A new paradigm to understand success in professional football: analysis of match statistics in LaLiga for 8 complete seasons

Winning determinants between top and second division in Chinese professional football leagues: an interpretable machine learning approach

This study investigated the impact of winning determinants in two professional soccer leagues. The sample was composed of 1,440 Chinese Super Football League (CSL) and Chinese Football Association China League (CFACL) matches (CSL matches = 720; CFACL matches = 720) during the 2017-2019 seasons. The study employed eXtreme Gradient Boosting (XGBoost) to assess the importance of 25 indicators exhibiting significant differences (p < 0.05) in their association with match outcomes, and the SHapley Additive explanations (SHAP) was utilized to interpret these findings. The results showed that scoring performance indicators, such as Shots On Target Inside Box (SOTIB), Shots, and Shots On Target (SOT), significantly influenced outcomes in both the CSL ([Formula: see text]=37.854%) and CFACL ([Formula: see text]=38.934%), with SOTIB being the most impactful. Additionally, this study found that defensive feature clearances were highly influential in both leagues, ranking second only to SOTIB of variable importance. Meanwhile, defensive feature fouls were a more significant factor in determining match outcomes in the CFACL than in the CSL. In both the CSL and CFACL, players must prioritize precision in shooting within the penalty area rather than merely increasing the frequency of shots. For CFACL teams, if consistent high-quality passing is unattainable, effective use of set pieces (e.g., free kicks) could serve as an alternative strategy to organize attacks. These findings can assist coaches in formulating tailored tactical strategies suited to the distinct demands of each league level.

Impact of offensive team variables on goal scoring in the first division of the spanish soccer league: a comprehensive 10-year study

This study assessed the impact of team offensive variables on goals scored in Spain's first-division soccer league from 2012-2013 to 2021-2022. A nomothetic multidimensional study was conducted, following the STROBE checklist. From 115 team variables available in the INSTAT database, 57 offensive metrics were selected. The selection was performed independently by five researchers to ensure comprehensive inclusion of relevant metrics. The data included 38 league matches each season, involving 30 teams. The study identified key offensive performance metrics strongly correlated with goals scored. These include shots on target (r = 0.898), chances created (r = 0.871), penalty box entries (r = 0.852), positional attacks with shots (r = 0.818), total shots (r = 0.807), central attacks with shots (r = 0.804), accurate passes (r = 0.760), and efficiency in positional attacks (r = 0.755). The findings underscore the importance of specific offensive metrics in enhancing goal-scoring capabilities. Coaches can improve their team's offensive performance by focusing on passing accuracy, dribbling, and maximizing scoring chances. Successful teams consistently convert attacks into shots on goal through various situations, including central attacks, flanks, counterattacks, corners, and set pieces. Tactical adjustments based on these insights can optimize offensive effectiveness.

Impact of Technical-Tactical and Physical Performance on the Match Outcome in Professional Soccer: A Case Study

Match outcomes and championship rankings are the consequence of the team's technical, tactical, and physical variables. This study aimed to compare physical and modern technical-tactical performance variables between matches with different outcomes for a professional soccer team. Total distance covered, distance covered between 20.0 and 25.0 km/h and at > 25.0 km/h, distance covered at ≥ 3 m/s2 and at ≤ -3 m·s-2 along with several modern technical-tactical variables (expected goals in favor (xG) and against (xGA), expected goals chain in favor (xGC) and against (xGCA) and passes per defensive action (PPDA)) were collected for 71 soccer matches during the 2020/2021 and 2021/2022 seasons from a team competing in the French Ligue 2. These technical-tactical and running performance variables were obtained by a validated video tracking system (OPTA) and their values per match were compared depending on the match outcome which was categorized as "loss" (L), "draw" (D) or "win" (W). No significant differences were observed for the different running metrics depending on the match outcome. However, significant differences were observed for xGA (0.70 ± 0.39 vs. 1.24 ± 0.59; pbonferroni= 0.004) and xGCA (5.38 ± 2.78 vs. 10.92 ± 6.18; pbonferroni = 0.002) between wins and losses, respectively. Additionally, there was a weak, but significant correlation between xGCA and distance covered in acceleration (r = 0.255; p = 0.032) and deceleration (r = 0.237; p = 0.047). In conclusion, while our study found associations between technical-tactical variables and match outcomes, causality cannot be inferred. Improved technical-tactical performance may positively impact the match result, especially by the reduction of the opposing team's goal expectancy. On the contrary, running performance variables showed no associations with the match outcome.

