journal article·2024-09-18Open access

Identifying Key Factors for Securing a Champions League Position in French Ligue 1 Using Explainable Machine Learning Techniques

Spyridon Plakias, Christos Kokkotis, Michalis Mitrotasios, Vasileios Armatas, Themistoklis Tsatalas, Giannis Giakas

Applied Sciences· Volume 14· Issue 18

Abstract

Introduction: Performance analysis is essential for coaches and a topic of extensive research. The advancement of technology and Artificial Intelligence (AI) techniques has revolutionized sports analytics. Aim: The primary aim of this article is to present a robust, explainable machine learning (ML) model that identifies the key factors that contribute to securing one of the top three positions in the standings of the French Ligue 1, ensuring participation in the UEFA Champions League for the following season. Materials and Methods: This retrospective observational study analyzed data from all 380 matches of the 2022–23 French Ligue 1 season. The data were obtained from the publicly-accessed website “whoscored” and included 34 performance indicators. This study employed Sequential Forward Feature Selection (SFFS) and various ML algorithms, including XGBoost, Support Vector Machine (SVM), and Logistic Regression (LR), to create a robust, explainable model. The SHAP (SHapley Additive Explanations) model was used to enhance model interpretability. Results: The K-means Cluster Analysis categorized teams into groups (TOP TEAMS, 3 teams/REST TEAMS, 17 teams), and the ML models provided significant insights into the factors influencing league standings. The LR classifier was the best-performing classifier, achieving an accuracy of 75.13%, a recall of 76.32%, an F1-score of 48.03%, and a precision of 35.17%. “SHORT PASSES” and “THROUGH BALLS” were features found to positively influence the model’s predictions, while “TACKLES ATTEMPTED” and “LONG BALLS” had a negative impact. Conclusions: Our model provided satisfactory predictive accuracy and clear interpretability of results, which gave useful information to stakeholders. Specifically, our model suggests adopting a strategy during the ball possession phase that relies on short passes (avoiding long ones) and aiming to enter the attacking third and the opponent’s penalty area with through balls.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Sports Analytics and Performance · Sports Performance and Training

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Department of Physical Education and Sport Science, University of Thessaly, 42150 Trikala, Greece

Department of Physical Education and Sport Science, Democritus University of Thrace, 69100 Komotini, Greece

School of Physical Education and Sport Science, National and Kapodistrian University of Athens, 10679 Athens, Greece

References (60)

