Explainable expected goal models for performance analysis in football analytics

被引:3
|
作者
Cavus, Mustafa [1 ,2 ]
Biecek, Przemyslaw [1 ]
机构
[1] Warsaw Univ Technol, Fac Math & Informat Sci, Warsaw, Poland
[2] Eskisehir Tech Univ, Dept Stat, Eskisehir, Turkey
关键词
football; expected goal; machine learning; explainable artificial intelligence; aggregated profiles;
D O I
10.1109/DSAA54385.2022.10032440
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The expected goal provides a more representative measure of the team and player performance which also suit the low-scoring nature of football instead of score in modern football. The score of a match involves randomness and often may not represent the performance of the teams and players, therefore it has been popular to use the alternative statistics in recent years such as shots on target, ball possessions, and drills. To measure the probability of a shot being a goal by the expected goal, several features are used to train an expected goal model which is based on the event and tracking football data. The selection of these features, the size and date of the data, and the model which are used as the parameters that may affect the performance of the model. Using black-box machine learning models for increasing the predictive performance of the model decreases its interpretability that causes the loss of information that can be gathered from the model. This paper proposes an accurate expected goal model trained consisting of 315,430 shots from seven seasons between 2014-15 and 2020-21 of the top-five European football leagues. Moreover, this model is explained by using explainable artificial intelligence tool to obtain an explainable expected goal model for evaluating a team or player performance. To the best of our knowledge, this is the first paper that demonstrates a practical application of an explainable artificial intelligence tool aggregated profiles to explain a group of observations on an accurate expected goal model for monitoring the team and player performance. Moreover, these methods can be generalized to other sports branches.
引用
收藏
页码:947 / 955
页数:9
相关论文
共 50 条
  • [21] Visual variability analysis for goal models
    González-Baixauli, B
    Leite, JCSD
    Mylopoulos, J
    12TH IEEE INTERNATIONAL REQUIREMENTS ENGINEERING CONFERENCE, PROCEEDINGS, 2004, : 198 - 207
  • [22] Predicting goal probabilities with improved xG models using event sequences in association football
    Bandara, Ishara
    Shelyag, Sergiy
    Rajasegarar, Sutharshan
    Dwyer, Dan
    Kim, Eun-jin
    Angelova, Maia
    PLOS ONE, 2024, 19 (10):
  • [23] Sensitivity Analysis of Aircraft Design Service Goal to Expected Operation Route
    Li, Zhongjian
    Yu, Mengze
    2019 INTERNATIONAL CONFERENCE ON ADVANCED ELECTRONIC MATERIALS, COMPUTERS AND MATERIALS ENGINEERING (AEMCME 2019), 2019, 563
  • [25] Analysis of Explainable Goal-Driven Reinforcement Learning in a Continuous Simulated Environment
    Portugal, Ernesto
    Cruz, Francisco
    Ayala, Angel
    Fernandes, Bruno
    ALGORITHMS, 2022, 15 (03)
  • [26] Performance assessment in football.: What do we mean by performance analysis in football?
    Açikada, C
    PROCEEDINGS OF THE 4TH EUROPEAN SPORTS MEDICINE CONGRESS EFSMA, 2005, : 3 - 4
  • [27] THE INFLUENCE OF COMPONENT PARTICIPATION AND ROLE MODELS ON GOAL ACCEPTANCE, GOAL SATISFACTION, AND PERFORMANCE
    EARLEY, PC
    KANFER, R
    ORGANIZATIONAL BEHAVIOR AND HUMAN DECISION PROCESSES, 1985, 36 (03) : 378 - 390
  • [28] A Markovian score model for evaluating provider performance for continuity of care-An explainable analytics approach
    Topuz, Kazim
    Urban, Timothy L.
    Yildirim, Mehmet B.
    EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2024, 317 (02) : 341 - 351
  • [29] Explainable Deep Learning Models in Medical Image Analysis
    Singh, Amitojdeep
    Sengupta, Sourya
    Lakshminarayanan, Vasudevan
    JOURNAL OF IMAGING, 2020, 6 (06)
  • [30] Predicting Football Team Performance with Explainable AI: Leveraging SHAP to Identify Key Team-Level Performance Metrics
    Moustakidis, Serafeim
    Plakias, Spyridon
    Kokkotis, Christos
    Tsatalas, Themistoklis
    Tsaopoulos, Dimitrios
    FUTURE INTERNET, 2023, 15 (05):