5.6%) and sprinting distance (p < 0.001, 11.4%) compared to left external defenders (left ED). The number of high-intensity runs was greater for right RD as well (p < 0.001, 6.4%). Physical match activity for left ED who are left-footed was significantly higher (p < 0.001) in comparison with right-footed left ED. The number of offensive actions played on the right side of the pitch was significantly (p < 0.001) higher than those performed on the left side. Players whose dominant foot is in accordance with the side of the pitch cover longer distances during the match. Moreover, the number of offensive actions played through the wings could affect the physical performance of external defenders.

Match running performance in Brazilian professional soccer players: comparisons between successful and unsuccessful teams

Background

This study aimed to compare the match running performance between bottom- and top-ranked teams in professional soccer players over the 2020 season of the Brazilian National 2nd Division League. In addition, this study verified the independent and interactive effects of playing position and contextual factors on running outputs between these teams.

Methods

Forty-eight professional male outfield soccer players participated in this study (top-ranked team, n = 24; bottom-ranked team, n = 24). The distance- and accelerometry-based measures were recorded during 69 matches using a global positioning system (10 Hz) integrated with an accelerometer (400 Hz).

Results

The top-ranked team covered greater total distance [median (interquartile range); 10,330.0 m (1430.0)] and high-acceleration [97.0 m (32.0)] than the bottom-ranked team, in home and away matches [p < 0.05, effect size (ES) = small]. The midfielders of the top-ranked team covered higher total distance, high-speed running (> 18 km h⁻¹), high acceleration (≥ 3 m s⁻²), high-deceleration (≤ −3 m s⁻²), and performed more sprints [(> 25 km h⁻¹) compared to midfielders of the bottom-ranked team (p < 0.05, η² = small-moderate]. The matches against top-level opponents required high values of high-acceleration and number of sprints only for the top-ranked team (p < 0.05, ES = small). Independent analysis showed that match outcome (loss vs. draw vs. win) was not influenced by running performance for both bottom- and top-ranked teams (p > 0.05; η² = small). However, the top-ranked team covered greater total distance, high-acceleration/deceleration than bottom-ranked team in loss matches (p < 0.05, η² = small).

Conclusions

These findings should be considered when the coaches and practitioners interpret the match running outputs and when evaluating the effects of training intervention on these performance indicators.

Effects of Match Location, Quality of Opposition and Match Outcome on Match Running Performance in a Portuguese Professional Football Team

The aim of this study was to analyze the effects of match location, quality of opposition and match outcome on match running performance according to playing position in a Portuguese professional football team. Twenty-three male professional football players were monitored from eighteen Portuguese Football League matches during the 2019-2020 season. Global positioning system technology (GPS) was used to collect time-motion data. The match running performance was obtained from five playing positions: central defenders (CD), fullbacks (FB), central midfielders (CM), wide midfielders (WM) and forwards (FW). Match running performance was analyzed within specific position and contextual factors using one-way analysis of variance (ANOVA) for repeated measures, standardized (Cohen) differences and smallest worthwhile change. CM and WM players covered significantly greater total distance (F = 15.45, p = 0.000, η² = 0.334) and average speed (F = 12.79, p < 0.001, η² = 0.294). WM and FB players covered higher distances at high-speed running (F = 16.93, p = 0.000, η² = 0.355) and sprinting (F = 13.49; p < 0.001, η² = 0.305). WM players covered the highest number of accelerations (F = 4.69, p < 0.001, η² = 0.132) and decelerations (F = 12.21, p < 0.001, η² = 0.284). The match running performance was influenced by match location (d = 0.06-2.04; CI: -0.42-2.31; SWC = 0.01-1.10), quality of opposition (d = 0.13-2.14; CI: -0.02-2.60; SWC = 0.01-1.55) and match outcome (d = 0.01-2.49; CI: -0.01-2.31; SWC = 0.01-0.35). Contextual factors influenced the match running performance with differential effects between playing positions. This study provides the first report about the contextual influence on match running performance in a Portuguese professional football team. Future research should also integrate tactical and technical key indicators when analyzing the match-related contextual influence on match running performance.

