Unlocking the potential of big data to support tactical performance analysis in professional soccer: A systematic review

Exploring the recurrent states of football teams' tactical organization on the pitch during Brazilian official matches

Football teams' tactical organization on the pitch is usually represented by the surface area. Considering the different shapes adopted by the teams during the match, the role of the tactical variability for success is lacking. The aim of this study was to explore and to evaluate the association between recurrent states of tactical organization and technical performance during football matches. A total of 28 teams of Brazilian First Division Championships were analysed. Teams' surface area shapes were represented by the maximum value of the Multiscale Fractal Dimension in each timestamp, producing a time series. Recurrences of states of tactical organization were determined via recurrence plots and recurrence quantitative analysis during attacking and defending phases, and considering the whole match. The outcomes were correlated with nine traditional technical performance indicators. The main results showed that structural recurrence or variability on tactical organization is associated with performance success during the defending and attacking actions. Recurrence plot and measures based on the recurrence density proved to be valuable tools to represent teams' dynamics.

Factors Affecting the Running Performance of Soccer Teams in the Turkish Super League

Performance analysis in sports is a rapidly evolving field, where academics and applied performance analysts work together to improve coaches' decision making through the use of performance indicators (PIs). This study aimed to provide a comprehensive analysis of factors affecting running performance (RP) in soccer teams, focusing on low (LI), medium (MI), and high-speed distances (HI) and the number of high-speed runs (NHI). Data were collected from 185 matches in the Turkish first division's 2021-2022 season using InStat Fitness's optical tracking technology. Four linear mixed-model analyses were conducted on the RP metrics with fixed factors, including location, team quality, opponent quality, ball possession, high-press, counterattacks, number of central defenders, and number of central forwards. The findings indicate that high-press and opponent team quality affect MI (d = 0.311, d = 0.214) and HI (d = 0.303, d = 0.207); team quality influences MI (d = 0.632); location and counterattacks impact HI (d = 0.228, d = 0.450); high-press and the number of central defenders affects NHI (d = 0.404, d = 0.319); and ball possession affects LI (d = 0.287). The number of central forwards did not influence any RP metrics. This study provides valuable insights into the factors influencing RP in soccer, highlighting the complex interactions between formations and physical, technical-tactical, and contextual variables. Understanding these dynamics can help coaches and analysts optimize team performance and strategic decision making.

Data Mining Paths for Standard Weekly Training Load in Sub-Elite Young Football Players: A Machine Learning Approach

The aim of this study was to test a machine learning (ML) model to predict high-intensity actions and body impacts during youth football training. Sixty under-15, -17, and -19 sub-elite Portuguese football players were monitored over a 6-week period. External training load data were collected from the target variables of accelerations (ACCs), decelerations (DECs), and dynamic stress load (DSL) using an 18 Hz global positioning system (GPS). Additionally, we monitored the perceived exertion and biological characteristics using total quality recovery (TQR), rating of perceived exertion (RPE), session RPE (sRPE), chronological age, maturation offset (MO), and age at peak height velocity (APHV). The ML model was computed by a feature selection process with a linear regression forecast and bootstrap method. The predictive analysis revealed that the players' MO demonstrated varying degrees of effectiveness in predicting their DEC and ACC across different ranges of IQR. After predictive analysis, the following performance values were observed: DEC (x¯predicted = 41, β = 3.24, intercept = 37.0), lower IQR (IQRpredicted = 36.6, β = 3.24, intercept = 37.0), and upper IQR (IQRpredicted = 46 decelerations, β = 3.24, intercept = 37.0). The player's MO also demonstrated the ability to predict their upper IQR (IQRpredicted = 51, β = 3.8, intercept = 40.62), lower IQR (IQRpredicted = 40, β = 3.8, intercept = 40.62), and ACC (x¯predicted = 46 accelerations, β = 3.8, intercept = 40.62). The ML model showed poor performance in predicting the players' ACC and DEC using MO (MSE = 2.47-4.76; RMSE = 1.57-2.18: R2 = -0.78-0.02). Maturational concerns are prevalent in football performance and should be regularly checked, as the current ML model treated MO as the sole variable for ACC, DEC, and DSL. Applying ML models to assess automated tracking data can be an effective strategy, particularly in the context of forecasting peak ACC, DEC, and bodily effects in sub-elite youth football training.

