A Study of Momentum in Tennis Based on Multiscale Momentum-Success Test Model and Swings Prediction Model

Authors

  • Yiyi Lin
  • Yuhang Xiang
  • Yuhan Huang

DOI:

https://doi.org/10.62051/0maem067

Keywords:

Tennis; Momentum; Swing; SVM; FNN.

Abstract

In tennis, "momentum" is one of the most important factors affecting the results of the game. First, this paper establishes the Multiscale Momentum-Success Test Model and calculates the proportion of the winning side’s momentum at four different scales (score, game, set and match). The proportions of the four scales are 70.3%,78.1%,84.6%,93.5%. Therefore, it can be proved that momentum plays a role in the game. Also, the fluctuation and success in the game are not random. Afterward, this paper establishes the Support Vector Machine Model (SVM) and the Feed-Forward Neural Network Model (FNN). Three correlations are analyzed for factors such as scoring ratio, serve, consecutive scores (lost points), highlight scores, major lost points, and physical condition. It is concluded that the serve, consecutive scores (lost points), highlight scores, and major lost points will play a role in the occurrence of Swing Points. By the two models, we create the Swings Prediction Model. The prediction accuracy of SVM and FNN Model are 84.85% and 67.4%. Finally, based on the momentum changes, match suggestions can be made for the coaches.

Downloads

Download data is not yet available.

References

[1] Dietl H, Nesseler C. Momentum in tennis: Controlling the match [J]. UZH Business Working Paper Series, 2017 (365).

[2] Richardson P A, Adler W, Hankes D. Game, set, match: Psychological momentum in tennis [J]. The Sport Psychologist, 1988, 2 (1): 69 - 76. DOI: https://doi.org/10.1123/tsp.2.1.69

[3] Yu H, Hutson A D. Inferential procedure based on the weighted Pearson correlation coefficient test statistic[J]. Journal of Applied Statistics, 2024, 51 (3): 481 - 496.

[4] Ali Abd Al-Hameed K. Spearman's correlation coefficient in statistical analysis [J]. International Journal of Nonlinear Analysis and Applications, 2022, 13 (1): 3249 - 3255.

[5] SHAQIRI M, ILJAZI T, KAMBERI L, et al. DIFFERENCES BETWEEN THE CORRELATION COEFFICIENTS PEARSON, KENDALL AND SPEARMAN [J]. Journal of Natural Sciences and Mathematics of UT, 2023, 8 (15-16): 392 - 397.

[6] Badillo S, Banfai B, Birzele F, et al. An introduction to machine learning [J]. Clinical pharmacology & therapeutics, 2020, 107 (4): 871 - 885. DOI: https://doi.org/10.1002/cpt.1796

[7] Mathew A, Amudha P, Sivakumari S. Deep learning techniques: an overview [J]. Advanced Machine Learning Technologies and Applications: Proceedings of AMLTA 2020, 2021: 599 - 608. DOI: https://doi.org/10.1007/978-981-15-3383-9_54

[8] Cervantes J, Garcia-Lamont F, Rodríguez-Mazahua L, et al. A comprehensive survey on support vector machine classification: Applications, challenges and trends [J]. Neurocomputing, 2020, 408: 189 - 215. DOI: https://doi.org/10.1016/j.neucom.2019.10.118

[9] Yu H, Hutson A D. Inferential procedure based on the weighted Pearson correlation coefficient test statistic [J]. Journal of Applied Statistics, 2024, 51 (3): 481 - 496. DOI: https://doi.org/10.1080/02664763.2022.2137477

[10] DOĞAN İ, REVAN S, ARIKAN Ş. Analysis of tennis competitions on different court surfaces [J]. Turkish Journal of Sport and Exercise, 2021, 23 (1): 60 - 66.

Downloads

Published

12-08-2024

How to Cite

Lin, Y., Xiang, Y. and Huang, Y. (2024) “A Study of Momentum in Tennis Based on Multiscale Momentum-Success Test Model and Swings Prediction Model”, Transactions on Computer Science and Intelligent Systems Research, 5, pp. 1095–1102. doi:10.62051/0maem067.