Search Results (15)

Soccer’s global popularity as the world’s favorite sport is driven by many factors, with high player salaries being one of the key reasons behind its appeal. These salaries not only reflect on-field performance, but also capture a broader evaluation of player value. Despite the increasing use of performance data in sports analytics, a critical gap remains in establishing fair compensation models that comprehensively account for both quantifiable and intangible contributions. To address these challenges, this study adopts machine learning (ML) techniques that model player salaries based on a combination of performance metrics and contextual features. This research focuses on reducing bias and improving transparency in salary decisions through a systematic, data-driven approach. Utilizing a dataset spanning the 2016–2022 seasons, we apply both traditional and automated ML frameworks to uncover the most influential factors in salary determination. The results indicate a nearly 17% improvement in R² and about a 30% reduction in MAE after incorporating the newly constructed features and methods, demonstrating a significant enhancement in model performance. Gradient Boosting demonstrates superior effectiveness, revealing a group of significantly underestimated and overestimated players, and showcasing the model’s proficiency in detecting valuation discrepancies. Full article

This study explores market value depreciation among soccer players across the top five European leagues, addressing a critical gap in the sports finance literature by focusing on post-prime valuation dynamics. Leveraging a dataset from the 2023/2024 season, player market values and attributes sourced from Transfermarkt and Sportmonks were analyzed using league-specific multilinear regression models. The findings reveal a consistent decline in market values beginning at age 27, with notable variation across leagues. The German Bundesliga demonstrates the steepest depreciation rates, suggesting shorter career peaks or distinct market dynamics. In contrast, the Italian Serie A and Spanish La Liga exhibit the slowest depreciation rates, preserving player value for older athletes longer than other leagues. The English Premier League and French Ligue 1 show moderate depreciation, with the Premier League’s decline closely aligning with Ligue 1 and diverging less from other leagues than traditionally assumed. These results challenge preconceived narratives about league-specific player valuations and offer empirical insights into the transfer market. By providing a nuanced understanding of depreciation trends, this study can inform strategic decisions for agents, managers, and clubs, particularly in optimizing contract negotiations, transfer strategies, and long-term asset management in professional football. Full article

Soccer is evolving into a science rather than just a sport, driven by intense competition between professional teams. This transformation requires efforts beyond physical training, including strategic planning, data analysis, and advanced metrics. Coaches and teams increasingly use sophisticated methods and data-driven insights to enhance decision-making. Analyzing team performance is crucial to prepare players and coaches, enabling targeted training and strategic adjustments. Expected goals (xG) analysis plays a key role in assessing team and individual player performance, providing nuanced insights into on-field actions and opportunities. This approach allows coaches to optimize tactics and lineup choices beyond traditional scorelines. However, relying solely on xG might not provide a full picture of player performance, as a higher xG does not always translate into more goals due to the intricacies and variabilities of in-game situations. This paper seeks to refine performance assessments by incorporating predictions for both expected goals (xG) and actual goals (aG). Using this new model, we consider a wider variety of factors to provide a more comprehensive evaluation of players and teams. Another major focus of our study is to present a method for selecting and categorizing players based on their predicted xG and aG performance. Additionally, this paper discusses expected goals and actual goals for each individual game; consequently, we use expected goals per game (xGg) and actual goals per game (aGg) to reflect them. Moreover, we employ regression machine learning models, particularly ridge regression, which demonstrates strong performance in forecasting xGg and aGg, outperforming other models in our comparative assessment. Ridge regression’s ability to handle overlapping and correlated variables makes it an ideal choice for our analysis. This approach improves prediction accuracy and provides actionable insights for coaches and analysts to optimize team performance. By using constructed features from various methods in the dataset, we improve our model’s performance by as much as 12%. These features offer a more detailed understanding of player performance in specific leagues and roles, improving the model’s accuracy from 83% to nearly 95%, as indicated by the R-squared metric. Furthermore, our research introduces a player selection methodology based on their predicted xG and aG, as determined by our proposed model. According to our model’s classification, we categorize top players into two groups: efficient scorers and consistent performers. These precise forecasts can guide strategic decisions, player selection, and training approaches, ultimately enhancing team performance and success. Full article