Data analytics in the football industry: a survey investigating operational frameworks and practices in professional clubs and national federations from around the world

The use of data and analytics in professional football organisations has grown steadily over the last decade. Nevertheless, how and whether these advances in sports analytics address the needs of professional football remain unexplored. Practitioners from national federations qualified for the FIFA World Cup Qatar 2022™ and professional football clubs from an international community of practitioners took part in a survey exploring the characteristics of their data analytics infrastructure, their role, and their value for elaborating player monitoring and positional data. Respondents from 29 national federations and 32 professional clubs completed the survey, with response rates of 90.6% and 77.1%, respectively. Summary information highlighted the underemployment of staff with expertise in applied data analytics across organisations. Perceptions regarding analytical capabilities and data governance framework were heterogenous, particularly in the case of national federations. Only a third of national federation respondents (~30%) perceived information on positional data from international sports data analytics providers to be sufficiently clear. The general resourcing limitations, the overall lack of expertise in data analytics methods, and the absence of operational taxonomies for reference performance metrics pose constraints to meaningful knowledge translations from raw data in professional football organisations.

The keys of pressing to gain the ball - Characteristics of defensive pressure in elite soccer using tracking data

Recently, the availability of big amounts of data enables analysts to dive deeper into the constraints of performance in various team sports. While offensive analyses in football have been extensively conducted, the evaluation of defensive performance is underrepresented in this sport. Hence, the aim of this study was to analyze successful defensive playing phases by investigating the space and time characteristics of defensive pressure.Therefore, tracking and event data of 153 games of the German Bundesliga (second half of 2020/21 season) were assessed. Defensive pressure was measured in the last 10 seconds of a defensive playing sequence (time characteristic) and it was distinguished between pressure on the ball-carrier, pressure on the group (5 attackers closest to the ball), and pressure on the whole team (space characteristic). A linear mixed model was applied to evaluate the effect of success of a defensive play (ball gain), space characteristic, and time characteristic on defensive pressure.Defensive pressure is higher in successful defensive plays (14.47 ± 16.82[%]) compared to unsuccessful defensive plays (12.87 ± 15.31[%]). The characteristics show that defensive pressure is higher in areas closer to the ball (space characteristic) and the closer the measurement is to the end of a defensive play (time characteristic), which is especially true for successful defensive plays. Defensive pressure is a valuable key performance indicator for defensive play. Further, this study shows that there is an association between the pressing of the ball-carrier and areas close to the ball with the success of defensive play.

Analysis of football research trends using text network analysis

This study was aimed to identify football research trends in various periods. A total of 30,946 football papers were collected from a representative academic database and search engine, the 'Web of Science'. Keyword refinement included filtering nouns, establishing synonyms and thesaurus, and excluding conjunctions, and the Cyram's Netminer 4.0 software was used for network analysis. A centrality analysis was conducted by extracting the words corresponding to the top 2% of the main research topics to obtain the degree and eigenvector centralities. The most frequently mentioned research keywords were injury, performance, and club. Keyword performance showed the highest degree centrality (0.294) and keyword world and cup showed the highest eigenvector centrality (0.710). The keyword with the highest eigenvector degree changed from injury in the 1990s and world in the 2000s to cup since the 2010s. Although various studies on football injuries have been conducted, research on the sport itself has recently been conducted. This study provides fundamental information on football trends from research published over the past 30 years.

Adaptation of YOLOv7 and YOLOv7_tiny for Soccer-Ball Multi-Detection with DeepSORT for Tracking by Semi-Supervised System

Object recognition and tracking have long been a challenge, drawing considerable attention from analysts and researchers, particularly in the realm of sports, where it plays a pivotal role in refining trajectory analysis. This study introduces a different approach, advancing the detection and tracking of soccer balls through the implementation of a semi-supervised network. Leveraging the YOLOv7 convolutional neural network, and incorporating the focal loss function, the proposed framework achieves a remarkable 95% accuracy in ball detection. This strategy outperforms previous methodologies researched in the bibliography. The integration of focal loss brings a distinctive edge to the model, improving the detection challenge for soccer balls on different fields. This pivotal modification, in tandem with the utilization of the YOLOv7 architecture, results in a marked improvement in accuracy. Following the attainment of this result, the implementation of DeepSORT enriches the study by enabling precise trajectory tracking. In the comparative analysis between versions, the efficacy of this approach is underscored, demonstrating its superiority over conventional methods with default loss function. In the Materials and Methods section, a meticulously curated dataset of soccer balls is assembled. Combining images sourced from freely available digital media with additional images from training sessions and amateur matches taken by ourselves, the dataset contains a total of 6331 images. This diverse dataset enables comprehensive testing, providing a solid foundation for evaluating the model's performance under varying conditions, which is divided by 5731 images for supervised system and the last 600 images for semi-supervised. The results are striking, with an accuracy increase to 95% with the focal loss function. The visual representations of real-world scenarios underscore the model's proficiency in both detection and classification tasks, further affirming its effectiveness, the impact, and the innovative approach. In the discussion, the hardware specifications employed are also touched on, any encountered errors are highlighted, and promising avenues for future research are outlined.

