The purpose of this study is to develop an optimized prediction model for Champions League qualification using machine learning and SHAP methods. The research data comprises 14 match statistics from 300 teams over 15 seasons, from the 2009–2010 season to the 2023–2024 season of the English Premier League. The prediction models were evaluated by combining four algorithms with six data balancing techniques, resulting in the evaluation of 24 models. Additionally, the hyperparameters of the top-performing models were tuned to evaluate the optimized models’ performance. Finally, SHAP methodology was applied to assess the importance of variables in the optimized models. The results of this study are as follows. First, the performance of the SMOTE XGBoost model was the highest, followed by the SMOTE-Tomek Gradient Boosting Trees model. Second, the most important variable in the SMOTE XGBoost model was the Shots OT pg, followed by Six Yard Box. These results can contribute not only to predicting team performance in advance but also to improving operational efficiency and can serve as foundational data for teams aiming for long-term success.
AlavyKGaskellALeachS, et al. On the edge of your seat: demand for football on television and the uncertainty of outcome hypothesis. Int J Sport Finance2010; 5(2): 75.
2.
JangNK. Outcome uncertainty as psychological distance in decision making: a construal-level perspective. Korean J Sport Manag2023; 28(5): 20–37.
3.
ChoiHJ. Comparison of machine learning methods for a prediction of match outcomes in soccer. Korean J Meas Eval Phys Educ Sport Sci2022; 24(4): 81–91.
4.
AlonsoRPBabacMB. Machine learning approach to predicting a basketball game outcome. Int J Data Sci2022; 7(1): 60–77.
5.
OwramipurFEskandarianPMoznebFS. Football result prediction with Bayesian network in Spanish League-Barcelona team. Int J Comput Theory Eng2013; 5(5): 812.
6.
SchaubergerGGrollA. Predicting matches in international football tournaments with random forests. Stat Model2018; 18(5–6): 460–482.
7.
PrasetioD. Predicting football match results with logistic regression. In: 2016 international conference on advanced informatics: concepts, theory and application (ICAICTA), Penang, Malaysia, 16–19 August 2016, pp.1–5. New York: IEEE.
8.
DavenportTH. How strategists use “big data” to support internal business decisions, discovery and production. Strategy Leadersh2014; 42(4): 45–50.
9.
BabootaRKaurH. Predictive analysis and modelling football results using machine learning approach for English Premier League. Int J Forecast2019; 35(2): 741–755.
10.
ThabtahFZhangLAbdelhamidN. NBA game result prediction using feature analysis and machine learning. Ann Data Sci2019; 6(1): 103–116.
11.
KoselerKStephanM. Machine learning applications in baseball: a systematic literature review. Appl Artif Intell2017; 31(9–10): 745–763.
12.
YuanBZhuJPanP, et al. Winning determinants between top and second division in Chinese professional football leagues: an interpretable machine learning approach. BMC Sports Sci Med Rehabil2025; 17(1): 86.
13.
XiaoLXiangyuCSongG, et al. Do contextual factors cause differences in passing performance between men and women? A network metrics analysis of the 2022 men’s and 2023 women’s FIFA World Cups using mixed linear models. Int J Perform Anal Sport. Epub ahead of print 11 July 2025. https://doi.org/10.1080/24748668.2025.2531627
14.
QuinlanJR. Induction of decision trees. Mach Learn1986; 1: 81–106.
15.
HastieTTibshiraniRFriedmanJ. An introduction to statistical learning. New York: Springer; 2009.
16.
HastieTTibshiraniRFriedmanJ. Unsupervised learning. In: BickelPDigglePFienbergS, et al. (eds). The elements of statistical learning: data mining, inference, and prediction. 2nd ed.New York: Springer, 2009, pp.485–585.
17.
BreimanL. Random forests. Mach Learn2001; 45: 5-32.
18.
FriedmanJH. Greedy function approximation: a gradient boosting machine. Ann Stat2001; 29(5): 1189–1232.
19.
ChenTXuBZhangC, et al. Training deep nets with sublinear memory cost. arXiv preprint arXiv:1604.06174. 2016.
20.
ChenTGuestrinC. Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, San Francisco, CA, USA, 13–17 August 2016. New York: ACM; 2016. p. 785-794.
HeHBaiYGarciaEA, et al. ADASYN: adaptive synthetic sampling approach for imbalanced learning. In: IEEE international joint conference on neural networks (IJCNN), Hong Kong, 1–8 June 2008, pp.1322–1328. New York: IEEE.
23.
BatistaGEPratiRCMonardMC. A study of the behavior of several methods for balancing machine learning training data. ACM SIGKDD Explor Newsl2004; 6(1): 20–29.
24.
TomekI. Two modifications of CNN. IEEE Trans Syst Man Cybern1976; 6(6): 769–772.
25.
LundbergSMLeeSI. A unified approach to interpreting model predictions. In: Advances in neural information processing systems 30, Long Beach, CA, USA, 4–9 December 2017, pp.4765–4774. Red Hook, NY: Curran Associates, Inc.
26.
YiJLeeW. Pandemic nationalism in South Korea. Society2020; 57(4): 446–451.
27.
SmyrnovVMitryasovaOSalamonI, et al. Analysis of trends and impacts of anthropogenic factors on groundwater quality. Ecol Eng Environ Technol2024; 25: 165–177.
28.
SmyrnovMFunckeFKablimanE. Prediction of material toughness using ensemble learning and data augmentation. Philos Mag Lett2024; 104(1): 2372497.
29.
CastellanoJCasamichanaDLagoC. The use of match statistics that discriminate between successful and unsuccessful soccer teams. J Hum Kinet2012; 31: 139–147.
30.
Lago-PeñasCLago-BallesterosJDellalA, et al. Game-related statistics that discriminated winning, drawing and losing teams from the Spanish soccer league. J Sports Sci Med2010; 9(2): 288–293.
31.
LalwaniASaraiyaASinghA, et al. Machine learning in sports: a case study on using explainable models for predicting outcomes of volleyball matches. arXiv preprint arXiv:2206.09258. 2022.
32.
ZhangY. Multi-factors analysis using visualizations and SHAP: comprehensive case analysis of tennis results forecasting. Int J Adv Comput Sci Appl2025; 16(1).
