Serving Up Success: Unveiling the Power of Machine Learning for Volleyball League Prediction

Year 2024, Volume: 29 Issue: 3, 202 - 209, 31.07.2024

Emre Altundağ Hasan Aka Çağlar Soylu Pervin Demir

https://doi.org/10.53434/gbesbd.1478533

Abstract

This study investigates the efficacy of Artificial Neural Networks (ANN) in predicting volleyball league standings, focusing on the Turkish Volleyball Federation's Sultanlar and Efeler leagues over five seasons (2018-19 to 2022-23). Given the complexity and volume of performance data in volleyball, traditional analysis methods often face challenges such as data overload and high operational costs. ANN models, known for their ability to learn from and generalize data, present a promising solution to these challenges. By analyzing 23 input variables related to match performance, including points scored, services, attacks, and blocks, this study aims to identify the most influential factors on final league standings and provide a more objective, rapid, and economical analysis method. The results indicate significant potential for ANN in sports analytics, demonstrating high accuracy rates in predictions, especially for the Sultanlar League. However, the study also acknowledges limitations such as data quality and model complexity, suggesting areas for future research to enhance predictive accuracy and applicability of ANN in volleyball and other sports analytics.

Keywords

Artificial Neural Networks, Volleyball League Standings, Machine Learning, Sports Analytics, Performance Prediction

Başarıya Hizmet Etmek: Voleybol Ligi Tahmini için Makine Öğreniminin Gücünün Ortaya Çıkarılması

Abstract

Bu çalışma, Türkiye Voleybol Federasyonu'nun Sultanlar ve Efeler liglerine odaklanarak, beş sezon boyunca (2018-19 - 2022-23) voleybol lig sıralamalarını tahmin etmede Yapay Sinir Ağlarının (YSA) etkinliğini araştırmaktadır. Voleybolda performans verilerinin karmaşıklığı ve büyüklüğü göz önüne alındığında, geleneksel analiz yöntemleri genellikle aşırı veri yükü ve yüksek operasyonel maliyetler gibi zorluklarla karşılaşmaktadır. Verilerden öğrenme ve genelleme yetenekleriyle bilinen YSA modelleri, bu zorluklara umut verici bir çözüm sunmaktadır. Bu çalışma, atılan sayılar, servisler, ataklar ve bloklar dahil olmak üzere maç performansıyla ilgili 23 girdi değişkenini analiz ederek, nihai lig sıralaması üzerinde en etkili faktörleri belirlemeyi ve daha objektif, hızlı ve ekonomik bir analiz yöntemi sağlamayı amaçlamaktadır. Sonuçlar, özellikle Sultanlar Ligi için tahminlerde yüksek doğruluk oranları göstererek spor analitiğinde YSA için önemli bir potansiyel olduğunu göstermektedir. Bununla birlikte, çalışma aynı zamanda veri kalitesi ve model karmaşıklığı gibi sınırlamaları da kabul etmekte ve YSA'nın voleybol ve diğer spor analitiklerinde tahmin doğruluğunu ve uygulanabilirliğini artırmak için gelecekteki araştırmalar için alanlar önermektedir.

Keywords

Yapay Sinir Ağları, Voleybol Lig Sıralamaları, Makine Öğrenimi, Spor Analitiği, Performans Tahmini