Analysis of contextualized intensity in Men's elite handball using graph-based deep learning

Manual annotation of data in invasion games is a costly task which poses a natural limit on sample sizes and the level of granularity used in match and performance analyses. To overcome this challenge, this work introduces FAUPA-ML, a Framework for Automatic Upscaled Performance Analysis with Machine Learning, which leverages graph neural networks to scale domain-specific expert knowledge to large data sets. Networks were trained using position data of match phases (counter/position attacks), annotated manually by domain experts in 10 matches. The best network was applied to contextualize N = 539 matches of elite handball (2019/20-2021/22 German Men's Handball Bundesliga) with 86% balanced accuracy. Distance covered, speed, metabolic power, and metabolic work were calculated for attackers and defenders and differences between counters and position attacks across seasons analyzed with an ANOVA. Results showed that counter attacks are shorter, less frequent and more intense than position attacks and that attacking is more intense than defending. Findings show that FAUPA-ML generates accurate replications of expert knowledge that can be used to gain insights in performance analysis previously deemed infeasible. Future studies can use FAUPA-ML for large-scale, contextualized analyses that investigate influences of team strength, score-line, or team tactics on performance.

Identifying Soccer Players' Playing Styles: A Systematic Review

Identifying playing styles in football is highly valuable for achieving effective performance analysis. While there is extensive research on team styles, studies on individual player styles are still in their early stages. Thus, the aim of this systematic review was to provide a comprehensive overview of the existing literature on player styles and identify research areas required for further development, offering new directions for future research. Following the PRISMA guidelines for systematic reviews, we conducted a search using a specific strategy across four databases (PubMed, Scopus, Web of Science, and SPORTDiscus). Inclusion and exclusion criteria were applied to the initial search results, ultimately identifying twelve studies suitable for inclusion in this review. Through thematic analysis and qualitative evaluation of these studies, several key findings emerged: (a) a lack of a structured theoretical framework for player styles based on their positions within the team formation, (b) absence of studies investigating the influence of contextual variables on player styles, (c) methodological deficiencies observed in the reviewed studies, and (d) disparity in the objectives of sports science and data science studies. By identifying these gaps in the literature and presenting a structured framework for player styles (based on the compilation of all reported styles from the reviewed studies), this review aims to assist team stakeholders and provide guidance for future research endeavors.

Identifying Soccer Teams' Styles of Play: A Scoping and Critical Review

Identifying and measuring soccer playing styles is a very important step toward a more effective performance analysis. Exploring the different game styles that a team can adopt to enable a great performance remains under-researched. To address this challenge and identify new directions in future research in the area, this paper conducted a critical review of 40 research articles that met specific criteria. Following the 22-item Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) guidelines, this scoping review searched for literature on Google Scholar and Pub Med database. The descriptive and thematic analysis found that the objectives of the identified papers can be classified into three main categories (recognition and effectiveness of playing styles and contextual variables that affect them). Critically reviewing the studies, the paper concluded that: (i) factor analysis seems to be the best technique among inductive statistics; (ii) artificial intelligence (AI) opens new horizons in performance analysis, and (iii) there is a need for further research on the effectiveness of different playing styles, as well as on the impact of contextual variables on them.