Show source-provided references
1. Plakias, S., Moustakidis, S., Kokkotis, C., Papalexi, M., Tsatalas, T., Giakas, G., and Tsaopoulos, D. (2023). Identifying Soccer Players’ Playing Styles: A Systematic Review. J. Funct. Morphol. Kinesiol., 8.10.3390/jfmk8030104 ↗
2. Plakias, S., Moustakidis, S., Kokkotis, C., Tsatalas, T., Papalexi, M., Plakias, D., Giakas, G., and Tsaopoulos, D. (2023). Identifying soccer teams’ styles of play: A scoping and critical review. J. Funct. Morphol. Kinesiol., 8.10.3390/jfmk8020039 ↗
3. Developing a framework for professional practice in applied performance analysis10.1080/24748668.2021.1951490 ↗
4. Match analysis, big data and tactics: Current trends in elite soccer10.5960/dzsm.2018.322 ↗
5. Big data and tactical analysis in elite soccer: Future challenges and opportunities for sports science10.1186/s40064-016-3108-2 ↗
6. A new method proposed for realizing human gait pattern recognition: Inspirations for the application of sports and clinical gait analysis10.1016/j.gaitpost.2023.10.019 ↗
7. Xu, D., Zhou, H., Quan, W., Gusztav, F., Wang, M., Baker, J.S., and Gu, Y. (2023). Accurately and effectively predict the ACL force: Utilizing biomechanical landing pattern before and after-fatigue. Comput. Methods Programs Biomed., 241.10.1016/j.cmpb.2023.107761 ↗
8. UEFA champions league revenues, performance and participation 2003–2004 to 2016–201710.1080/23750472.2018.1513341 ↗
9. Dancing with the stars: Does playing in elite tournaments affect performance?10.1111/obes.12520 ↗
10. Do financial markets price UEFA Champions League competition events?10.1108/EMJB-09-2021-0134 ↗
11. How to be successful in football: A systematic review10.2174/1875399X01811010003 ↗
12. Offense and defense statistical indicators that determine the Greek Superleague teams placement on the Table 2011-12
13. Fernández-Cortés, J., García-Ceberino, J.M., García-Rubio, J., and Ibáñez, S.J. (2023). Influence of game indicators on the ranking of teams in the Spanish soccer league. Appl. Sci., 13.10.3390/app13148097 ↗
14. Key team physical and technical performance indicators indicative of team quality in the soccer Chinese super league10.1080/15438627.2018.1431539 ↗
15. Physical Performance Indicators and Team Success in the German Soccer League10.2478/hukin-2022-0099 ↗
16. Andrzejewski, M., Oliva-Lozano, J.M., Chmura, P., Chmura, J., Czarniecki, S., Kowalczuk, E., Rokita, A., Muyor, J.M., and Konefał, M. (2022). Analysis of team success based on match technical and running performance in a professional soccer league. BMC Sports Sci. Med. Rehabil., 14.10.1186/s13102-022-00473-7 ↗
17. Longo, U.G., Sofi, F., Candela, V., Risi Ambrogioni, L., Pagliai, G., Massaroni, C., Schena, E., Cimmino, M., D’Ancona, F., and Denaro, V. (2021). The influence of athletic performance on the highest positions of the final ranking during 2017/2018 Serie A season. BMC Sports Sci. Med. Rehabil., 13.10.1186/s13102-021-00259-3 ↗
18. Coso, J.D., Brito, D.d.S., Moreno-Perez, V., Buldú, J.M., Nevado, F., Resta, R., and López-Del Campo, R. (2020). Influence of players’ maximum running speed on the team’s ranking position at the end of the Spanish LaLiga. Int. J. Environ. Res. Public Health, 17.10.3390/ijerph17238815 ↗
19. Quantifying the relation between performance and success in soccer10.1142/S021952591750014X ↗
20. Match running performance and success across a season in German Bundesliga soccer teams10.1055/s-0034-1398578 ↗
21. González-Rodenas, J., Ferrandis, J., Moreno-Pérez, V., López-Del Campo, R., Resta, R., and Del Coso, J. (2023). Differences in playing style and technical performance according to the team ranking in the Spanish football LaLiga. A thirteen seasons study. PLoS ONE, 18.10.1371/journal.pone.0293095 ↗
22. Association between offensive and defensive playing style variables and ranking position in a national football league10.1080/02640414.2021.1976488 ↗
23. Machine learning application in soccer: A systematic review10.5114/biolsport.2023.112970 ↗
24. A review of machine learning applications in soccer with an emphasis on injury risk10.5114/biolsport.2023.114283 ↗
25. Rossi, A., Pappalardo, L., and Cintia, P. (2021). A narrative review for a machine learning application in sports: An example based on injury forecasting in soccer. Sports, 10.10.3390/sports10010005 ↗
26. Xu, D., Quan, W., Zhou, H., Sun, D., Baker, J.S., and Gu, Y. (2022). Explaining the differences of gait patterns between high and low-mileage runners with machine learning. Sci. Rep., 12.10.1038/s41598-022-07054-1 ↗
27. Factors associated with match outcomes in elite European football–insights from machine learning models10.3233/JSA-240745 ↗
28. Moustakidis, S., Plakias, S., Kokkotis, C., Tsatalas, T., and Tsaopoulos, D. (2023). Predicting Football Team Performance with Explainable AI: Leveraging SHAP to Identify Key Team-Level Performance Metrics. Future Internet, 15.10.3390/fi15050174 ↗
