Türkiye Süper Ligi'nde Futbol Şut Sonuçlarının Tahmini: Destek Vektör Makineleri ve Naive Bayes Modelleri ile Özellik Önem Analizi

Öz

Bu çalışma, 2020–2025 sezonları arasında Türkiye Süper Ligi’nde gerçekleşen şut kayıtlarını temel alarak, gol tahminini ikili sınıflandırma problemi (gol için 1, gol olmaması durumu için 0) olarak formüle eden bir modelleme çerçevesi sunmaktadır. Çalışmada, tahmin modelleri için Naive Bayes ve Destek Vektör Makinesi, denetimli makine öğrenmesi algoritmaları, kullanılmıştır. Bu çalışmanın odak noktası, orijinal veri setindeki gol ve gol dışı durumlar arasındaki önemli sınıf dengesizliğini gidererek model kurmak ve modelin genel performansını artırmaktır. Dengeli bir veri seti için oluşturulan makine öğrenmesi modellerine ait sonuçlar karşılaştırılmış ve bulgular, futbolun karmaşık veri yapısına uyum sağlamada SVM modellerinin görece daha başarılı olduğunu göstermiştir. Model tahminlerinin gerçek sonuçlarla uyum sergilediği ve güvenilir sonuçlar ürettiği gözlemlenmiştir. Model açıklanabilirlik teknikleri kullanılarak yapılan analizlerde, mesafe ve pass mesafesinin şut başarısını açıklamada en temel belirleyiciler olduğu doğrulanmıştır. En önemli değişkenlerin mesafe ve açı ile ilgili olduğu görülmektedir. Bu çalışma, tahmin gücü ve model şeffaflığı ile hem literatüre katkı sağlamakta hem de özellikle Türkiye Süper Ligi için bir karar destek çerçevesi sunmaktadır.

Anahtar Kelimeler

• Gol
• futbol
• Makine Öğrenmesi
• Sınıf Dengesizliği
• Spor Analitiği
• Açıklanabilir Yapay Zeka (XAI)
• Türkiye Süper Ligi.

Predicting Football Shot Outcomes in the Turkish Super League: Support Vector Machine and Naive Bayes Models with Feature Importance Analysis

Öz

This study presents a modeling framework that formulates goal prediction as a binary classification problem (1 for a goal, 0 for no goal), based on shot records from the Turkish Super League between the 2020–2025 seasons. In this study, Naive Bayes (NB) and Support Vector Machine (SVM), which are supervised machine learning algorithms, used for prediction models. The focus of this study is to build a model and improve its overall performance by addressing the significant class imbalance between goals and non-goals in the original dataset. The results of machine learning models created for a balanced dataset were compared, and the findings showed that SVM models were relatively more successful in adapting to the complex data structure of football. Feature importance analyses confirmed that distance is the most dominant predictor of shot success. It has appeared that the most important variables are related to distance and angle. This study contributes to the literature with its predictive power and model transparency, and offers a decision support framework, especially for the Turkish Super League.

Anahtar Kelimeler

• Goal
• football
• Machine Learning
• Imbalanced data
• Sports Analytics
• Explainable AI (XAI)
• Turkish Super League

Kaynakça

1. Anzer, G., & Bauer, P. (2021). A goal scoring probability model for shots based on synchronized positional and event data in football (soccer). Frontiers in sports and active living, 3, 624475. https://doi.org/10.3389/fspor.2021.624475
2. Burhaein, E., Fadjerı, A., & Widiyono, I. P. (2024). Application of Naive Bayes Algorithm for Physical Fitness Level Classification. International Journal of Disabilities Sports and Health Sciences, 7(1), 178-187. https://doi.org/10.33438/ijdshs.1330745
3. Cavus, M., Stańdo, A., & Biecek, P. (2026). Glocal Explanations of Expected Goal Models in Football. In: Guidotti, R., Schmid, U., Longo, L. (eds) Explainable Artificial Intelligence. xAI 2025. Communications in Computer and Information Science, vol 2580. Springer, Cham. https://doi.org/10.1007/978-3-032-08333-3_1
4. Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 16, 321–357. https://doi.org/10.1613/jair.953
5. Davis, J., & Robberechts, P. (2024). Biases in expected goals models confound finishing ability. arXiv preprint arXiv:2401.09940. https://arxiv.org/abs/2401.09940
6. Ding, S. (2020). Game Predication of FIFA Football World Cup Based on Support Vector Machine. Academic Journal of Computing & Information Science, 3(5), 17–22.
7. Eggels, H. (2016, October). Expected goals in soccer: Explaining match results using predictive analytics. In The machine learning and data mining for sports analytics workshop (Vol. 16, p. 131). Technische Universiteit Eindhoven.
8. Fairchild, A., Pelechrinis, K., & Kokkodis, M. (2018). Spatial analysis of shots in MLS: A model for expected goals and fractal dimensionality. Journal of Sports Analytics, 4(3), 165–174. https://doi.org/10.3233/JSA-170207