A vector-agent approach to (spatiotemporal) movement modelling and reasoning

Modelling a complex system of autonomous individuals moving through space and time essentially entails understanding the (heterogeneous) spatiotemporal context, interactions with other individuals, their internal states and making any underlying causal interrelationships explicit, a task for which agents (including vector-agents) are specifically well-suited. Building on a conceptual model of agent space-time and reasoning behaviour, a design guideline for an implemented vector-agent model is presented. The movement of football players was chosen as it is appropriately constrained in space, time and individual actions. Sensitivity-variability analysis was applied to measure the performance of different configurations of system components on the emergent movement patterns. The model output varied more when the condition of the contextual actors (players' role-areas) was manipulated. The current study shows how agent-based modelling can contribute to our understanding of movement and how causally relevant evidence can be produced, illustrated through a spatiotemporally constrained football case-study.

Design and Reliability of an Observational Framework to Evaluate the Individual Offensive Behavior in Youth Soccer-The INDISOC Tool

Despite the great development of match analysis in professional soccer during the last decade, very few studies have assessed the individual technical and tactical behaviors of youth soccer players. The purpose of this paper was to design and assess the reliability of an observational instrument to evaluate the INDIvidual offensive behavior in competitive 7 and 11-a-side SOCcer (INDISOC). A total of eight experts in soccer training and analysis were included in the design of the tool by means of meetings and exploratory observations. This process involved design and re-design steps of the INDISOC tool to its final format which includes twelve dimensions related to the spatial, technical, and tactical constraints of individual behavior in soccer. The unit of analysis was the individual ball possession (IBP), described as the time that starts when a player can perform an action with the ball, and which ends when the IBP for another player begins. In the INDISOC tool, the IBP is analyzed taking into account three temporal moments: (1) receiving the ball, (2) processing the ball, and (3) culminating the individual action. Inter-observer and intra-observer analyses were performed and the kappa (K) coefficients were calculated to test the instrument reliability. The K values showed optimal inter (7-a-side: 0.73-0.95; 11-a-side: 0.76-0.98) and intra-observer (7-a-side: 0.84-1;11-a-side: 0.79-1) reliability levels. These results support the notion that the INDISOC observational tool could be a suitable instrument for analyzing the individual offensive behavior in competitive youth (7-a-side), junior and senior (11-a-side) soccer.

Characterizing player's playing styles based on player vectors for each playing position in the Chinese Football Super League

Characterizing playing style is important for football clubs on scouting, monitoring and match preparation. Previous studies considered a player's style as a combination of technical performances, failing to consider the spatial information. Therefore, this study aimed to characterize the playing styles of each playing position in the Chinese Football Super League (CSL) matches, integrating a recently adopted Player Vectors framework. Data of 960 matches from 2016-2019 CSL were used. Match ratings, and 10 types of match events with the corresponding coordinates for all the line-up players whose on-pitch time exceeded 45 minutes were extracted. Players were first clustered into eight positions. A player vector was constructed for each player in each match based on the Player Vectors using Nonnegative Matrix Factorization (NMF). Another NMF process was run on the player vectors to extract different types of playing styles. The resulting player vectors discovered 18 different playing styles in the CSL. Six performance indicators of each style were investigated to observe their contributions. In general, the playing styles of forwards and midfielders are in line with football performance evolution trends, while the styles of defenders should be reconsidered. Multifunctional playing styles were also found in high-rated CSL players.

A systematic review of match-play characteristics in women's soccer

This review aimed to (1) systematically review the scientific literature evaluating the match-play characteristics of women's soccer, (2) determine the methods adopted to quantify match-play characteristics of women's soccer, and (3) present the physical, technical and tactical characteristics of women's soccer match-play across age-groups, playing standards and playing positions. A systematic search of electronic databases was conducted in May 2021; keywords relating to the population, soccer and match-play characteristics were used. Studies which quantified physical, technical or tactical performance of women's soccer players during match-play were included. Excluded studies included adapted match-play formats and training studies. Sixty-nine studies met the eligibility criteria. Studies predominantly quantified match-play characteristics of senior international (n = 27) and domestic (n = 30) women's soccer match-play, with only seven studies reporting youth match-play characteristics. Physical (n = 47), technical (n = 26) and tactical characteristics (n = 2) were reported as whole-match (n = 65), half-match (n = 21), segmental (n = 17) or peak (n = 8) characteristics. Beyond age-groups, playing standard, and playing position, fourteen studies quantified the impact of contextual factors, such as environment or match outcome, on match-play characteristics. Distance was the most commonly reported variable (n = 43), as outfield women's soccer players covered a total distance of 5480-11160 m during match-play. This systematic review highlights that physical match-performance increases between age-groups and playing standards, and differs between playing positions. However, further research is warranted to understand potential differences in technical and tactical match-performance. Coaches and practitioners can use the evidence presented within this review to inform population-specific practices, however, they should be mindful of important methodological limitations within the literature (e.g. inconsistent velocity and acceleration/deceleration thresholds). Future research should attempt to integrate physical, technical and tactical characteristics as opposed to quantifying characteristics in isolation, to gain a deeper and more holistic insight into match-performance.