An eight-season analysis of the teams' performance in the Spanish LaLiga according to the final league ranking

This study aimed to analyse the performance of 5,518 collective observations of the Spanish LaLiga teams for eight consecutive seasons (from 2011-12 to 2018-19), considering the final league ranking. The teams were divided into four groups: Europe (from 1st to 6th), Upper-Middle (from 7th to 11th), Lower-Middle (from 12th to 17th) and Relegation (from 18th to 20th). The variables recorded were: Passes, Successful Passes, Crosses, Shots, Goals, Corners, Fouls, Width, Length, Height, distance from the goalkeeper to the nearest defender (GkDef), total distance covered (TD) and number of points accumulated. The main results were that: 1) Europe, being superior to the rest of the groups, showed lower values of Length from 2015-16, and lower values of GkDef from 2014-15; 2) Upper-Middle showed lower values of Length from 2015-16; 3) Lower-Middle showed fewer Shots from 2013-14, and lower values of Length, GkDef and TD from 2014-15; and, 4) Relegation barely showed significant differences between seasons in any variable. The study concludes that the teams of the Europe, Upper-Middle and Relegation groups showed quite stable performance, while the teams of the Lower-Middle group presented a worsening in different dimensions as the seasons progressed. The information provided in this study makes it possible to have reference values that have characterized the performance of the teams for each group.

Evidence for a new model of the complex interrelationship of ball possession, physical intensity and performance in elite soccer

BACKGROUND

How the physical metrics, especially physical intensity, and possession interact with each other, and subsequently combine to influence performance remains opaque. Therefore, we investigated the interrelationship of possession, physical metrics, and team performance in elite soccer.

METHODS

Four seasons of a top European league were used to derive 80 team league performances (points), together with possession and physical data. Physical metrics were absolute distances (m) during the whole match and ball-in-play, and rates of distance covered (m⋅min-1 ) as the index of physical intensity, notably when in-possession/out-of-possession, in total and within five speed categories. Interrelationships of possession, physical metrics, possession, and performance were assessed with Pearson's correlations and mediation analysis.

RESULTS

Overall possession (r = 0.794) and time out-of-possession within the defensive third (r = -0.797) were most strongly correlated with performance. The strong relationships between in-possession distances and performance appeared coincidental due to greater time in-possession. Physical intensity had a complex relationship with possession and performance, with opposite relationships according to possession status: lower physical intensity when in-possession and higher physical intensity when out-of-possession were associated with possession and performance. Mediation analysis revealed the direct, independent importance of possession for team performance; however, the association of physical intensity with performance was largely (>79%) mediated by possession.

CONCLUSION

Based on these findings, we propose a novel model of the interrelationships between possession, physical intensity, and performance, whereby higher possession is the largest, direct contributor toward enhanced team performance, with lower physical intensity in-possession a consequence of higher possession, but greater physical intensity when out-of-possession a cause of increased possession.

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.

Deciphering the offensive process in women's elite football: a multivariate study

Over the last few years there has been considerable increase in scientific knowledge about women's football. However, the tactical and tactical-strategic aspects have not yet been sufficiently covered in scientific literature. Therefore, this work proposed the following aims: to describe how the offensive phase is produced in women's football, to identify the significant statistical criteria that may be modulating success in attack, and finally to propose different predictive success models, with the ultimate aim of passing this knowledge on to the applied field. The observational methodology was used, one of the most appropriate methodologies for the analysis of motor behaviors in sport. The units of analysis collected and analysed were 6,063 attacks carried out during the FIFA Women's World Cup Canada 2015 and France 2019. The available results demonstrate that, on the one hand, offensive team actions are ineffective (almost 70% finish unsuccessfully), but criteria such as the start form of the attack, zone of ball possession, partial match result or ball possession time are statistically significant criteria that modulate attack success (goal, shot or pass into the area). Lastly, the multivariate results allow us to propose a theoretical model, passing the probability of success from 31% in the absence of a model, to a theoretical auction probability of 52.6%, based on fast attacks with the intervention of few players, and with possession zone in the opposite field. These results could be directly transferred to the practical field where trainers and technical bodies can put this information into practice in training sessions or matches.

