Football Match Result Prediction Using Machine Learning and Binary Model Fusion

• Douglas da S. Souza Universidade Federal Fluminense (UFF)
• Leandro S. de Araújo Universidade Federal Fluminense (UFF) https://orcid.org/0000-0002-3631-8761

DOI: https://doi.org/10.5753/sbbd_estendido.2026.249742

Resumo

This paper investigates English Premier League match result prediction using complementary machine learning approaches: direct multiclass classification, temporal goal forecasting, Isolation Forest-based binary anomaly detection, and simple binary decision-level fusion. Experiments were conducted on EPL data from the 2006–07 to the 2024–25 seasons using an expanding-window walk-forward validation protocol. Results show that betting odds concentrate most of the predictive information in direct classification, while temporal goal forecasting provides useful numerical estimates but does not necessarily improve outcome reconstruction. Isolation Forest underperforms supervised models in the binary setting, and binary fusion does not outperform the best individual model.

Palavras-chave: Football Prediction, Data Fusion, Prediction of sports results, Machine Learning, Goal prediction

Referências

Berrar, D., Lopes, P., and Dubitzky, W. (2019). Incorporating domain knowledge in machine learning for soccer outcome prediction. Machine Learning, 108:97–126.

Dixon, M. J. and Coles, S. G. (1997). Modelling association football scores and inefficiencies in the football betting market. Journal of the Royal Statistical Society: Series C (Applied Statistics), 46(2):265–280.

Goddard, J. (2005). Regression models for forecasting goals and match results in association football. International Journal of Forecasting, 21(2):331–340.

Igiri, C. P. and Nwachukwu, E. O. (2014). An improved prediction system for football match result. IOSR Journal of Engineering, 4(12):12–20.

Liu, F. T., Ting, K. M., and Zhou, Z.-H. (2008). Isolation forest. In 2008 Eighth IEEE International Conference on Data Mining, pages 413–422. IEEE.

Maher, M. J. (1982). Modelling association football scores. Statistica Neerlandica, 36(3):109–118.

Zhang, Q., Xu, H., Wei, L., and Zhou, L. (2019). Prediction of football match results based on model fusion. In Proceedings of the 2019 3rd International Conference on Innovation in Artificial Intelligence, pages 198–202.