In order to explore the influence of various factors on the outcome of football matches, a total of 1520 matches of English Premier League, French Ligue 1, Spanish Liga, and Italian Serie A in the 2021-2022 season were selected as the research object, and Analytic hierarchy process (AHP) and Binary classification machine learning algorithm were used for modeling. The paper strength and onfield factors of the team are taken as variables, and the final winning or losing results of each participating team is taken as the result for statistical modeling. After obtaining the results of the model, it can be applied to the team’s future result to lay out strategies in advance, thus providing a more intuitive understanding of the team’s tactical style and scoring result. In general, the paper strength of attacking, passing, defense, goalkeeping and so on reflects the strength of the team to a large extent, and also determines the result and goal difference to a certain extent. In addition, the influence of the host and visiting venues on crowd support, player adaptation, and travel time has a further impact on the outcome of football matches, especially for teams with a small difference in paper strength. Even for some of the weaker teams or teams with similar paper strength, home field advantage will compensate for the difference in strength; for different leagues, the league with stronger average strength will be less affected by home and away, while the league with weaker average strength will be affected with greater variation. In summary, the accuracy of the overall prediction results is relatively significant.

Yuqing Yang. Research on the winning factors of football matches based on machine learning. Academic Journal of Mathematical Sciences (2023) Vol. 4, Issue 4: 51-56. https://doi.org/10.25236/AJMS.2023.040408.

[1] Horvat, Tomislav, and Josip Job. "The use of machine learning in sport outcome prediction: A review." Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery 10.5 (2020): e1380.

[2] Saaty, Thomas L. "How to make a decision: the analytic hierarchy process." European journal of operational research 48.1 (1990): 9-26 [J].

[3] Varela G, Novoa N, Jiménez M.F, et al. A pplicability of logistic regression (LR) risk modelling to decision making in lung cancer resection[J].Interactive Cardiovascular & Thoracic Surgery, (2003) (1):12-15.

[4] Liaw A, Wiener M .Classification and Regression by Random Forest [J]. R News, (2002), 23(23).

[5] Mccallum A, Nigam K. A comparison of event models for Naive Bayes text classification[J]. IN AAAI-98 WORKSHOP ON LEARNING FOR TEXT CATEGORIZATION, (1998) 41--48.

[6] Rumelhart D E, Hinton G E, Williams R J .Learning Representations by Back Propagating Errors[J].Nature, (1986), 323(6088):533-536.

[7] Kingma D, Ba J. Adam: A Method for Stochastic Optimization[J]. Computer Science, (2014).

[8] Hanley, James A., and Barbara J. McNeil. "The meaning and use of the area under a receiver operating characteristic (ROC) curve." Radiology 143.1 (1982): 29-36.