References

• Aka, H., Akarçeşme, C., Aktuğ, Z. B., & Ozden, S. (2021a). The estimation of the set results in 2016/2017 &stel &nus sultans league games by artificial neural network. European Journal of Human Mo&ment; 47: 32-39.
• Aka, H., Aktuğ, Z. B. & Kılıç, F. (2021b). Estimating the England premier league ranking with artificial neural network. Applied Artificial Intelligence; 35: 393-402.
• Akarçeşme C, Aka H, Özden S, & Aktug, Z.B. (2020). Estimating the volleyball team ranking in the 2016 Rio Olympics by artificial neural network and linear model: Yapay sinir ağları & doğrusal model ile 2016 Rio Olimpiyatlarındaki voleybol takım sıralamasının tahmin edilmesi. Journal of Human Sciences 17: 1069-1078.
• Bai, Z. & Bai, X. (2021). Sports Big Data: Management, Analysis, Applications, and Challenges. Complexity;6676297.
• Beck, M. W. (2018). Neural NetTools: Visualization and analysis tools for neural networks. Journal of statistical software; 85: 1.
• Cossich, V. R. A., Carlgren, D., Holash, R. J., & Katz, L. (2023). Technological Breakthroughs in Sport: Current Practice and Future Potential of Artificial Intelligence, Virtual Reality, Augmented Reality, and Modern Data Visualization in Performance Analysis. Applied Sciences 13: 12965.
• Cortsen, K. & Rascher, D. A. (2018). The application of sports technology and sports data for commercial purposes. The use of technology in sport: Emerging challenges: 47-84.
• Górriz, J.M., Álvarez-Illán, I., Álvarez-Marquina, A., et al (2023). Computational approaches to Explainable Artificial Intelligence: Advances in theory, applications and trends. Information Fusion 100: 101945.
• João, P. V., Vaz, L. & Mota, M. P. (2019). The statistics which qualified Portugal for the European Volleyball Championship 2019. Motricidade 15: 139-139.
• Fernandez-Eche&rria, C., Mesquita, I., González-Silva, J., & Eche&rría, F. C. (2017). Match analysis within the coaching process: a critical tool to impro& coach efficacy. International Journal of Performance Analysis in Sport; 17: 149-163.
• Jörg, M., Perl, J. & Schöllhorn, W. (2017). Analysis of players’ configuration by means of artifical neural networks. International Journal of Performance Analysis in Sport; 7: 90-105.
• Kautz, T., Groh, B. H., Hannink, J., Jensen, U. (2017). Activity recognition in beach volleyball using a Deep Convolutional Neural Network: Le&raging the potential of Deep Learning in sports. Data Mining and Knowledge Disco&ry 31: 1678-1705.
• Komar, E., Egrioglu, E. & Semiz, K. (2023). Türkiye & İtalya Voleybol Süper Ligleri 2013-2020 İstatistik &rilerinin &ri Madenciliği Yöntemleriyle Analizi. Eurasian Research in Sport Science; 8: 54-66.
• Kufel, J., Bargieł-Łączek, K., Kocot, S., et al. (2023). What Is Machine Learning, Artificial Neural Networks and Deep Learning?-Examples of Practical Applications in Medicine. Diagnostics (Basel, Switzerland) 13 2023/08/12. DOI: 10.3390/diagnostics13152582.
• Millington, B. & Millington, R. (2015). ‘The datafication of everything’: Toward a sociology of sport and big data. Sociology of Sport Journal; 32: 140-160.
• Palao, J. M. & Hernández-Hernández, E. (2014). Game statistical system and criteria used by Spanish volleyball coaches. International Journal of Performance Analysis in Sport 14: 564-573.
• Taye, M. M. (2023). Understanding of Machine Learning with Deep Learning: Architectures, Workflow, Applications and Future Directions. Computers; 12: 91.
• Tümer, A. E. & Koçer, S. (2017). Prediction of team league’s rankings in volleyball by artificial neural network method. International Journal of Performance Analysis in Sport; 17: 202-211.
• Yang, Y. (2021). Data Mining Algorithm in Volleyball Match Technical and Tactical Analysis. In: Application of Big Data, Blockchain, and Internet of Things for Education Informatization: First EAI International Conference, BigIoT-EDU 2021, Virtual E&nt, August 1–3, 2021, Proceedings, Part II 1 2021, pp.204-213. Springer.
• Wei, T., Simko, V., Levy, M., et al. (2021). package “corrplot”: Visualization of a Correlation Matrix. 2017. &rsion 084 2021.
• Wickham, H., Chang, W. & Wickham, M. H. (2016). Package ‘ggplot2’. Create elegant data visualisations using the grammar of graphics &rsion 2016; 2: 1-189.
• Schumaker, R. P., Solieman, O. K., Chen, H., et al. (2010). Sports data mining: The field. Sports Data Mining 1-13.