Visualizing the momentum of tennis matches based on prediction and evaluation models

Jingyi Tang; Shijie Wu; Junjie Zhan; Shiming Chen; Zhiwei Xiong

doi:10.1117/12.3035394

21 July 2024 Visualizing the momentum of tennis matches based on prediction and evaluation models

Jingyi Tang, Shijie Wu, Junjie Zhan, Shiming Chen, Zhiwei Xiong

Proceedings Volume 13219, Fourth International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2024); 132192K (2024) https://doi.org/10.1117/12.3035394
Event: 4th International Conference on Applied Mathematics, Modelling and Intelligent Computing (CAMMIC 2024), 2024, Kaifeng, China

Abstract

Tennis, more than any other sport, is a game of Momentum. The absence of a clock to do the dirty work of finishing off an opponent, and a scoring system based on units used, makes the flow of the match much more important than any lead that has been established. In this study, we have developed Markov Chain model to predict the flow of play, Random Forest model to assess the impact of momentum changes on match outcomes. By comparison with XG-Boost, and LGBM, which achieves the accuracy of 0.6231 and 0.7061, we find that Random Forest achieves the highest accuracy of 0.8572 and passes the Monte Carlo test with a p-value of 0.048, rejecting the null hypothesis that momentum is unrelated to match outcomes.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Jingyi Tang, Shijie Wu, Junjie Zhan, Shiming Chen, and Zhiwei Xiong "Visualizing the momentum of tennis matches based on prediction and evaluation models", Proc. SPIE 13219, Fourth International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2024), 132192K (21 July 2024); https://doi.org/10.1117/12.3035394

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available