A Supervised Machine Learning Framework for Sports Championship Prediction: Case Studies in the NBA and FIFA World Cup

• João Vitor T. Arroyo UFSCar
• Lucas V. Fujii UFSCar
• Gustavo de O. Gimenes UFSCar
• Murilo C. Naldi UFSCar

DOI: https://doi.org/10.5753/eniac.2026.31361

Resumo

This paper proposes a generalizable machine learning framework for sports championship prediction, leveraging a structural analogy where qualifying phases provide features and championship phases yield targets. Evaluated on the NBA (2000–2025) and FIFA World Cup (1958–2022) across five classifiers, it addresses class imbalance via AUC-ROC optimization and threshold calibration. Logistic Regression achieved a 0.933 AUC-ROC in the NBA, while Random Forest and SVM led the World Cup with 0.921 AUC. Validation via DeLong and McNemar tests, bootstrap intervals, and temporal splits supports result stability. The framework readily adapts to other competitions, offering actionable insights for sports analytics.

Palavras-chave: Sports Championship Prediction, Supervised Machine Learning, Class Imbalance, Temporal Validation, Feature Engineering, Sports Data Mining

Referências

Bunker, R. and Susnjak, T. (2022). The application of machine learning techniques for predicting match results in team sport: A review. Journal of Artificial Intelligence Research, 73:1285–1322.

Bunker, R., Yeung, C., and Fujii, K. (2024). Machine learning for soccer match result prediction. In Artificial Intelligence, Optimization, and Data Sciences in Sports, pages 7–49. Springer.

Davis, J. and Goadrich, M. (2006). The relationship between precision-recall and ROC curves. Proceedings of the 23rd International Conference on Machine Learning, pages 233–240.

DeLong, E. R., DeLong, D. M., and Clarke-Pearson, D. L. (1988). Comparing the areas under two or more correlated receiver operating characteristic curves: A nonparametric approach. Biometrics, 44(3):837–845.

Duque, A. (2024). Brasileirão dataset. GitHub repository.

Felice, C. et al. (2024). Artificial intelligence and machine learning in sports prediction: A systematic review. Electronics, 13(17):3444.

Gifford, M. and Bayrak, T. (2023). A predictive analytics model for forecasting outcomes in the national football league games using decision tree and logistic regression. Decision Analytics Journal, 8:100296.

Gilch, L. A. and Müller, S. (2018). On Elo based prediction models for the FIFA World Cup 2018. Journal of Quantitative Analysis in Sports, 14(4):187–200.

Groll, A., Ley, C., Schauberger, G., and Van Eetvelde, H. (2019). A hybrid random forest to predict soccer matches in international tournaments. Journal of Quantitative Analysis in Sports, 15(4):271–287.

Hand, D. J. (2009). Measuring classifier performance: A coherent alternative to the area under the ROC curve. Machine Learning, 77(1):23–39.

Horvat, T. and Job, J. (2020). The use of machine learning in sport outcome prediction: A review. WIREs Data Mining and Knowledge Discovery, 10(5):e1380.

Lin, H.-Y., Lien, J.-J. J., and Chang, Y.-N. (2024). Machine learning in sports analytics: Volleyball match outcome prediction. In 2024 4th International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), pages 1–6. IEEE.

Loeffelholz, B., Bednar, E., and Bauer, K. W. (2009). Predicting NBA games using neural networks. Journal of Quantitative Analysis in Sports, 5(1).

Mart, J. (2024). International football results from 1872 to present. GitHub repository.

McNemar, Q. (1947). Note on the sampling error of the difference between correlated proportions or percentages. Psychometrika, 12(2):153–157.

Moya, D., Tipantuña, C., Villa, G., Calderón-Hinojosa, X., Rivadeneira, B., and Álvarez, R. (2025). Machine learning applied to professional football: Performance improvement and results prediction. Machine Learning and Knowledge Extraction, 7(3):85.

Song, G. et al. (2024). Predicting the FIFA World Cup Qatar 2022 using machine learning and SHAP analysis. Applied Sciences, 14(8):3169.

Sumitro Datta (2024). NBA/ABA/BAA Stats. Kaggle dataset.

Terner, Z. and Franks, A. (2021). Modeling player and team performance in basketball. Annual Review of Statistics and Its Application, 8:1–23.

Thabtah, F., Zhang, L., and Abdelhamid, N. (2019). Nba game result prediction using feature analysis and machine learning. Annals of Data Science, 6(1):103–116.