9. Guan, Z. (2025). Scalable Framework for Basketball Game Prediction Combining Image Processing XGBoost and Enhanced Support Vector Machine. Scalable Computing: Practice and Experience, 26(4), 1727-1739. https://doi.org/10.12694/scpe.v26i4.4684
10. Hewitt, M., & Karakuş, O. (2023). A Machine Learning Approach for Player and Position Adjusted Expected Goals in Football (Soccer) Franklin Open, 4, 100034. https://doi.org/10.1016/j.fraope.2023.100034
11. Hubáček, O., Šourek, G., & Železný, F. (2019). Learning to predict soccer results from relational data with gradient boosted trees. Machine Learning, 108(1), 29–47. https://doi.org/10.1007/s10994-018-5704-6
12. Iapteff, L., Brito, L., & Zanella, A. (2025). Toward interpretable expected goals modelling using Bayesian mixed models. Frontiers in Sports and Active Living, 7, 1504362. https://doi.org/10.3389/fspor.2025.1504362
13. Igiri, C. P. (2015). Support Vector Machine–Based Prediction System for a Football Match Result. IOSR Journals (IOSR Journal of Computer Engineering), 17(3), 21-26. https://www.europub.co.uk/articles/111323
14. Kahraman, H. T. (2022). Prediction of basketball match results using machine learning algorithms [Unpublished master's thesis]. Middle East Technical University.
15. Kim, J., & Park, J. (2025). Applying machine learning for analyzing shooting importance in modern pentathlon. Applied Sciences, 15(17), 9378. https://doi.org/10.3390/app15179378
16. Li, L., & Hao, A. (2025). Research on the sports training effect based on GABP neural network and artificial intelligence. Scientific Reports, 15(1), 39214. https://doi.org/10.1038/s41598-025-20426-7
17. Lucey, P., Bialkowski, A., Monfort, M., Carr, P., & Matthews, I. (2015). "Quality vs quantity": Improved shot prediction in soccer using strategic features from spatiotemporal data. Proceedings of the 9th Annual MIT Sloan Sports Analytics Conference, 1–9.
18. Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems 30 (pp. 4765–4774). Curran Associates.
19. Mead, J., O’Hare, A., & McMenemy, P. (2023). Expected goals in football: Improving model performance and demonstrating value. Plos one, 18(4), e0282295. https://doi.org/10.1371/journal.pone.0282295
20. Moustakidis, S., Plakias, S., Kokkotis, C., Tsatalas, T., & Tsaopoulos, D. (2023). Predicting football team performance with explainable AI: Leveraging SHAP to identify key team-level performance metrics. Future Internet, 15(5), 174. https://doi.org/10.3390/fi15050174
21. Ou-Yang, Y., Hong, W., Peng, L., Mao, C. X., Zhou, W. J., Zheng, W. T., ... & Wang, Y. F. (2025). Explaining basketball game performance with SHAP: insights from Chinese Basketball Association. Scientific Reports, 15(1), 13793. https://doi.org/10.1038/s41598-025-97817-3
22. Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, É. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825–2830.
23. Pietraszewski, P., Terbalyan, A., Roczniok, R., Maszczyk, A., Ornowski, K., Manilewska, D., Kuliś, S., Zając, A., & Gołaś, A. (2025). The role of artificial intelligence in sports analytics: A systematic review and meta-analysis of performance trends. Applied Sciences, 15(13), 7254. https://doi.org/10.3390/app15137254
24. Rudrapal, D., Boro, S., Srivastava, J., & Singh, S. (2020). A Deep Learning Approach to Predict Football Match Result. In: Behera, H., Nayak, J., Naik, B., Pelusi, D. (eds) Computational Intelligence in Data Mining. Advances in Intelligent Systems and Computing, vol 990. Springer, Singapore. https://doi.org/10.1007/978-981-13-8676-3_9
25. Scholtes, A., & Karakuş, O. (2024). Bayes-xG: player and position correction on expected goals (xG) using Bayesian hierarchical approach. Front. Sports Act. Living 6:1348983. https://doi.org/10.3389/fspor.2024.1348983
26. Senn, W. (2024). Addressing evaluation challenges on the expected goals (xG) metric in football analysis [Unpublished bachelor's thesis]. University of Applied Sciences and Arts Western Switzerland. https://sonar.ch/global/documents/331251
27. Seyrek, M., Kiriktir, E., Doğan, Y., & Yapıcıoğlu, B. (2021). Football Match Result Prediction Decision Support System. Journal of Current Research on Engineering, Science and Technology, 7 (2), 173-202. https://doi.org/10.26579/jocrest.85
28. Sharma, M., Monika, Kumar, N., & Kumar, P. (2022). Naive bayes-correlation based feature weighting technique for sports match result prediction. Evolutionary Intelligence, 15(3), 2171-2186. https://doi.org/10.1007/s12065-021-00629-3.
29. Tax, N., & Joustra, Y. (2015). Predicting the Dutch football competition using public data: A machine learning approach. https://doi.org/10.13140/RG.2.1.1383.4729
30. Venkatachalam, A., Rajeswari, D., & SS, S. N. (2023, March). Football prediction system using gaussian naïve bayes algorithm. In 2023 second international conference on electronics and renewable systems (ICEARS) (pp. 1640-1643). IEEE. DOI:10.1109/ICEARS56392.2023.10085510
31. Wu, L. C., Kuo, C., Loza, J., Kurt, M., Laksari, K., Yanez, L. Z., Senif, D., Anderson, S. C., Miller, L. E., Urban, J. E., Stitzel, J. D., & Camarillo, D. B. (2018). Detection of American football head impacts using biomechanical features and support vector machine classification. Scientific Reports, 8, 855. https://doi.org/10.1038/s41598-017-17864-3
32. Yeung, C., & Fujii, K. (2024). A strategic framework for optimal decisions in football 1-vs-1 shot-taking situations: An integrated approach of machine learning, theory-based modeling, and game theory. Complex & Intelligent Systems, 10(5), 5989–6008. https://doi.org/10.1007/s40747-024-01466-4