Quantifying the Effectiveness of Defensive Playing Styles in the Chinese Football Super League

Establishing and illustrating a predictive and prescriptive model of playing styles that football teams adopt during matches is a key step toward describing and measuring the effectiveness of styles of play. The current study aimed to identify and measure the effectiveness of different defensive playing styles for professional football teams considering the opponent's expected goal. Event data of all 1,120 matches played in the Chinese Football Super League (CSL) from the 2016 to 2020 seasons were collected, with fifteen defense-related performance variables being extracted. The PCA model (KMO = 0.76) output eight factors that represented 7 different styles of play (factor 6 and 8 represent one style of play) and explained 85.17% of the total variance. An expected goal (xG) model was built using data related to 27,852 shots. Finally, the xG of the opponent was calculated in the multivariate regression model, outputting five factors that (p < 0.05) explained 41.6% of the total variance in the xG of the opponent and receiving a dangerous situation (factor 7) was the most apparent style (31.3%). Finally, the predicted model with defensive styles correlated with actual xG of the opponent at r = 0.62 using the 2020 season as testing data which showed that the predicted xG was correlated moderately with the actual. The result indicated that if the team strengthened the defense closed to the own goal, high intensity confrontation, and defense of goalkeeper, meanwhile making less errors and receiving less dangerous situations, the xG of the opponent would be greatly reduced.

T-Pattern Detection and Analysis of Football Players' Tactical and Technical Defensive Behaviour Interactions: Insights for Training and Coaching Team Coordination

This article aims to study the coordination of the defenders’ tactical and technical behaviour of successful teams to recover the ball according to contextual variables. A total of 15,369 (480.28 ± 112.37) events and 49 to 12,398 different patterns in 32 games of the 2014 FIFA World Cup’s play-offs were detected and analysed. Results evidenced a T-pattern of the first defender pressuring the ball carrier and his teammates concentrating at the same zone to cover him or space, leading to ball recovery. Field zones, first defender tactical and technical behaviours, and ball carrier first touch constituted opportunities for defenders to coordinate themselves. Moreover, the third defender had a predominant role in his teammates’ temporisation and covering zone behaviours. In the draw, first half, second-tier quality of opponent and play-offs excluding third place and final matches, the ball regularly shifted from upper to lower field zones in short periods, resulting in ball recovery or shot on goal conceded. Defenders performed behaviours farther from the ball carrier, and player-marking were most recurrent to an effective defence. This study’s findings could help coaches give specific tips to players regarding interpersonal coordination in defence and set strategies to make tactical behaviour emerge globally.

In-play forecasting in football using event and positional data

Two highly relevant aspects of football, namely forecasting of results and performance analysis by means of performance indicators, are combined in the present study by analysing the value of in-play information in terms of event and positional data in forecasting the further course of football matches. Event and positional data from 50 matches, including more than 300 million datapoints were used to extract a total of 18 performance indicators. Moreover, goals from more than 30,000 additional matches have been analysed. Results suggest that surprisingly goals do not possess any relevant informative value on the further course of a match, if controlling for pre-game market expectation by means of betting odds. Performance indicators based on event and positional data have been shown to possess more informative value than goals, but still are not sufficient to reveal significant predictive value in-play. The present results are relevant to match analysts and bookmakers who should not overestimate the value of in-play information when explaining match performance or compiling in-play betting odds. Moreover, the framework presented in the present study has methodological implications for performance analysis in football, as it suggests that researchers should increasingly segment matches by scoreline and control carefully for general team strength.

