Machine Learning-Based Player Performance Analysis for Association of Tennis Professionals Tour

Youchen Qing

doi:10.54097/k84mdj10

Authors

Youchen Qing

DOI:

https://doi.org/10.54097/k84mdj10

Keywords:

ATP Tour; machine learning; data analysis.

Abstract

This study explores the use of data analysis in professional tennis, using the dataset of the world-renowned Association of Tennis Professionals (ATP) Tour, which is the top-class men's professional tennis tour. Utilizing the match data of all the players, mainly Novak Djokovic, the research applies various models and methods of data preprocessing and selection to predict match outcomes. The main objective is to provide data-supported insight to professional tennis players and coaches to help analyze and further improve their tennis. The analysis and model take factors like player performance, court types, and tournament importance into consideration. This study shows the potential of data analysis in sports where such resources are often limited to well-funded teams. Not only the effect of different models in forecasting tennis match outcomes is evaluated, but also the influence of non-critical tournaments and external factors like injuries and policies on the accuracy of predictions are explored. The research findings offer insights into the evolving role of data analysis in enhancing sports strategies and performance, indicating a promising future for data-driven decision-making in professional tennis for different levels of players.

Downloads

Download data is not yet available.

References

Wang Jin, Yaqiong Yang, Tian Wang, R. Simon Sherratt, and Jingyu Zhang. Big data service architecture: a survey. Journal of Internet Technology, 2020, 21(2): 393-405.

Zhu Pan, and Feng Sun. Sports athletes’ performance prediction model based on machine learning algorithm. In International Conference on Applications and Techniques in Cyber Intelligence, 2020, 7: 498-505.

Oytun Musa, Cevdet Tinazci, Boran Sekeroglu, Caner Acikada, and Hasan Ulas Yavuz. Performance prediction and evaluation in female handball players using machine learning models. IEEE Access, 2020, 8: 116321-116335.

Arcagni Alberto, Vincenzo Candila, and Rosanna Grassi. A new model for predicting the winner in tennis based on the eigenvector centrality. Annals of Operations Research, 2023, 325 (1): 615-632.

Yue Jack C., Elizabeth P. Chou, Ming-Hui Hsieh, and Li-Chen Hsiao. A study of forecasting tennis matches via the Glicko model. Plos one, 2022, 17(4): e0266838.

Kaggle ATP matches, URL: https://www.kaggle.com/datasets/sijovm/atpdata, Last Accessed 2023/11/20.

Chen Tianqi, and Carlos Guestrin. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 2016: 785-794.

Noble William. What is a support vector machine? Nature biotechnology, 2006, 24(2): 1565-1567.

Ke Guolin, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 2017, 30: 1-9.

Sharma, Poonam, and Akansha Singh. Era of deep neural networks: A review. In 2017 8th International Conference on Computing, Communication and Networking Technologies, 2017: 1-5.