A Goal Scoring Probability Model for Shots Based on Synchronized Positional and Event Data in Football (Soccer).
Ontology highlight
ABSTRACT:
SUBMITTER: Anzer G
PROVIDER: S-EPMC8056301 | biostudies-literature | 2021
REPOSITORIES: biostudies-literature
Publications
A Goal Scoring Probability Model for Shots Based on Synchronized Positional and Event Data in Football (Soccer).
Anzer Gabriel G Bauer Pascal P
Frontiers in sports and active living 20210329
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 <i>expected goals (xG)</i> model. This model is validated statistically and with professional match analysts. The best performing model uses an extreme gradi ...[more]
Similar Datasets
Project description:Goal celebration in sport is mostly spontaneous and is manifested via vocal expressions and bodily gestures aimed at communicating emotions. The aim of this study is to deconstruct the celebratory acts among elite professional football players in the European Champions League following scoring a goal, and to capture the multiple acts and functions of the celebrations. In examining the 2018/19 season of the European Champions League tournament, we draw attention to the players' celebrations and their corresponding social and individual functions. All goals/celebrations (K = 366) were used for the analyses. To analyze the goal celebration acts, a socio-psychological model was established which is comprised of several theories. To describe the goal celebration acts across the competition stages (e.g., preliminary and final), match location (i.e., home or away), time phase (0-15, 15-45, 45-75, 75-90, 90+ minutes), scoring mode (i.e., prior to the goal, after the goal), and players' continent origin (Europe, Africa, Asia, South/Central, and North America), the number and percent of all the celebratory acts were counted and presented in their respective mode (i.e., single, double, and team). The main findings indicate that (a) most of the goal celebration acts were performed interactively by the scoring player and his teammates, (b) the interactive modes of celebration lasted longer than the modes which were performed non-interactively, (c) the celebration lasted longer following goal scoring in the final stage than in the preliminary stage, (d) the celebration duration lasted the longest time when the goal was scored during the overtime phase (90+ min) of the final but not the preliminary stage, and (e) players from Africa and South America demonstrated religious acts more than their European counterparts. We assert that our conceptual model enables the categorization of a variety of personal and social meanings to the celebrations on the field during the most thrilling moments of the game.
| S-EPMC7494092 | biostudies-literature
Project description: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."
| S-EPMC8450592 | biostudies-literature
Project description:In association football, predicting the likelihood and outcome of a shot at a goal is useful but challenging. Expected goal (xG) models can be used in a variety of ways including evaluating performance and designing offensive strategies. This study proposed a novel framework that uses the events preceding a shot, to improve the accuracy of the expected goals (xG) metric. A combination of previously explored and unexplored temporal features is utilized in the proposed framework. The new features include; "advancement factor", and "player position column". A random forest model was used, which performed better than published single-event-based models in the literature. Results further demonstrated a significant improvement in model performance with the inclusion of preceding event information. The proposed framework and model enable the discovery of event sequences that improve xG, which include; opportunities built up from the sides of the 18-yard box, shots attempted from in front of the goal within the opposition's 18-yard box, and shots from successful passes to the far post.
| S-EPMC11524524 | biostudies-literature
Project description:Social rewards are important incentives for human behavior. This is especially true in team sports such as the most popular one worldwide: soccer. We investigated reward processing upon scoring a soccer goal in a standard two-versus-one situation and in comparison to winning in a monetary incentive task. The results show a strong overlap in brain activity between the two conditions in established reward regions of the mesolimbic dopaminergic system, including the ventral striatum and ventromedial pre-frontal cortex. The three main components of reward-associated learning, i.e., reward probability (RP), reward reception (RR) and reward prediction errors (RPE) showed highly similar activation in both con-texts, with only the RR and RPE components displaying overlapping reward activity. Passing and shooting behavior did not correlate with individual egoism scores, but we observe a positive correlation be-tween egoism and activity in the left middle frontal gyrus upon scoring after a pass versus a direct shot. Our findings suggest that rewards in the context of soccer and monetary incentives are based on similar neural processes.