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.

Graph representations for the analysis of multi-agent spatiotemporal sports data

Analyzing tactical patterns in invasion games using multi-agent spatiotemporal data is a challenging task at the intersection of computer and sports science. A fundamental yet understudied problem in this area is finding an optimal data representation for processing athlete trajectories using machine learning algorithms. In the present work, we address this gap by discussing common representations in use and propose Tactical Graphs, an alternative graph-based format capable of producing integrative, contextualized models for machine learning applications. We provide an in-depth, domain-specific motivation of the proposed data representation scheme and show how this approach exploits inherent data traits. We propose Tactical Graph Networks (TGNets), a light-weight, hybrid machine learning architecture sensitive to player interactions. Our method is evaluated with an extensive ablation study and the first comprehensive state of the art comparison between standard feature, state vector, and image-based methods on the same dataset. Experiments were conducted using real-world football data containing short sequences of defensive play labelled according to the outcome of ball winning attempts. The results indicate that TGNets are on par with state-of-the-art deep learning models while exhibiting only a fraction of their complexity. We further demonstrate that selecting the right data representation is crucial as it has a significant influence on model performance. The theoretical findings and the proposed method provide insights and a strong methodological alternative for all classification, prediction or pattern recognition applications in the areas of collective movement analysis, automated match analysis, and performance analysis.

College Sports Decision-Making Algorithm Based on Machine Few-Shot Learning and Health Information Mining Technology

Few-Shot Learning has had a significant influence on how people live, work, and learn. Physical education is a requirement for a college diploma. Sports management systems, which focus on data collection, organization, and analysis, as well as timeliness and guidance, are one of the current challenges in the field of physical education at the country’s top colleges and universities. The amount of sex in the room is minimal. Time is money when it comes to making college sports decisions, and this paper uses data from physical fitness tests to illustrate this point. Use Few-Shot Learning technology to extract relevant data from the data, allowing teachers to provide more scientific and effective guidance and suggestions to students. The design and implementation of this paper collect data from physical fitness tests in real-time using mobile edge computing, analyze the data, and display the results using machine learning technology, which mines deep features and displays analysis results, can be used to evaluate students’ physical fitness. The data and information in the physical fitness analysis system are more readable and time-saving, allowing students to better understand their true level of physical fitness. Because of the results of data mining, teachers can provide more specific guidance and recommendations for each student’s physical characteristics.

Who can receive the pass? A computational model for quantifying availability in soccer

The paper presents a computational approach to Availability of soccer players. Availability is defined as the probability that a pass reaches the target player without being intercepted by opponents. Clearly, a computational model for this probability grounds on models for ball dynamics, player movements, and technical skills of the pass giver. Our approach aggregates these quantities for all possible passes to the target player to compute a single Availability value. Empirically, our approach outperforms state-of-the-art competitors using data from 58 professional soccer matches. Moreover, our experiments indicate that the model can even outperform soccer coaches in assessing the availability of soccer players from static images.

Resilience in sports: a multidisciplinary, dynamic, and personalized perspective

Athletes are exposed to various psychological and physiological stressors, such as losing matches and high training loads. Understanding and improving the resilience of athletes is therefore crucial to prevent performance decrements and psychological or physical problems. In this review, resilience is conceptualized as a dynamic process of bouncing back to normal functioning following stressors. This process has been of wide interest in psychology, but also in the physiology and sports science literature (e.g. load and recovery). To improve our understanding of the process of resilience, we argue for a collaborative synthesis of knowledge from the domains of psychology, physiology, sports science, and data science. Accordingly, we propose a multidisciplinary, dynamic, and personalized research agenda on resilience. We explain how new technologies and data science applications are important future trends (1) to detect warning signals for resilience losses in (combinations of) psychological and physiological changes, and (2) to provide athletes and their coaches with personalized feedback about athletes' resilience.

