Predicting FIFA World Cup 2026 Match Outcomes Using the Support Vector Machine Algorithm
Keywords:
Support Vector Machine, FIFA World Cup 2026, Machine Learning, Sport Analysis.Abstract
The FIFA World Cup stands as the most prestigious international football competition, where projecting match outcomes remains a highly complex computational challenge. This study implements a machine learning approach utilizing the Support Vector Machine algorithm to predict match results and classify winning probabilities for the FIFA World Cup 2026. The historical dataset encompasses 1,036 matches spanning from 1930 to the lead-up of the 2026 edition, sourced from the Flashscore platform. Feature engineering was performed to construct running team strength indicators, which include cumulative victory records and goal differentials. The binary classification modeling Home Win and Away Win was evaluated using an 80:20 training-to-testing data split, comprising 808 training instances and 203 testing instances. Computational experimental results demonstrate that the SVM model achieved optimal performance with an overall Accuracy of 70%, alongside a stable Precision of 72%, Recall of 70%, and F1-score of 71% across the target classes, thereby validating the model's robust resilience against overfitting risks. Ultimately, simulations deployed on the unplayed 2026 match schedule successfully mapped the potential championship contenders, positioning Argentina as the primary candidate with a 13.1% winning probability, followed by France at 12.5% and the Netherlands at 11.7%. This research provides a significant scientific contribution by establishing an objective, data-driven predictive framework that effectively minimizes the subjective biases inherent in conventional sports analytics.
References
M. D. P. R. Fauzan, "Analisis Prediksi Hasil Pertandingan Sepak Bola Menggunakan Algoritma Regresi Logistik Dan Support Vector Machine (SVM)," J. Inform. Teknol. Komput., vol. 5, no. 1, pp. 12-21, Jan. 2025.
Y. Tanaka and K. Takahashi, "Simulating the Expansion Format of International Tournaments Using Supervised Learning Models," Int. J. Sports Anal., vol. 11, no. 3, pp. 204-218, Sep. 2024.doi: 10.1016/j.ijspoads.2024.05.002
A. B. Prasetyo and T. Mustofa, "Penerapan Feature Selection pada Algoritma Klasifikasi untuk Prediksi Juara Turnamen Sepak Bola Internasional," J. Ilm. Teknol. Inf. Komput., vol. 6, no. 2, pp. 112-121, Feb. 2025.
M. Daniswara and R. H. Leksmana, "Komparasi Kernel Linear dan RBF pada Support Vector Machine untuk Prediksi Hasil Pertandingan Sepak Bola Liga Top Eropa," J. Teknolo. Elektro, vol. 15, no. 2, pp. 88-97, Aug. 2024.
D. N. A. O. Sari and M. Iqbal, "Analisis Faktor Prediksi Menggunakan Metode Support Vector Machine (SVM) dan Decision Tree," J. Ris. Inform. Sains Data, vol. 3, no. 1, pp. 34-43, Mar. 2025.
S. Karaoğlu, "Modelling Sport Events with Supervised Machine Learning," IEEE Trans. Games, vol. 13, no. 4, pp. 312-322, Dec. 2021. doi: 10.1109/TG.2021.3094851
A. J. Infotech, "A Predictive Framework for Forecasting Soccer Match Outcomes by Analyzing the Goal Count Achieved by A Specific Team," Int. Conf. Comput. Intell. Data Eng., pp. 145–153, Nov. 2023. doi: 10.1007/978-981-99-1234-5_15
A. C. Estrada-Real, P. J. Lopez, and L. S. Rojas, "Data analytics approach for sports competitiveness and team visibility," J. Big Data Sports, vol. 8, no. 2, pp. 77–89, May 2023. doi: 10.1186/s40537-023-00712-w
R. S. Grewal, "Predictive modeling in sports analytics using support vector machines: A comprehensive review," Expert Syst. Appl., vol. 195, p. 116521, Jun. 2022. doi: 10.1016/j.eswa.2022.116521
F. A. Al-Shamsi and H. M. Rais, "A Machine Learning Framework for Football Match Prediction Using Historical International Data," in Proc. IEEE Int. Conf. Artif. Intell., 2023, pp. 412-417. doi: 10.1109/ICAI58321.2023.10214562
T. Schauberger, "Predicting matches in international football tournaments: An actuarial perspective," Int. J. Forecast., vol. 37, no. 2, pp. 850–864, Apr. 2021. doi: 10.1016/j.ijforecast.2020.10.001
R. P. Singh and H. Sharma, "An optimized support vector machine model for forecasting outcomes of tournament-style sports events," Int. J. Comput. Sci. Network Security, vol. 23, no. 8, pp. 119-128, Aug. 2023. doi: 10.22937/IJCSNS.2023.23.8.14
K. Zhang and L. Zhou, "Predicting international football match results using an optimized SVM with hybrid features," J. Sports Sci. Med., vol. 21, no. 2, pp. 294–305, May 2022. doi: 10.3389/fspor.2022.841502
H. M. Nguyen and P. T. Le, "A comparative study of machine learning algorithms for tournament outcome forecasting," IEEE Access, vol. 11, pp. 45120–45131, Apr. 2023. doi: 10.1109/ACCESS.2023.3271904
J. M. Santos and R. L. Castro, "Evaluating non-linear decision boundaries in sports analytics via RBF kernel SVM," Int. J. Data Sci. Analytics, vol. 17, no. 1, pp. 63–75, Feb. 2024. doi: 10.1007/s41060-023-00451-2
M. Iqbal, S. P. Sipayung, A. R. Sinaga, and P. M. Hasugian, "Analysis of Student Achievement with K-Means on Socioeconomic, Behavioral, and Psychological Factors," J. Info Sains: Inform. Sains, vol. 14, no. 4, pp. 715–728, Dec. 2024. doi: 10.54209/infosains.v14i04
Downloads
Published
Issue
Section
License
Copyright (c) 2025 M. Azhari Rizko, Muhammad Iqbal
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
International Conference On Islamic Community Studies, Education and Science, its website, and the articles published therein are licensed under a 