| S-EPMC4398371 | biostudies-literature
Project description:The majority of soccer analysis studies investigates specific scenarios through the implementation of computational techniques, which involve the examination of either spatiotemporal position data (movement of players and the ball on the pitch) or event data (relating to significant situations during a match). Yet, only a few applications perform a joint analysis of both data sources despite the various involved advantages emerging from such an approach. One possible reason for this is a non-systematic error in the event data, causing a temporal misalignment of the two data sources. To address this problem, we propose a solution that combines the SwiftEvent online algorithm (Gensler and Sick in Pattern Anal Appl 21:543-562, 2018) with a subsequent refinement step that corrects pass timestamps by exploiting the statistical properties of passes in the position data. We evaluate our proposed algorithm on ground-truth pass labels of four top-flight soccer matches from the 2014/15 season. Results show that the percentage of passes within half a second to ground truth increases from 14 to 70%, while our algorithm also detects localization errors (noise) in the position data. A comparison with other models shows that our algorithm is superior to baseline models and comparable to a deep learning pass detection method (while requiring significantly less data). Hence, our proposed lightweight framework offers a viable solution that enables groups facing limited access to (recent) data sources to effectively synchronize passes in the event and position data.
| S-EPMC10518005 | biostudies-literature
Project description:BackgroundPositional data have been used to capture physical and tactical factors in football, however current research is now looking to apply spatiotemporal parameters from an integrative perspective. Thus, the aim of this article was to systematically review the published articles that integrate physical and tactical variables in football using positional data.Methods and materialsFollowing the Preferred Reporting Item for Systematic Reviews and Meta-analyses (PRISMA), a systematic search of relevant English-language articles was performed from earliest record to August 2021. The methodological quality of the studies was evaluated using the modified Downs and Black Quality Index (observational and cross-sectional studies) and the Physiotherapy Evidence Database (PEDro) scale (intervention studies).ResultsThe literature search returned 982 articles (WoS = 495; PubMed = 232 and SportDiscus = 255). After screening, 26 full-text articles met the inclusion criteria and data extraction was conducted. All studies considered the integration of physical and tactical variables in football using positional data (n = 26). Other dimensions were also reported, such as psychophysiological and technical factors, however the results of these approaches were not the focus of the analysis (n = 5). Quasi-experimental approaches considered training sets (n = 20) and match contexts (n = 6). One study analysed both training and play insights. Small sided-games (SSG) were the most common training task formats in the reviewed studies, with only three articles addressing medium-sided (MSG) (n = 1) and large-sided games (LSG) (n = 2), respectively.ConclusionsAmong the current systematic review, the physical data can be integrated by player's movement speed. Positional datasets can be computed by spatial movement, complex indexes, playing areas, intra-team and inter-team dyads. Futures researches should consider applying positional data in women's football environments and explore the representativeness of the MSG and LSG.
| S-EPMC9671036 | biostudies-literature
Project description: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.
| S-EPMC11502709 | biostudies-literature
Project description:BackgroundLateral ankle sprain (LAS) is one of the most common types of injury in football (soccer). Normative baseline data of performance tests for Return to Play (RTP) decision are still lacking.PurposeThe primary aim of this study was to generate baseline values for uninjured elite youth football players for a multifactorial RTP assessment and compare with previously published data. A secondary aim was to investigate the use of the Limb Symmetry Index (LSI) as a method to determine whether an athlete passes a performance test or not.Study designObservational Cohort study.MethodsBaseline data of performance tests (Y-Balance [YBT-LQ], Heel Rise [HRT]; Singe Leg Squat [SLST]; Single Leg Drop Jump [SLDJ]; Side Hop [SHT]; Figure of 8 Hop [F-8]; Modified Agility T-Test [MAT]) were assessed in 20 elite youth football players, aged 16-21 years. Additionally, the traditional LSI (dividing the result of the non-dominant leg by the result of the dominant leg and multiplying by 100) and directionally corrected LSI (the worst value is divided by the better value and multiplied by 100) were calculated. The test values were compared to previously reported study results. LSI and side-to-side comparisons between dominant and non-dominant leg sides were analyzed using the Wilcoxon test.ResultsMale elite youth football players achieved better results in the dynamic performance tests (SHT, F-8, and MAT) compared to reference values of the cohorts previously described in the literature: YBT-LQ total score (cm) dominant (dom) 99.3±8.3, non-dominant (ND) 99.5±10.4; HRT (average number) dom. 27.1±5.4, ND 25.2±5.1); SLDJ height (cm) dom 15±5, ND 15±5 and contact time (sec) dom 0.29±0.08, ND 0.29±0.07, Reactive Strength Index (RSI) dom 0.52±0.12, ND 0.50±0.13); SHT (sec) dom 7.12±0.73, ND 7.39±0.93; F-8 (sec) dom 10.52±1.02, ND 10.37±1.04; and MAT (sec) 5.82±0.22. Directionally corrected LSI differed significantly from the traditional calculated LSI (p<0.05).ConclusionThe findings of this study highlight the need to determine specific baseline data for RTP testing in male elite youth football players after LAS. The traditional LSI should not be used as a "stand alone method" for determining RTP. LSI calculations should consider the direction of asymmetry to determine passing a performance test or not.Level of evidence3b.