Early Prediction of Physical Performance in Elite Soccer Matches-A Machine Learning Approach to Support Substitutions

Substitution is an essential tool for a coach to influence the match. Factors like the injury of a player, required tactical changes, or underperformance of a player initiates substitutions. This study aims to predict the physical performance of individual players in an early phase of the match to provide additional information to the coach for his decision on substitutions. Tracking data of individual players, except for goalkeepers, from 302 elite soccer matches of the Dutch 'Eredivisie' 2018-2019 season were used to enable the prediction of the individual physical performance. The players' physical performance is expressed in the variables distance covered, distance in speed category, and energy expenditure in power category. The individualized normalized variables were used to build machine learning models that predict whether players will achieve 100%, 95%, or 90% of their average physical performance in a match. The tree-based algorithms Random Forest and Decision Tree were applied to build the models. A simple Naïve Bayes algorithm was used as the baseline model to support the superiority of the tree-based algorithms. The machine learning technique Random Forest combined with the variable energy expenditure in the power category was the most precise. The combination of Random Forest and energy expenditure in the power category resulted in precision in predicting performance and underperformance after 15 min in a match, and the values were 0.91, 0.88, and 0.92 for the thresholds 100%, 95%, and 90%, respectively. To conclude, it is possible to predict the physical performance of individual players in an early phase of the match. These findings offer opportunities to support coaches in making more informed decisions on player substitutions in elite soccer.

Will Next Match Location Influence External and Internal Training Load of a Top-Class Elite Professional European Soccer Team?

Background: The purpose of this study is to compare training load (TL) preceding a home versus away match in a top-class elite European team during the 2015–2016 season. Methods: Twenty elite outfield soccer players with a mean ± SD age, height and body mass of 25.9 ± 4.6 years, 183.1 ± 6.6 cm and 78.6 ± 6.6 kg, respectively, participated in this study. Total distance covered, high-speed running distance (HSRD), average speed (AvS), rating of perceived exertion (RPE) multiplied by training duration (s-RPE) and Hooper index (HI) were collected. Data from 24 weeks were analyzed through match-day minus/plus approach (MD-5, -4, -3, -2, -1, MD + 1). Results: All external TL variables indicated a decrease from MD-5 until MD-1 and then an increase to MD + 1 (p < 0.01). HI decreased from MD-5 to MD-1, but s-RPE increased until MD-3 and then decreased until MD + 1. When comparing TL data that preceded home matches versus away matches, for MD-5, HSRD and muscle soreness exhibited higher values when away match neared (p < 0.05). For MD-4 and MD-3, total distance, HSRD and AvS exhibited higher values closer to an away match than a home match (p < 0.05). For MD-1, total distances covered were higher closer to a home match than an away match (p < 0.01). For MD + 1, all HI items and AvS were higher when an away match was played (p < 0.05). Conclusions: This study confirms and provides evidence regarding the influence on internal and external TL data preceding home and away matches from a team that played in European competitions.

The Influence of Playing Formation on Physical Demands and Technical-Tactical Actions According to Playing Positions in an Elite Soccer Team

The aim of this study was to examine the differences in the physical demands and technical-tactical actions encountered by soccer players between two playing formations (1-4-2-3-1 and 1-4-4-2) for each playing position. Twenty-three professional male soccer players who played 31 official matches participated in this study. Players were classified according to their playing position: central defenders (CD), wide defenders (WD), central midfielders (CM), wide midfielders (WM), offensive midfielders (OM) and forwards (FW). The physical demands were collected as total distance (TD), distance covered in different speed thresholds, and number of accelerations and decelerations. Also, the technical-tactical variables were recorded. The results showed that the 1-4-2-3-1 playing formation demanded decelerations between 2–4 m·s² (p = 0.027; ES = 0.26) in comparison with 1-4-4-2 for all players. Likewise, forwards (FW) and central midfielders (CM) registered higher physical demands playing with the 1-4-2-3-1 compared to the 1-4-4-2 formation. Regarding the technical-tactical actions, they showed differences between the playing positions of the two playing formations. The findings suggest coaches prescribe specific training programs based on the influence of the playing formation and playing position on the physical demands and technical-tactical actions encountered by players during official match-play.

