Beyond <i>xG</i>: A Dual Prediction Model for Analyzing Player Performance Through Expected and Actual Goals in European Soccer Leagues

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 met...

Full description

Saved in:
Bibliographic Details
Main Authors: Davronbek Malikov, Jaeho Kim
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/14/22/10390
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846154440844771328
author Davronbek Malikov
Jaeho Kim
author_facet Davronbek Malikov
Jaeho Kim
author_sort Davronbek Malikov
collection DOAJ
description 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 (<i>xG</i>) 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 <i>xG</i> might not provide a full picture of player performance, as a higher <i>xG</i> 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 (<i>xG</i>) and actual goals (<i>aG</i>). 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 <i>xG</i> and <i>aG</i> performance. Additionally, this paper discusses expected goals and actual goals for each individual game; consequently, we use expected goals per game (<i>xGg</i>) and actual goals per game (<i>aGg</i>) to reflect them. Moreover, we employ regression machine learning models, particularly ridge regression, which demonstrates strong performance in forecasting <i>xGg</i> and <i>aGg</i>, 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 <i>xG</i> and <i>aG</i>, 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.
format Article
id doaj-art-08b7c65d43ca4ad8abf7b2a405bf871a
institution Kabale University
issn 2076-3417
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-08b7c65d43ca4ad8abf7b2a405bf871a2024-11-26T17:48:35ZengMDPI AGApplied Sciences2076-34172024-11-0114221039010.3390/app142210390Beyond <i>xG</i>: A Dual Prediction Model for Analyzing Player Performance Through Expected and Actual Goals in European Soccer LeaguesDavronbek Malikov0Jaeho Kim1Department of AI Convergence Engineering, Gyeongsang National University (GNU), Jinjudaero 501, Jinjusi 52828, Republic of KoreaDepartment of AI Convergence Engineering & Department of Software Engineering, Gyeongsang National University (GNU), Jinjudaero 501, Jinjusi 52828, Republic of KoreaSoccer 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 (<i>xG</i>) 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 <i>xG</i> might not provide a full picture of player performance, as a higher <i>xG</i> 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 (<i>xG</i>) and actual goals (<i>aG</i>). 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 <i>xG</i> and <i>aG</i> performance. Additionally, this paper discusses expected goals and actual goals for each individual game; consequently, we use expected goals per game (<i>xGg</i>) and actual goals per game (<i>aGg</i>) to reflect them. Moreover, we employ regression machine learning models, particularly ridge regression, which demonstrates strong performance in forecasting <i>xGg</i> and <i>aGg</i>, 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 <i>xG</i> and <i>aG</i>, 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.https://www.mdpi.com/2076-3417/14/22/10390machine learningridge regressionsoccer analyticsexpected and actual goalsEuropean soccer leagues
spellingShingle Davronbek Malikov
Jaeho Kim
Beyond <i>xG</i>: A Dual Prediction Model for Analyzing Player Performance Through Expected and Actual Goals in European Soccer Leagues
Applied Sciences
machine learning
ridge regression
soccer analytics
expected and actual goals
European soccer leagues
title Beyond <i>xG</i>: A Dual Prediction Model for Analyzing Player Performance Through Expected and Actual Goals in European Soccer Leagues
title_full Beyond <i>xG</i>: A Dual Prediction Model for Analyzing Player Performance Through Expected and Actual Goals in European Soccer Leagues
title_fullStr Beyond <i>xG</i>: A Dual Prediction Model for Analyzing Player Performance Through Expected and Actual Goals in European Soccer Leagues
title_full_unstemmed Beyond <i>xG</i>: A Dual Prediction Model for Analyzing Player Performance Through Expected and Actual Goals in European Soccer Leagues
title_short Beyond <i>xG</i>: A Dual Prediction Model for Analyzing Player Performance Through Expected and Actual Goals in European Soccer Leagues
title_sort beyond i xg i a dual prediction model for analyzing player performance through expected and actual goals in european soccer leagues
topic machine learning
ridge regression
soccer analytics
expected and actual goals
European soccer leagues
url https://www.mdpi.com/2076-3417/14/22/10390
work_keys_str_mv AT davronbekmalikov beyondixgiadualpredictionmodelforanalyzingplayerperformancethroughexpectedandactualgoalsineuropeansoccerleagues
AT jaehokim beyondixgiadualpredictionmodelforanalyzingplayerperformancethroughexpectedandactualgoalsineuropeansoccerleagues