Momentum has been a consistently studied aspect of sports science for decades. Among the established literature, there has, at times, been a discrepancy between conclusions. However, if momentum is indeed an actual phenomenon, it would affect all aspects of sports, from player evaluation to pre-game prediction and betting. Therefore, using momentum-based features that quantify a team’s linear trend of play, we develop a data pipeline that uses a small sample of recent games to assess teams’ quality of play and measure the predictive power of momentum-based features versus the predictive power of more traditional frequency-based features across several leagues using several machine learning techniques. More precisely, we use our pipeline to determine the differences in the predictive power of momentum-based features and standard statistical features for the National Hockey League (NHL), National Basketball Association (NBA), and five major first-division European football leagues. Our findings show little evidence that momentum has superior predictive power in the NBA. Still, we found some instances of the effects of momentum on the NHL that produced better pre-game predictors, whereas we view a similar trend in European football/soccer. Our results indicate that momentum-based features combined with frequency-based features could improve pre-game prediction models and that, in the future, momentum should be studied more from a feature/performance indicator point-of-view and less from the view of the dependence of sequential outcomes, thus attempting to distance momentum from the binary view of winning and losing. Full article

Football (also known as Soccer), boasts a staggering fan base of 3.5 billion individuals spread across 200 countries, making it the world’s most beloved sport. The widespread adoption of advanced technology in sports has become increasingly prominent, empowering players, coaches, and team management to enhance their performance and refine team strategies. Among these advancements, player substitution plays a crucial role in altering the dynamics of a match. However, due to the absence of proven methods or software capable of accurately predicting substitutions, these decisions are often based on instinct rather than concrete data. The purpose of this research is to explore the potential of employing machine learning algorithms to predict substitutions in Football, and how it could influence the outcome of a match. This study investigates the effect of timely and tactical substitutions in football matches and their influence on the match results. Machine learning techniques such as Logistic Regression (LR), Decision tree (DT), K-nearest Neighbor (KNN), Support Vector Machine (SVM), Multinomial Naïve Bayes (MNB), Random Forest (RF) classifiers were implemented and tested to develop models and to predict player substitutions. Relevant data was collected from the Kaggle dataset, which contains data of 51,738 substitutions from 9074 European league football matches in 5 leagues spanning 6 seasons. Machine learning models were trained and tested using an 80-20 data split and it was observed that RF model provided the best accuracy of over 70% and the best F1-score of 0.65 on the test set across all football leagues. SVM model achieved the best Precision of almost 0.8. However, the worst computation time of up to 2 min was consumed. LR showed some overfitting issues with 100% accuracy in the training set, but only 60% accuracy was obtained for the test set. To conclude, based on the time of substitution and match score-line, it was possible to predict the players who can be substituted, which can provide a match advantage. The achieved results provided an effective way to decide on player substitutions for both the team manager and coaches. Full article

It has yet to be determined whether or not differences in body composition are present between international and non-international players playing in the same elite professional club competition. Similarly, it is not yet clear whether or not differences in body composition exist according to ethnic origin where relative homogeneity is to be expected among soccer players. There is no single anthropometric profile that guarantees sporting success, as success differs according to characteristics. The aim of this study was to assess the description, comparison, and correlation of the body composition profile of Latin American professional football players playing in European leagues. The sample was composed of 238 Latin American male football players from European professional football leagues of Spain, Italy and England during the competition period. Differences were found in all measures. The present study shows that Latin American professional football players playing in Europe have significant differences in various body composition variables such as weight, height, WC, skinfold and fat values. This means that training, revalidation after injury and the classifications of sporting performance carried out in European football clubs should take into account the anthropometric difference between Latin American and European players. Full article

Ranking sports teams generally relies on supervised techniques, requiring either prior knowledge or arbitrary metrics. In this paper, we offer a purely unsupervised technique. We apply this to operational decision-making, specifically, the controversial European Super League for association football, demonstrating how this approach can select dominant teams to form the new league. We first use random forest regression to select important variables predicting goal difference, which we use to calculate the Euclidian distances between teams. Creating a Laplacian eigenmap, we bisect the Fiedler vector to identify the natural clusters in five major European football leagues. Our results show how an unsupervised approach could identify four clusters based on five basic performance metrics: shots, shots on target, shots conceded, possession, and pass success. The top two clusters identify teams that dominate their respective leagues and are the best candidates to create the most competitive elite super league. Full article