Relationships Between Aerobic Performance, Hemoglobin Levels, and Training Load During Small-Sided Games: A Study in Professional Soccer Players

The purposes of this study were (1) to analyze between-session variations of external and internal load measures during small-sided games (SSGs) and (2) to test the relationships between the maximum speed reached (VIFT) during the last stage of the 30-15 Intermittent Fitness Test, hemoglobin levels, and training load measures during SSG intervals among professional soccer players. Sixteen professional soccer players (mean ± SD; age 27.2 ± 3.4 years, height 174.2 ± 3.6 cm, body mass 69.1 ± 6.4 kg, and body fat 10.4 ± 4.1%) participated in this study. Hemoglobin and aerobic performance were first tested, and then a 3-week SSG program was applied using a 3 vs. 3 format. During those 3 weeks, internal and external load of entire sessions were also monitored for all training sessions. Trivial-to-small, standardized differences were observed between sessions for external and internal measures during SSGs. Total distance (TD) and mechanical work (MW) were the only variables that indicated small changes. Large-to-very-large relationships were found between VIFT and external loads: TD (r range: 0.69; 0.87), high-intensity running (HIR; r range: 0.66; 0.75), and MW (r range: 0.56; 0.68). Moderate-to-large negative relationships were found between hemoglobin levels and internal loads: Edwards' TRIMP (r range: -0.36; -0.63), %HRmax (r range: -0.50; -0.61), and red zone (r range: -0.50; -0.61). VIFT had unclear relationships with overall internal loads, while hemoglobin levels presented unclear relationships with overall external loads. In conclusion, no meaningful changes were found between sessions considering the format of play used. Additionally, the detected relationships indicate that VIFT and hemoglobin levels are good indicators of the performance capacity and physiological profile of players during SSGs. Also, the use of SSGs protocols as a monitoring complement of the 30-15IFT is suggested.

Physiology Responses and Players' Stay on the Court During a Futsal Match: A Case Study With Professional Players

Physiological responses in futsal have not been studied together with temporal information about the players’ stay on the court. The aim of this study was to compare heart rate (HR) and blood lactate concentration ([La⁻]) responses between 1-H and 2-H considering the time of permanency of the players on the court at each substitution in a futsal match. HR was recorded during entire match and [La⁻] was analyzed after each substitution of seven players. %HR_mean (89.61 ± 2.31 vs. 88.03 ± 4.98 %HR_max) and [La⁻] mean (8.46 ± 3.01 vs. 8.17 ± 2.91 mmol·L⁻¹) did not differ between 1-H and 2-H (ES, trivial-small). Time in intensity zones of 50–100 %HR_max differed only in 60–70 %HR_max (ES, moderate). HR coefficient of variation throughout the match was low (7%) and among the four outfield players on the court (quartets, 5%). Substitutions (2 player’s participation in each half), time of permanence on the court (7.15 ± 2.39 vs. 9.49 ± 3.80 min), ratio between time in- and out-ratio on the court (In:Outcourt = 1:1.30 ± 1:0.48 vs. 1:1.05 ± 1:0.55 min) also were similar between 1-H and 2-H (ES, moderate and small, respectively). Balancing the number of substitutions, and the In:Outcourt ratio of players in both halves of the match, playing lower time at 1-H, ~8 min for each participation in the match, made it possible to maintain intensity of the match in 2-H similar to the 1H. These results are a good guidance to coaches and for application in future studies.