| S-EPMC11392466 | biostudies-literature
Project description:BackgroundInjury among soccer referees is rarely studied, especially with regard to differences in the quality level of the refereeing. Additionally, we have found no study that has reported injury occurrence during official physical fitness testing for soccer referees. The aim of this study was to investigate the frequency, type and consequences of match-related and fitness-testing related injuries among soccer referees of different competitive levels.MethodsWe studied 342 soccer referees (all males; mean age 32.9?±?5.02?years). The study was retrospective, and a self-administered questionnaire was used. In the first phase of the study, the questionnaire was tested for its reliability and applicability. The questionnaire included morphological/anthropometric data, refereeing variables, and musculoskeletal disorders together with the consequences.ResultsThe sample comprised 157 main referees (MR; mean age 31.4?±?4.9?years) and 185 assistant referees (AR; mean age 34.1?±?5.1?years) divided into: international level (Union of European Football Associations-UEFA) referees (N?=?18; 6 MRs; 12 ARs) ; 1st (N?=?78; 31 MRs; 47 ARs), 2nd (N?=?91; 45 MRs; 46 ARs); or 3rd national level referees (N?=?155; 75 MRs; 80 ARs). In total, 29% (95%CI: 0.23-0.37) of the MRs and 30% (95%CI: 0.22-0.36) of the ARs had experienced an injury during the previous year, while 13% (95%CI: 0.05-0.14) of the MRs, and 19% (95%CI: 0.14-0.25) of the ARs suffered from an injury that occurred during fitness testing. There was an obvious increase in injury severity as the refereeing advanced at the national level, but the UEFA referees were the least injured of all referees. The results showed a relatively high prevalence of injuries to the upper leg (i.e., quadriceps and hamstrings) during physical fitness testing for all but the UEFA referees. During game refereeing, the ankles and lower legs were the most commonly injured regions. The MRs primarily injured their ankles. The ARs experienced lower leg and lower back disorders. However, the overall injury rate was equal for both groups, with 5.29 (95%CI: 2.23-8.30) and 4.58 (95%CI: 2.63-6.54) injuries per 1000?hours of refereeing for MRs and ARs, respectively.ConclusionIn addition to the reported risk of injury during soccer games, physical fitness testing should be classified as a risk for injury among soccer referees. Special attention should be given to (I) lower leg injuries during games and (II) upper leg injuries during physical fitness tests. A higher physical fitness level and a qualitative approach to training are recognized as protective factors against injury. Subsequent studies should investigate the specific predictors of injuries among referees.
| S-EPMC3599725 | biostudies-literature
Project description:Meeting the global food demand of roughly 10 billion people by the middle of the 21st century will become increasingly challenging as the Earth's climate continues to warm. Earlier studies suggest that once the optimum growing temperature is exceeded, mean crop yields decline and the variability of yield increases even if interannual climate variability remains unchanged. Here, we use global datasets of maize production and climate variability combined with future temperature projections to quantify how yield variability will change in the world's major maize-producing and -exporting countries under 2 °C and 4 °C of global warming. We find that as the global mean temperature increases, absent changes in temperature variability or breeding gains in heat tolerance, the coefficient of variation (CV) of maize yields increases almost everywhere to values much larger than present-day values. This higher CV is due both to an increase in the SD of yields and a decrease in mean yields. For the top four maize-exporting countries, which account for 87% of global maize exports, the probability that they have simultaneous production losses greater than 10% in any given year is presently virtually zero, but it increases to 7% under 2 °C warming and 86% under 4 °C warming. Our results portend rising instability in global grain trade and international grain prices, affecting especially the ∼800 million people living in extreme poverty who are most vulnerable to food price spikes. They also underscore the urgency of investments in breeding for heat tolerance.
| S-EPMC6042138 | biostudies-literature