How Positional Constraints Affect Footedness in Football: A Notational Analysis of Five Leagues in Europe

In elite-level soccer, the ability to take shots with both limbs from different positions in the pitch may be key to success. This research aimed to: 1) analyze footedness of elite-football players in European leagues during shooting by computing frequency of right- and left-foot use and accuracy; and 2) investigate whether an athlete's distance from the target (goal, penalty, and outside penalty area) and pitch zone (center, left, or right from the goal) can constrain foot selection during shooting. We analyzed 1826 games from the 2017/18 season, divided between: Spanish LaLiga (380 matches); Italian Serie A (380 matches); English Premier League (380 matches); German Bundesliga (306 matches); and French Ligue 1 (380 matches). Results revealed asymmetrical proportions of foot selection, favoring the preferred foot for right- and left-footed athletes. Frequency of preferred foot selection increased as a function of distance from the target (i.e., the farther the athlete, higher the percentage of preferred foot selection). Shots taken from the left side were more often performed with the right foot and vice-versa, for both left- and right-footed athletes. Interestingly, asymmetries were observed only in foot selection, but not in performance, as success rate did not vary between limbs in any position.

Association between offensive and defensive playing style variables and ranking position in a national football league

The aim of this study was to determine the association of playing style and efficacy variables with football success in a professional football league. Match statistics were obtained from 23 football teams competing in the 2017-2018 and 2018-2019 seasons of the Spanish national league(LaLiga). Offensive and defensive playing style and efficacy variables were calculated. Pearson's correlation coefficient tests and principal component analysis (PCA) were applied to establish the influence of these variables on the number of points obtained at the end of the season and on the ranking position. In isolation, the efficacy of completion showed the highest association with ranking points and position. A two-dimension PCA explained 77.8% of the variance in the ranking position. In dimension-1 (58.5%), game initiative and attack building, and in dimension-2 (19.3%), efficacy of defensive containment and a lower rate of long passes were within the variables that explained more variance in the ranking position. Success in football, measured by ranking position at the end of the Spanish national league, was associated with several playing style and efficacy variables. Overall, a dominant game style with high efficacy to finish attacking plays, and an offensive game initiative, are most associated with successful football.

Perceptions of Football Analysts Goal-Scoring Opportunity Predictions: A Qualitative Case Study

This study aimed to understand the way tactical football analysts perceive the general match analysis issues and to analyze their tactical interpretation of the predictive models of conceded goal-scoring opportunities. Nine tactical analysts responded to the semi-structured interviews that included a general section on the match analysis and a specific one on the results of a study on goal-scoring opportunities conceded by a Spanish La Liga team. Following their transcription, the interviews were codified into categories by the two researchers using Atlas Ti® software. Subsequently, frequency count and co-occurrence analysis were performed based on the encodings. The content analysis reflected that analysts play a crucial role in the analysis of their own team and that of the opponent, the essential skills to exercise as a tactical analyst being "understanding of the game" and "clear observation methodology." Based on the case study of the conceded goal-scoring opportunities, the major causes and/or solutions attributed by analysts in some of the predictive models were the adaptability of the "style of play" itself according to the "opponent" and "pressure after losing."

Understanding gender differences in professional European football through machine learning interpretability and match actions data

After the great success of the Women’s World Cup in 2019, several platforms have started identifying the reasons for gender inequality in European football. Even though these inequalities emerge from a variety of key aspects in the modern sport, we focused on the game and evaluated the main differential features of European male and female football players in match actions data under the assumption of finding significant differences and established patterns between genders. A methodology for unbiased feature extraction and objective analysis is presented based on data integration and machine learning explainability algorithms. Female (\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$n_0 = 1511$$\end{document}n0=1511) and male (\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$n_1 = 2703$$\end{document}n1=2703) data points were collected from event data and categorized by game period and player position. We set up a supervised classification pipeline to predict the gender of each player by looking at their actions in the game. The comparison methodology did not include any qualitative enrichment or subjective analysis to prevent biased data enhancement or gender-related processing. The pipeline included three representative binary classification models; A logic-based Decision Trees, a probabilistic Logistic Regression and a multilevel perceptron Neural Network. Each model tried to draw the differences between male and female data points, and we extracted the results using machine learning explainability methods to understand the underlying mechanics of the models implemented. The study was able to determine pivotal factors that differentiate each gender performance as well as disseminate unique patterns by gender involving more than one indicator. Data enhancement and critical variables analysis are essential next steps to support this framework and serve as a baseline for further studies and training developments.

