Using multiple machine learning algorithms to classify elite and sub-elite goalkeepers in professional men’s football

Jamil, Mikael; Phatak, Ashwin; Mehta, Saumya; Beato, Marco; Memmert, Daniel; Connor, Mark

doi:10.1038/s41598-021-01187-5

Cited by 23 publications

(11 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…a viz. modern state of art machine learning [13], [25,26] Ordered Weighted Averaging Aggregation (OWA) Operator [18], Fuzzy Linguistic Quantifier [19], and many more for the talent identification in different sports. Among the various sports, Cricket is a highly attractive game among people.…”

Section: Literature Reviewmentioning

confidence: 99%

SVMCTI: Support Vector Machine-based Cricket Talent Identification Model

Reyaz

Ahamad

Khan

et al. 2023

Preprint

View full text Add to dashboard Cite

Recognizing sports talent is one of the intensively discussed topics in this day and age. Cricket is a sport of keen interest and has fascinated researchers all over the world to ponder and work in this domain. In this era of technological competence, incorporating technology in cricket talent identification is an incumbent task. Also, early-age talent identification is considered to be more beneficial as instead of wasting time and other resources on random performers, we can limit the training and spending on the talented performers that could yield better results. In this article, a machine learning-based approach is proposed for Cricket Talent Identification using SVM (RBF kernel) to classify a dataset of performers into talented performers (possessing cricketing talent) and non-talented performers (not possessing cricketing talent). The dataset has been collected from early-age performers taking into consideration the benefits of talent identification at early ages. The data have been gathered concerning various physical/motor, anthropometric, and cognitive abilities. Using the feature selection technique, the best-contributing parameters were determined and supplied to the model. After performing experimentation, the results were evaluated based on various evaluation metrics like Accuracy, precision, and f1-Score. we achieved an accuracy score of 96.42%, a precision of 0.94, and an f1_score of 0.96. The results obtained have been cross-validated using the 10-cross validation technique.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

SVMCTI: Support Vector Machine-based Cricket Talent Identification Model

Reyaz

Ahamad

Khan

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Another example of the application of machine learning in soccer is in analysing player performance. Jamil et al (Jamil et al, 2021) applied several machine learning algorithms to classify the performance of professional goalkeepers aiming to distinguish an elite goalkeeper from a sub-elite goalkeeper. The algorithms used were Logistic Regression, Gradient Boosting, and Random Forest.…”

Section: Machine Learning In Soccermentioning

confidence: 99%

The Elusive Features of Success in Soccer Passes: A Machine Learning Perspective

Muacho

Ribeiro

Lopes

2022

Proceedings of the 10th International Conference on Sport Sciences Research and Technology Support

View full text Add to dashboard Cite

Machine learning has in recent years been increasingly used in the soccer realm. This paper focuses on investigating the factors influencing pass success, a chief element in team performance. Decision tree techniques are used aiming to identify which features are the most important in pass success. This process is applied to a data set of 13 matches of the French "Ligue 1". Two experiments are conducted using different feature sets: one containing the positional data and Voronoi area off all players, the second considering only the ball carrier and closest teammates and opponents. The results obtained with the first feature set indicate that the relative importance of features is match dependent and somehow related to teams' formation and players' tactical mission. The second feature set, being more directly related to the passing process, provided a more consistent ranking of features. Features related to the interaction with the opponent standout. Low precision and recall values show that the features and factors leading to pass success are in fact elusive.

show abstract

“…Multiple studies have been conducted for analysis of position data, devising player ratings, data visualization and data driven performance analysis but, so far none of them consider the requirement of preprocessing the features while analyzing performance indices 14 – 17 . Using such raw data can lead to evening out of the results and lead to issues such as reliability, validity and precision of findings 6 , 18 .…”

Section: Introductionmentioning

confidence: 99%

Context is key: normalization as a novel approach to sport specific preprocessing of KPI’s for match analysis in soccer

Phatak

Mehta

Wieland

et al. 2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

Key Performance Indicators (KPIs) have been investigated, validated and applied in multitude of sports for recruiting, coaching, opponent, self-analysis etc. Although a wide variety of in game performance indicators have been used as KPIs, they lack sports specific context. With the introduction of artificial intelligence and machine learning (AI/ML) in sports, the need for building intrinsic context into the independent variables is even greater as AI/ML models seem to perform better in terms of predictability but lack interpretability. The study proposes domain specific feature preprocessing method (normalization) that can be utilized across a wide range of sports and demonstrates its value through a specific data transformation by using team possession as a normalizing factor while analyzing defensive performance in soccer. The study performed two linear regressions and three gradient boosting machine models to demonstrate the value of normalization while predicting defensive performance. The results demonstrate that the direction of correlation of the relevant variables changes post normalization while predicting defensive performance of teams for the whole season. Both raw and normalized KPIs showing significant correlation with defensive performance (p < 0.001). The addition of the normalized variables contributes towards higher information gain, improved performance and increased interpretability of the models.

show abstract

Using multiple machine learning algorithms to classify elite and sub-elite goalkeepers in professional men’s football

Cited by 23 publications

References 45 publications

SVMCTI: Support Vector Machine-based Cricket Talent Identification Model

SVMCTI: Support Vector Machine-based Cricket Talent Identification Model

The Elusive Features of Success in Soccer Passes: A Machine Learning Perspective

Context is key: normalization as a novel approach to sport specific preprocessing of KPI’s for match analysis in soccer

Contact Info

Product

Resources

About