A Predictive Framework for Forecasting Soccer Match Outcomes by Analyzing the Goal Count Achieved by A Specific Team
Keywords:
Soccer, Machine Learning, Predictive ModelAbstract
Soccer, a widely embraced sport, proves to be an intriguing subject for study due to its substantial data output. This article introduces a machine learning-based model designed to predict the success or failure of a soccer team based on its goal-scoring performance. The model employs four machine learning classifiers: Linear Regression, Support Vector Machines, Naive Bayes, and Decision Trees. Drawing on data from the Mexican football league spanning from 2012 to March 2020, the study is bifurcated into two segments: one encompassing draws and the other excluding them, aimed at unveiling the impact of draws on the analysis. The proposed model achieved an accuracy ranging from 81% to 84% when draws were excluded, while incorporating draws resulted in an accuracy range of 72% to 75%.
References
Buchdahl, J. (2003). Fixed odds sports betting: statistical forecasting and risk management. High Stakes Publisher, London.
Rahman, A. (2020). A deep learning framework for football match prediction. SN Applied Sciences, Vol. 2, No. 165.
Behravan, I., Razavi, S. (2020). A novel machine learning method for estimating football players’ value in the transfer market. Soft Computing, Vol. 25, pp. 2499–2511. DOI: 10.1007/s00500-020-05319-3.
Domínguez, J., López, B., Mihaylova, P. Georgieva, P. (2019). Incremental learning for football match outcomes prediction. Iberian Conference on Pattern Recognition and Imagine Analysis, pp. 217–228. DOI: 10.1007/978-3-030- 31321-0_19.
Igual, L., Seguí, S. (2017). Introduction to data science, a python approach to concepts, techniques and applications. Springer.
Scikit learn (2011). Scikit learn developers (BSD License). Support vector machines.
Scikit learn (2011). Scikit learn developers (BSD License). Decision trees.
Scikit learn (2011). Scikit learn developers (BSD License). Naive Bayes.
Paper, D., (2020). Scikit-learn classifier tuning from complex training sets. Hands-on Scikit-Learn for Machine Learning Applications, pp. 165–188. DOI: 10.1007/978-1-4842-5373-1_6. 10. Singh, P. (2019). Machine learning with PySpark, with natural language processing and recommender systems. Second Edition, Apress.
Nelli, F. (2018). Python data analytics, with pandas, numpy and matplotlib. Second Edition, Apress.
Abdullah, K, Folorunso, S., Solanke, O., Sodimu, S. (2018). A predictive model for tweet sentiment analysis and classification. Annals. Computer Science Series. Vol. 16, No. 2.
