Research on Tennis Match Result Analysis Based on Multi-model Integration
DOI:
https://doi.org/10.54097/a3v4wm09Keywords:
Neural Network, Random Forest, Decision Tree Regression, Tennis.Abstract
Tennis is particularly prominent among the many highly competitive sports, and it is critical to provide scientific strategic guidance to players in modern tennis competitions. Based on data from the men's singles final of the 2023 Wimbledon Tennis Championships, this study synthesized match flow and scoring dynamics, quantified key metrics (e.g., serve dominance and player ability), and constructed the Momentum Evaluation Model to assess and predict trends in athlete momentum. By analyzing the main factors affecting momentum shifts, the model can predict the game's outcome more accurately. The study results show that momentum flows to the side of the more dominant player with different metrics. The model test shows that its prediction accuracy reaches more than 70%, which provides solid theoretical support for the tactical analysis of tennis matches and the optimization of athletes' on-court performances, as well as an effective guide for scientific, data-driven decision-making in tennis.
Downloads
References
[1] Claudino J G, Capanema D O, de Souza T V, et al. Current approaches to the use of artificial intelligence for injury risk assessment and performance prediction in team sports: a systematic review[J]. Sports medicine-open, 2019, 5: 1-12.
[2] Maszczyk A, Gołaś A, Pietraszewski P, et al. Application of neural and regression models in sports results prediction[J]. Procedia-Social and Behavioral Sciences, 2014, 117: 482-487.
[3] Loeffelholz, Bernard, Bednar, Earl, Bauer, Kenneth W. Predicting NBA Games Using Neural Networks[J], Journal of Quantitative Analysis in Sports, 2009, 5(1): 7.
[4] McCullagh J. Data mining in sport: A neural network approach[J]. International Journal of Sports Science and Engineering, 2010, 4(3): 131-138.
[5] Xiangwei X, Lijuan M, Jinling H, et al. The Correlation between Physical Exercise and Comprehensive Health of Chinese Graduate Students: An Empirical Research Based on BP Neural Networks[J]. Global Education [2024-11-08].
[6] Jie W. The Resource-based Research-training-learning Platform Construction of Sports Techniques and Tactics[J]. Journal of Shanghai University of Sport, 2018.
[7] LV X C, GU D Y, LIU X H, et al. Momentum prediction models of tennis match based on CatBoost regression and random forest algorithms [J]. Scientific Reports, 2024, 14(1).
[8] MEIER P, FLEPP R, RUEDISSER M, et al. Separating psychological momentum from strategic momentum: Evidence from men's professional tennis [J]. Journal of Economic Psychology, 2020, 78.
[9] DEPKEN C A, GANDAR J M, SHAPIRO D A. Set-level strategic and psychological momentum in best-of-three-set professional tennis matches [J]. Journal of Sports Economics, 2022, 23(5): 598-623.
[10] LEI Y L, LIN A, CAO J N. Rhythms of Victory: Predicting Professional Tennis Matches Using Machine Learning [J]. Ieee Access, 2024, 12: 113608-17.
[11] YU H, JIA L Y, MIAO Y M, et al. CLSTM: A Dynamic Model for Predicting Winning Percentages in Tennis Matches; proceedings of the 5th International Conference on Computing, Networks and Internet of Things (CNIOT), Tokyo, JAPAN, F May 24-26, 2024 [C]. 2024.
[12] LI X H, LIU C, ZHANG Y, et al. Momentum Prediction Model: Catch the Flow and Swing; proceedings of the International Conference on Modeling, Natural Language Processing and Machine Learning (CMNM), Xian, PEOPLES R CHINA, F May 17-19, 2024 [C]. 2024.
[13] LEI Y L, LIN A, CAO J N. Rhythms of Victory: Predicting Professional Tennis Matches Using Machine Learning [J]. Ieee Access, 2024, 12: 113608-17.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Highlights in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