Influence of Players' Maximum Running Speed on the Team's Ranking Position at the End of the Spanish LaLiga

The maximum running speed that a football player can attain during match play has become one of the most popular variables to assess a player's physical talent. However, the influence of a player's maximum running speed on football performance has not yet been properly investigated. The aim of this study was to determine the influence of a player's peak/maximum running speed on the team's ranking position at the end of a national league. A second aim was to investigate differences in maximum running speed among playing positions. To fulfil this aim, the peak/maximum running speeds of 475 male professional football players were recorded for 38 fixtures of the Spanish first-division league (LaLiga) from the 2017-2018 season (7838 data points). Players' peak running speeds in each match were assessed with a validated multicamera tracking system and associated software (Mediacoach®). Players' maximum running speed was established as the fastest running speed they attained during the entire season. Most players (53.5% of the total) had a maximum running speed in the range of 32.0-33.9 km/h, with only three players (0.6%) with a maximum running speed of over 35.0 km/h. Overall, forwards were faster than defenders and both types of players were faster than midfielders (33.03 ± 1.35 > 32.72 ± 1.32 > 32.08 ± 1.63 km/h; p < 0.001). There was no association between teams' maximum running speed and ranking position at the end of the league (r = -0.356, p = 0.135). The correlations between teams' maximum speeds and ranking position were low for defenders (r = -0.334, p = 0.163), midfielders (r = 0.125, p = 0.610), and forwards (r = -0.065, p = 0.791). As a result, the variance in the ranking position at the end of the season explained by a team's maximum speed was of only 7.5%. Finally, as an average for all teams, players' peak running speeds remained stable at ~30.7 ± 0.6 km/h throughout the whole season. These results suggest that successful and less successful football teams have squads with players able to obtain similar maximum running speeds during match play throughout the season. Hence, players' maximum running speeds have a poor association with the team's ranking position at the end of the Spanish professional national league.

Asymmetries in Football: The Pass—Goal Paradox

We investigate the relation between the number of passes made by a football team and the number of goals. We analyze the 380 matches of a complete season of the Spanish national league “LaLiga" (2018/2019). We observe how the number of scored goals is positively correlated with the number of passes made by a team. In this way, teams on the top (bottom) of the ranking at the end of the season make more (less) passes than the rest of the teams. However, we observe a strong asymmetry when the analysis is made depending on the part of the match. Interestingly, fewer passes are made in the second half of a match, while, at the same time, more goals are scored. This paradox appears in the majority of teams, and it is independent of the number of passes made. These results confirm that goals in the first half of matches are more “costly” in terms of passes than those scored in second halves.

An Extensive Comparative Analysis of Successful and Unsuccessful Football Teams in LaLiga

The characterization of the in-game actions with the strongest influence on victory in football might be useful for designing playing styles that enhance teams’ performance. The aim of this study was to analyze in-game match statistics on the top-3 and bottom-3 teams ranked in LaLiga. Accumulated offensive and defensive match statistics when playing at home and away were obtained from LaLiga for 8 consecutive seasons. Data extraction was performed by computerized video-analysis. The top-3 and bottom-3 teams were compared using independent t-test analysis and the magnitude of the difference was cataloged with effect sizes. Overall, the offensive variable with the greatest magnitude of difference in the top-3 vs. bottom-3 comparison was shooting accuracy (ES ± 90% confidence interval = 4.15 ± 0.52) followed by the number of offsides (2.25 ± 0.60) and corners (2.14 ± 0.61). However, when playing away, the offensive variable with the greatest magnitude of difference in the top-3 vs bottom-3 comparison was the number of shots (3.30 ± 0.44). The defensive variables that best differentiated top 3 - bottom 3 teams were the number of corners (2.16 ± 0.43) and shots conceded (2.04 ± 0.39). In conclusion, the match statistics that best discriminated successful from unsuccessful football teams were shooting accuracy while attacking and the number of shots conceded while defending.