To evaluate the extent and characteristics of COVID-19 cases in relation to environmental COVID-19 incidences in the four best European soccer leagues (Bundesliga, Premier League, Serie A and La Liga) from the first of January 2020 until the end of January 2022. Methods: A retrospective evaluation of all publicly available COVID-19 cases in the studied cohorts was performed. The 14-day case incidences from epidemiological national data were used as reference values. The leagues studied are the Bundesliga (Germany), Premier League (Great Britain), Serie A (Italy) and La Liga (Spain). For all cases, the duration of time loss and date of case notification were recorded. Results: League-specific mean time loss due to disease or quarantine per COVID-19 case differs significantly between La Liga (11.45; ±5.21 days) and the other leagues studied (Bundesliga 20.41; ±33.87; p 0.0242; Premier League 17.12; ±10.39; p 0.0001; Serie A 17.61; ±12.71; p < 0.0001). A positive correlation between 14-day national incidence with COVID-19 disease occurrence in soccer leagues was found for all leagues studied. The correlations were strong in the Bundesliga (r 0.5911; CI 0.4249–0.7187; p < 0.0001), Serie A (r 0.5979; CI 0.4336–0.7238; p < 0.0001) and La Liga (r 0.5251; CI 0.3432–0.6690; p < 0.0001). A moderate correlation was found for the Premier League (r 0.3308; CI 0.1147–0.5169; p 0.0026). Odds ratios for altered environmental case risk in the cohorts studied could be calculated for four different national COVID-19 incidence levels (<50/100.000 to >500/100.000). A trend towards shorter COVID-19 case duration in the second half of 2021 was shown for all leagues studied. Conclusions: There was a significantly lower mean time-loss caused by a COVID-19 infection for cases occurred in La Liga compared with the other three leagues studied. For all four leagues studied, a positive, significant correlation of national environmental COVID-19 incidence level and the incidence of COVID-19 cases in the cohort of a football league was found. Full article

Billions of euros are invested every year by professional football clubs for the recruitment of players. How do market actors decide prices? This paper presents an econometric model unveiling the key factors coming into play in determining fees on the transfer market for professional football (soccer) players. The statistical technique used to build the model is multiple linear regression (MLR), with fees paid by clubs as an independent variable. The sample comprises over 2000 transactions of players transferred for money from clubs in the five major European leagues during the period stretching from July 2012 to November 2021. This paper notably highlights the importance of taking into consideration the remaining duration of contracts binding players with the club to which they belong, a factor often neglected in the existing literature. It also shows that a statistical model can explain over 80% of the differences in the transfer fees paid for players. This paper reveals various applications of the approach developed for the football industry to both assess and predict football players’ transfer fees and values: transfer negotiations, club sales or purchases, bank credit, fund raising, financial planning and communication, legal disputes, etc. Full article

The growth of professional soccer in the United States is evident through the rapid expansion of franchises and increased game attendance within Major League Soccer (MLS) and the United Soccer League (USL). Coinciding with this growth is the emergence of European-style supporters’ groups filling sections of MLS and USL stadiums. In this study, the authors utilized an egocentric network analysis to explore relationships among supporters’ group members for two professional soccer clubs based in the United States. Egocentric network research focuses on the immediate social environment of individuals and is often viewed as an alternative approach to sociocentric (i.e., whole network) analyses. This study employed hierarchical linear modeling as an example of multilevel modeling with egocentric data, using ego- and alter-level variables to explain the strength of co-attendance ties. The results indicate the perceived commitment of fellow fans to the team, shared membership in a supporters’ group, age, and interactions with other fans in team settings related to higher levels of co-attendance. The outcomes of this study are both theoretical, as they advance an understanding of sport consumer behavior within soccer supporters’ groups, and methodological, as they illustrate the unique value of employing egocentric network analysis in sport fan research. Full article

The relative age effect (RAE) consists of the lower presence of members of an age group born in the months furthest from the age cut-off date established. In youth soccer, it is known that because of this effect the birth dates of more players in a team are closer to the cutoff of 1 January. These older players, due to their physical and psychological advantages, are more likely to be identified as talent. This study aimed to examine whether RAE can be identified in professional players of the top five European soccer leagues (Spain, Italy, England, Germany, and France) and to assess its influence on the perceived market value of the players. Market value data for 2577 players were obtained from the Transfermarkt database. A significant RAE was produced in all leagues (p < 0.05). However, this bias did not affect the market value of the professional elite soccer players examined here. Our observations indicate that, while the identification and promotion of talent at young ages are often biased by RAE, once players have reached the professional stage, the market value assigned to them is based more on factors other than their date of birth. Full article