Reference values for collective tactical behaviours based on positional data in professional football matches: a systematic review

Match collective tactical behaviours can be used as a reference to design and select training strategies to improve individual and team performance in professional football. The aim of the systematic review was to cluster the collective tactical variables used to highlight and compare male soccer teams’ collective behaviour during professional official matches, providing reference values for each of them. A systematic review of relevant articles was carried out using three electronic databases (PubMed, SPORTdiscus and Web of Science). From a total of 1,187 studies initially found, 13 original articles were included in the qualitative synthesis. The articles found concerned studies carried out on the Spanish, Portuguese, English and Brazilian 1^st divisions and during the European UEFA Champions League. The team length and width ranged from 31 to 46 m and from 35 to 48 m, respectively. The distance from a defending team’s goalkeeper to the nearest teammate ranged from 9 ± 6 to 30 ± 7 m, the goal line-recovery location from 27 to 37 m, and the opponent’s goal line from 42 to 50 m. The stretch index ranged from 7 to 16 m. Mean team area was ~900 m² and the area of the pitch which included all outfield players divided by the 20 outfield players ranged from 79 ± 15 to 94 ± 16 m². All studies provided greater distance and area values during the team-possession phase in comparison to the non-possession one. The ball location on the pitch determined the collective tactical behaviour of the teams. The differences between halves in the distance and area values were contradictory. Further studies should assess the effect of the interaction between the contextual factors on the collective tactical behaviour to obtain more accurate references. This could help football coaches in the design of suitable training tasks to optimize tactical performance.

Construction and validation of an observation tool of the imbalance pass in futsal

Abstract This study aimed to construct a tool for observing the imbalance pass in futsal through Microsoft Excel® software and to establish its content validity and intra- and interobserver reliability based on the calculation of the content validity coefficient (CVC) and the intraclass correlation coefficient (ICC). For the construction of the tool, futsal specialists (n = 10) with an average age of 44.1 ± 12.34 years and 19 ± 7.21 years of experience in the field participated in the study. 60% of the specialists have international-level expertise and 50% are active in practice and in academic field (higher education professor). According to the methodology, 23 items were proposed to assess the imbalance pass in futsal. CVC was calculated based on language clarity, practical pertinence and theoretical relevance for each item of the instrument and for the instrument as a whole; ICC was calculated based on intra- and interobserver agreement. Language clarity, practical pertinence and theoretical relevance revealed a result of 0.92, 0.93 and 0.95, respectively, and the values for intra- and interobserver agreement reliability were excellent according to the literature (> 0.75). Thus, it is concluded that the items proposed in the tool obtained satisfactory psychometric properties.

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.

The "Hockey" Assist Makes the Difference-Validation of a Defensive Disruptiveness Model to Evaluate Passing Sequences in Elite Soccer

With the growing availability of position data in sports, spatiotemporal analysis in soccer is a topic of rising interest. The aim of this study is to validate a performance indicator, namely D-Def, measuring passing effectiveness. D-Def calculates the change of the teams' centroid, centroids of formation lines (e.g., defensive line), teams' surface area, and teams' spread in the following three seconds after a pass and therefore results in a measure of disruption of the opponents' defense following a pass. While this measure was introduced earlier, in this study we aim to prove the usefulness to evaluate attacking sequences. In this study, 258 games of Dutch Eredivisie season 2018/19 were included, resulting in 13,094 attacks. D-Def, pass length, pass velocity, and pass angle of the last four passes of each attack were calculated and compared between successful and unsuccessful attacks. D-Def showed higher values for passes of successful compared to unsuccessful attacks (0.001 < p ≤ 0.029, 0.06 ≤ d ≤ 0.23). This difference showed the highest effects sizes in the penultimate pass (d = 0.23) and the maximal D-Def value of an attack (d = 0.23). Passing length (0.001 < p ≤ 0.236, 0.08 ≤ d ≤ 0.17) and passing velocity (0.001 < p ≤ 0.690, -0.09 ≤ d ≤ 0.12) showed inconsistent results in discriminating between successful and unsuccessful attacks. The results indicate that D-Def is a useful indicator for the measurement of pass effectiveness in attacking sequences, highlighting that successful attacks are connected to disruptive passing. Within successful attacks, at least one high disruptive action (pass with D-Def > 28) needs to be present. In addition, the penultimate pass ("hockey assist") of an attack seems crucial in characterizing successful attacks.

