Machine Learning Models Reveal Key Performance Metrics of Football Players to Win Matches in Qatar Stars League

Abstract

As football (soccer) is one of the most popular sports worldwide, winning football matches is becoming an essential aspect of football clubs. In this study, we analyzed football players' performance in a total of 864 football matches of the Qatar Stars League (QSL) between the years 2012 and 2019. For each match, the collective performance of the players in key playing positions was analyzed to understand their effectiveness in winning games. We formulated this study as a classification framework in the machine learning (ML) context to distinguish the winning team from the losing team in a match. This allowed us to check the effectiveness of different performance metrics considered a feature vector for ML models. Different ML models were considered for this classification task, and the logistic regression-based model was considered the best performing model, with more than 80% accuracy. Multiple feature selection methods were leveraged to identify players' performance metrics that could be considered as contributing factors to determine the match result. The proposed ML model identified several features, including (a) shots on target by forwarders (b) distance covered by forwarders and midfielders at very high speed (c) successful passes, that can be considered as effective performance metrics for winning a football match in QSL. Interestingly, we revealed that the defenders' role could not be ignored for match results, and playing fair games improves the chance of winning matches in QSL. We also showed that players' performance metrics from the last five seasons would provide sufficient discriminative power to the proposed ML model to predict the match-winner in the upcoming season. The proposed ML model will support the players, coaching staff, and team management to focus on specific performance metrics that may lead to winning a match in QSL.

Football Match Line-Up Prediction Based on Physiological Variables: A Machine Learning Approach

“…As presented in this study, distance covered at max speed (distance.>7) by F was one of the variables that had a bigger impact on winning. As suggested in [23,24], teams with F's that covered more distance at a very high speed were closer to winning the match when comparing two opposing teams. For the Central Midfielders (CM) position, one of the variables selected was the distance covered per minutes as suggested in [22,25], and which refer that CM, during the matches, has the highest value in total distance covered.…”

A Framework for Optimizing Ensemble Learning for Offensive Tweet Identification

“…The lower the values of FP and FN, the better the model and vice versa. The values TN, FN, FP, and TP can be computed in terms of precision, recall, F1-score, and MCC as shown in Equation ( 1) -( 4), respectively [4,10]:…”

SoccerNet: A Gated Recurrent Unit-based model to predict soccer match winners

“…Match outcome prediction based on data-driven fashion is one of the key areas of interest for every football team. Many computational methods such as statistical analysis [3], neural network-based approaches [4] and contemporary machine learning (ML) [5,6] based approaches have already been proposed in the literature for predicting match winners from different football leagues. But there existed no literature focusing on Qatar Stars League (QSL), the only professional football league in Qatar, for match result prediction based on ML techniques.…”

“…But there existed no literature focusing on Qatar Stars League (QSL), the only professional football league in Qatar, for match result prediction based on ML techniques. We were the first to propose the first ML model for match outcome prediction for QSL [ 5 ]. As part of this initiative, we focused on the improvement of the model.…”