Aerobic fitness and game performance indicators in professional football players; playing position specifics and associations

The aim of this study was to identify associations between aerobic fitness (AF) and game performance indicator (GPI) in elite football. Participants were professional football players (males, n = 16; age: 23.76 ± 2.64; body height: 181.62 ± 7.09 cm; body mass: 77.01 ± 6.34 kg). AF testing was conducted by direct measurement and included VO2max, running speed at aerobic threshold (AeT), and running speed at anaerobic threshold (AT). The GPI were collected by the position-specific performance statistics index (InStat index). The players were observed over one competitive half-season, resulting in 82 game performances, grouped according to the positions in game: defenders (n = 39), midfielders (n = 32) and forwards (n = 11). VO2max was not found to be a good discriminator of AF among different playing positions. AeT (F-test = 26.36. p = 0.01) and AT (F-test = 7.25, p = 0.01) were highest among midfielders, and lowest among forwards. No correlations were found between AF and GPI. This study confirmed that AeT and AT are better indicators of AF than VO2max in football players at different playing positions. The lack of associations between AF and GPI was discussed with regard to calculation of InStat as a GPI.

Node and Network Entropy—A Novel Mathematical Model for Pattern Analysis of Team Sports Behavior

Pattern analysis is a well-established topic in team sports performance analysis, and is usually centered on the analysis of passing sequences. Taking a Bayesian approach to the study of these interactions, this work presents novel entropy mathematical models for Markov chain-based pattern analysis in team sports networks, with Relative Transition Entropy and Network Transition Entropy applied to both passing and reception patterns. To demonstrate their applicability, these mathematical models were used in a case study in football—the 2016/2017 Champions League Final, where both teams were analyzed. The results show that the winning team, Real Madrid, presented greater values for both individual and team transition entropies, which indicate that greater levels of unpredictability may bring teams closer to victory. In conclusion, these metrics may provide information to game analysts, allowing them to provide coaches with accurate and timely information about the key players of the game.

The Impact of Match Location and Players' Physical and Technical Activities on Winning in the German Bundesliga

This study aimed to examine whether the physical and technical activities of soccer players and match locations can be associated with higher or lower odds of winning matches whose outcome can be described as “close.” The study comprised 7972 individual observations of German Bundesliga players during the 2014/2015 (n = 2794), 2015/2016 (n = 2494), and 2016/2017 (n = 2684) seasons. A selection of “close matches” was made, which were defined as those in which the difference in numbers of scored goals was ≤1. Players’ five pitch positions were considered: central defenders, fullbacks, central midfielders, wide midfielders, and forwards. Data on 12 physical and 10 technical activities performed by players during matches as well as on match location were retrieved from the Impire AG (Germany) match analysis system. The study results show that the odds of winning at home are different for each playing position: from 41.99% for wide midfielders to 91.34% for central midfielders. Another conclusion was that one of the key components of the predictive model for forwards is the percentage of overall distance covered at speeds >24 km/h (7.99%), which is a variable with an increasing trend. The proposed model predicts that each 1% increase in this variable will theoretically be associated with a 4.08% raise of the odds of winning in further seasons. The presented statistical model may be used by trainers to identify players’ physical and technical activities and contextual variables that may significantly affect the match outcome. In addition, it can help to determine the individual training load related to the player’s position on the pitch.

Effects of Match-Related Contextual Factors on Weekly Load Responses in Professional Brazilian Soccer Players

This study aimed to quantify the weekly training load distributions according to match location, opponent standard, and match outcome in professional soccer players. Rate-of-perceived-exertion-based training load (sRPE) and distance- and accelerometry-based measures were monitored daily during 52 training sessions and 11 matches performed by 23 players. Athletes who played ≥ 60 min during non-congested weeks were considered for data analysis. The training days close to away matches (e.g., one day before the match = MD-1) presented greater sRPE, distance-based volume measures, and mechanical work (player load) compared to the training days close to home matches (p = 0.001-0.002; effect size (ES) = medium-large). The most distant days of the home matches (e.g., five days before the match = MD-5) presented higher internal and external loads than before away matches (p = 0.002-0.003, ES = medium). Higher sRPE, distance-based volume measures, and mechanical work were found during the middle of the week (e.g., three days before the match, MD-3) before playing against bottom vs. medium-ranking teams (p = 0.001-0.01, ES = small-medium). These metrics were lower in MD-5 before matches against bottom vs. medium-ranking opponents (p = 0.001, ES = medium). Higher values of all external load measures were observed during the training session before winning matches (MD-1) compared to a draw or loss (p < 0.001-0.001, ES = medium-large). In conclusion, the training load distribution throughout the week varied considerably according to match-contextual factors.