This paper addresses the dynamics of four European soccer teams over the season 2018–2019. The modeling perspective adopts the concepts of fractional calculus and power law. The proposed model embeds implicitly details such as the behavior of players and coaches, strategical and tactical maneuvers during the matches, errors of referees and a multitude of other effects. The scale of observation focuses the teams’ behavior at each round. Two approaches are considered, namely the evaluation of the team progress along the league by a variety of heuristic models fitting real-world data, and the analysis of statistical information by means of entropy. The best models are also adopted for predicting the future results and their performance compared with the real outcome. The computational and mathematical modeling lead to results that are analyzed and interpreted in the light of fractional dynamics. The emergence of patterns both with the heuristic modeling and the entropy analysis highlight similarities in different national leagues and point towards some underlying complex dynamics. Full article

In recent times, football (soccer) has aroused an increasing amount of attention across continents and entered unexpected dimensions. In this course, the number of bookmakers, who offer the opportunity to bet on the outcome of football games, expanded enormously, which was further strengthened by the development of the world wide web. In this context, one could generate positive returns over time by betting based on a strategy which successfully identifies overvalued betting odds. Due to the large number of matches around the globe, football matches in particular have great potential for such a betting strategy. This paper utilizes machine learning to forecast the outcome of football games based on match and player attributes. A simulation study which includes all matches of the five greatest European football leagues and the corresponding second leagues between 2006 and 2018 revealed that an ensemble strategy achieves statistically and economically significant returns of 1.58% per match. Furthermore, the combination of different machine learning algorithms could neither be outperformed by the individual machine learning approaches nor by a linear regression model or naive betting strategies, such as always betting on the victory of the home team. Full article

Despite the globalisation of European soccer, each professional league exhibits specificities. French Ligue 1 sometimes contends with the trading-off of financial performance against sporting performance of its teams in European soccer competitions, and its inner auditing body, the Direction Nationale du Contrôle de Gestion (DNCG), is in charge of controlling clubs’ financial accounts. Moreover, Ligue 1 operates with one of the best competitive balances in the Big Five, which is detrimental to its clubs’ success at the European level. However, the league and a number of clubs have not been able to curb payroll inflation and have not avoided being recurrently run in a deficit and accumulating debts, in particular payment arrears and player transfer overdue. Lax management occurs, since very few clubs have been sanctioned by a payment failure, even fewer by liquidation, and there has been no bankruptcy. The concept of a soft budget constraint theoretically encapsulates such empirical evidence. The novelty of the paper is to establish a link between the soft budget constraint and the players’ labour market where it crucially triggers market disequilibria: an excess of demand for superstars’ talents and an excess of supply for journeymen players are modelled. Data paucity about player individual wages hinders econometric testing of the aforementioned link and the model. However, a look at transfer fees that concentrates on a few of the top European soccer clubs provides a first insight into the arms race for talent that fuels an excess of demand for superstars and dips a number of clubs’ finance into the red. Full article

The aim of this article is to investigate the explanatory variables of the number of Facebook fans and Twitter followers for professional sports clubs based on the financial value literature. Such explanatory variables are related to local market conditions and on-field and off-field performance. Based upon a sample of North American major league clubs and the most valuable European soccer clubs as evaluated by Forbes over the 2011–2013 period (423 observations), our results indicate a range of variables with a significant positive impact on the number of social media fans: population, no competing team in the market, current sports performance, historical sports performance, facility age, attendance, operating income, expenses/league mean, and being an English football club. An improved understanding of the effectiveness of clubs’ social media presence is important for contemporary sport managers in terms of enhancing supporter communication, involvement, and accountability, as well as maximizing clubs’ revenue generation possibilities. Our findings could help sport managers to realize their clubs’ social media potential in pursuit of these objectives, specifically to understand which variables are under-exploited and why some clubs over-perform, which will allow managers to prioritize decisions to increase their number of social media fans and financial value. Full article