Data-driven detection of counterpressing in professional football

Detecting counterpressing is an important task for any professional match-analyst in football (soccer), but is being done exclusively manually by observing video footage. The purpose of this paper is not only to automatically identify this strategy, but also to derive metrics that support coaches with the analysis of transition situations. Additionally, we want to infer objective influence factors for its success and assess the validity of peer-created rules of thumb established in by practitioners. Based on a combination of positional and event data we detect counterpressing situations as a supervised machine learning task. Together, with professional match-analysis experts we discussed and consolidated a consistent definition, extracted 134 features and manually labeled more than 20, 000 defensive transition situations from 97 professional football matches. The extreme gradient boosting model—with an area under the curve of $$87.4\%$$ 87.4 % on the labeled test data—enabled us to judge how quickly teams can win the ball back with counterpressing strategies, how many shots they create or allow immediately afterwards and to determine what the most important success drivers are. We applied this automatic detection on all matches from six full seasons of the German Bundesliga and quantified the defensive and offensive consequences when applying counterpressing for each team. Automating the task saves analysts a tremendous amount of time, standardizes the otherwise subjective task, and allows to identify trends within larger data-sets. We present an effective way of how the detection and the lessons learned from this investigation are integrated effectively into common match-analysis processes.

A Goal Scoring Probability Model for Shots Based on Synchronized Positional and Event Data in Football (Soccer)

Due to the low scoring nature of football (soccer), shots are often used as a proxy to evaluate team and player performances. However, not all shots are created equally and their quality differs significantly depending on the situation. The aim of this study is to objectively quantify the quality of any given shot by introducing a so-called expected goals (xG) model. This model is validated statistically and with professional match analysts. The best performing model uses an extreme gradient boosting algorithm and is based on hand-crafted features from synchronized positional and event data of 105, 627 shots in the German Bundesliga. With a ranked probability score (RPS) of 0.197, it is more accurate than any previously published expected goals model. This approach allows us to assess team and player performances far more accurately than is possible with traditional metrics by focusing on process rather than results.

Attacking Key Performance Indicators in Soccer: Current Practice and Perceptions from the Elite to Youth Academy Level

Key Performance Indicators (KPIs) are used to evaluate the offensive success of a soccer team (e.g. penalty box entries) or player (e.g. pass completion rate). However, knowledge transfer from research to applied practice is understudied. The current study queried practitioners (n = 145, mean ± SD age: 36 ± 9 years) from 42 countries across different roles and levels of competition (National Team Federation to Youth Academy levels) on various forms of data collection, including an explicit assessment of twelve attacking KPIs. 64.3% of practitioners use data tools and applications weekly (predominately) to gather KPIs during matches. 83% of practitioners use event data compared to only 52% of practitioners using positional data, with a preference for shooting related KPIs. Differences in the use and value of metrics derived from positional tracking data (including Ball Possession Metrics) were evident between job role and level of competition. These findings demonstrate that practitioners implement KPIs and gather tactical information in a variety of ways with a preference for simpler metrics related to shots. The low perceived value of newer KPIs afforded by positional data could be explained by low buy-in, a lack of education across practitioners, or insufficient translation of findings by experts towards practice.

Machine Learning-Based Identification of the Strongest Predictive Variables of Winning and Losing in Belgian Professional Soccer

This study aimed to identify the strongest predictive variables of winning and losing in the highest Belgian soccer division. A predictive machine learning model based on a broad range of variables (n = 100) was constructed, using a dataset consisting of 576 games. To avoid multicollinearity and reduce dimensionality, Variance Inflation Factor (threshold of 5) and BorutaShap were respectively applied. A total of 13 variables remained and were used to predict winning or losing using Extreme Gradient Boosting. TreeExplainer was applied to determine feature importance on a global and local level. The model showed an accuracy of 89.6% ± 3.1% (precision: 88.9%; recall: 90.1%, f1-score: 89.5%), correctly classifying 516 out of 576 games. Shots on target from the attacking penalty box showed to be the best predictor. Several physical indicators are amongst the best predictors, as well as contextual variables such as ELO -ratings, added transfers value of the benched players and match location. The results show the added value of the inclusion of a broad spectrum of variables when predicting and evaluating game outcomes. Similar modelling approaches can be used by clubs to identify the strongest predictive variables for their leagues, and evaluate and improve their current quantitative analyses.