Effects of match period and playing position on the individual and collective dynamics in professional soccer: a case study

Abstract This study aimed to compare the width, the length, the length per width ratio, and the stretch index between the first and the second halves in official soccer matches, and to compare the spatial exploration index between players from different positions. Seventeen professional soccer players from a Brazilian club participated in the study and were monitored during six official matches by a GPS device. Collective positional data were compared between the two halves using a paired t-test, while the spatial exploration index was compared between the playing positions and within the halves by a mixed two-way ANOVA. The results revealed no differences between the two halves for the collective variables. The highest values of spatial exploration index were reported for central midfielders and wing forwards. We conclude that the tactical behavior of professional soccer players is position-dependent, and midfielders are the most exploratory players on the pitch.

Analysis of the Association between Running Performance and Game Performance Indicators in Professional Soccer Players

Running performance (RP) and game performance indicators (GPI) are important determinants of success in soccer (football), but there is an evident lack of knowledge about the possible associations between RP and GPI. This study aimed to identify associations between RP and GPI in professional soccer players and to compare RP and GPI among soccer playing positions. One hundred one match performances were observed over the course of half of a season at the highest level of national competition in Croatia. Players (mean ± SD, age: 23.85 ± 2.88 years; body height: 183.05 ± 8.88 cm; body mass: 78.69 ± 7.17 kg) were classified into five playing positions (central defenders (n = 26), full-backs (n = 24), central midfielders (n = 33), wide midfielders (n = 10), and forwards (n = 8). RP, as measured by global positioning system, included the total distance covered, distance covered in five speed categories (walking, jogging, running, high-speed running, and maximal sprinting), total number of accelerations, number of high-intensity accelerations, total number of decelerations, and number of high-intensity decelerations. The GPI were collected by the position-specific performance statistics index (InStat index). The average total distance was 10,298.4 ± 928.7 m, with central defenders having the shortest and central midfielders having the greatest covered distances. The running (r = 0.419, p = 0.03) and high-intensity accelerations (r = 0.493, p = 0.01) were correlated with the InStat index for central defenders. The number of decelerations of full-backs (r = −0.43, p = 0.04) and the distance covered during sprinting of forwards (r = 0.80, p = 0.02) were associated with their GPI obtained by InStat index. The specific correlations between RP and GPI should be considered during the conditioning process in soccer. The soccer training should follow the specific requirements of the playing positions established herein, which will allow players to meet the game demands and to perform successfully.

Play-by-Play Network Analysis in Football

This study identifies dominant and intermediary players in football by applying a play-by-play social network analysis (SNA) on 70 professional matches from the 1. and 2. German Bundesliga during the 2017/2018 season. SNA provides a quantification of the complex interaction patterns between players in team sports. So far, the individual contributions and roles of players in football have only been studied at match-level considering the overall passing of a team. In order to consider the real structure of football, a play-by-play network analysis is needed that reflects actual interplay. Moreover, a distinction between plays of certain characteristics is important to qualify different interaction phases. As it is often impossible to calculate well known network metrics such as betweenness on play-level, new adequate metrics are required. Therefore, flow betweenness is introduced as a new playmaker indicator on play-level and computed alongside flow centrality. The data on passing and the position of players was provided by the Deutsche Fußball Liga (DFL) and gathered through a semi-automatic multiple-camera tracking system. Central defenders are identified as dominant and intermediary players, however, mostly in unsuccessful plays. Offensive midfielders are most involved and defensive midfielders are the main intermediary players in successful plays. Forward are frequently involved in successful plays but show negligible playmaker status. Play-by-play network analysis facilitates a better understanding of the role of players in football interaction.