29. Geurkink, Y., Boone, J., Verstockt, S., and Bourgois, J.G. (2021). Machine learning-based identification of the strongest predictive variables of winning and losing in Belgian professional soccer. Appl. Sci., 11.10.3390/app11052378 ↗
30. Predicting injury risk using machine learning in male youth soccer players10.1016/j.chaos.2022.113079 ↗
31. A multi-season machine learning approach to examine the training load and injury relationship in professional soccer10.3233/JSA-240718 ↗
32. Machine learning for understanding and predicting injuries in soccer10.1186/s40798-022-00465-4 ↗
33. Forcher, L., Beckmann, T., Wohak, O., Romeike, C., Graf, F., and Altmann, S. Prediction of defensive success in elite soccer using machine learning-Tactical analysis of defensive play using tracking data and explainable AI, Sci. Med. Footb., in press.
34. Stival, L., Pinto, A., Andrade, F.d.S.P.d., Santiago, P.R.P., Biermann, H., Torres, R.d.S., and Dias, U. (2023). Using machine learning pipeline to predict entry into the attack zone in football. PLoS ONE, 18.10.1371/journal.pone.0265372 ↗
35. Tümer, A.E., Akyıldız, Z., Güler, A.H., Saka, E.K., Ievoli, R., Palazzo, L., and Clemente, F.M. (Proc. Inst. Mech. Eng. Part P J. Sports Eng. Technol., 2022). Prediction of soccer clubs’ league rankings by machine learning methods: The case of Turkish Super League, Proc. Inst. Mech. Eng. Part P J. Sports Eng. Technol., in press.10.1177/17543371221140492 ↗
36. Li, C., and Zhao, Y. (2021). Comparison of goal scoring patterns in “The Big Five” European football leagues. Front. Psychol., 11.10.3389/fpsyg.2020.619304 ↗
37. (2023, July 20). Whoscored. Statistics. Available online: https://www.whoscored.com/Statistics.
38. Inter-operator reliability of live football match statistics from OPTA Sportsdata10.1080/24748668.2013.11868690 ↗
39. Match performance difference between African and Top Five teams in the group stage of the 2022 World Cup
40. Yi, Q., Groom, R., Dai, C., Liu, H., and Gómez Ruano, M.Á. (2019). Differences in technical performance of players from ‘the big five’European football leagues in the UEFA Champions League. Front. Psychol., 10.10.3389/fpsyg.2019.02738 ↗
41. (2024, July 30). Whoscored. Glossary. Available online: https://www.whoscored.com/Glossary?fbclid=IwY2xjawEhuvZleHRuA2FlbQIxMAABHY0BGSX-n2SvqNFQAXM8fe1YrepDyQLyggXI6N5Gcwuyitw-OMQlRP45DQ_aem_RkdOv8VmWvsHjpUArenZLg.
42. (2024, July 30). Opta. Opta Event Definitions. Available online: https://www.statsperform.com/opta-event-definitions/?fbclid=IwY2xjawEhuvpleHRuA2FlbQIxMAABHTT4_KxCgegjiu1-EetYNDfx94A--zoxUjiH8k5GoGGOj4JOddAI0ywFQg_aem_ULv1_JcQQUkT30bFLaoOlA.
43. Analysis of the effectiveness of long distance passes in 2014 Brazil FIFA World Cup10.5007/1980-0037.2017v19n6p676 ↗
44. Exploring the impact of possession-based performance indicators on goal scoring in elite football leagues
45. Towards maximizing expected possession outcome in soccer10.1177/17479541231154494 ↗
46. Successful short passing frequency of defenders differentiates between top and bottom four English Premier League teams10.1080/24748668.2013.11868678 ↗
47. The correlation of the penetrative pass on offensive third with the possession of the ball in high level soccer
48. Creation of goal scoring opportunities by means of different types of offensive actions in US major league soccer10.5114/hm.2017.73616 ↗
49. Elite-level defensive performance in football: A systematic review10.1007/s12662-023-00900-y ↗
50. Hassan, A., Akl, A.-R., Hassan, I., and Sunderland, C. (2020). Predicting wins, losses and attributes’ sensitivities in the soccer world cup 2018 using neural network analysis. Sensors, 20.10.3390/s20113213 ↗
51. Data-driven team ranking and match performance analysis in Chinese Football Super League10.1016/j.chaos.2020.110330 ↗
52. The use of match statistics that discriminate between successful and unsuccessful soccer teams10.2478/v10078-012-0015-7 ↗
53. Performance in team sports: Identifying the keys to success in soccer10.2478/v10078-010-0035-0 ↗
54. Engler, F., Hohmann, A., and Siener, M. (2023). Validation of a New Soccer Shooting Test Based on Speed Radar Measurement and Shooting Accuracy. Children, 10.10.3390/children10020199 ↗
55. Statistical analysis for the soccer matches of the first Bundesliga10.1260/1747-9541.9.3.553 ↗
56. Swathi, Y., and Challa, M. (2023, January 19–20). A Comparative Analysis of Explainable AI Techniques for Enhanced Model Interpretability. Proceedings of the 2023 3rd International Conference on Pervasive Computing and Social Networking (ICPCSN), Salem, India.
57. Explainability as a Method for Learning From Computers10.1109/ACCESS.2023.3265582 ↗
58. Plakias, S., Tsatalas, T., Armatas, V., Tsaopoulos, D., and Giakas, G. (2024). Tactical Situations and Playing Styles as Key Performance Indicators in Soccer. J. Funct. Morphol. Kinesiol., 9.10.3390/jfmk9020088 ↗
59. From a static to a dynamic perspective in handball match analysis: A systematic review10.2174/1875399X01508010025 ↗
60. Goal scoring in elite male football: A systematic review10.14198/jhse.2018.131.19 ↗