Welcome to Francis Academic Press

Academic Journal of Computing & Information Science, 2024, 7(5); doi: 10.25236/AJCIS.2024.070520.

Momentum Study Based on CRNN Neural Network and Logistic Regression


Zehao Qu

Corresponding Author:
Zehao Qu

School of Computer and Communication, Lanzhou University of Technology, Lanzhou, China


This paper investigates the influence of momentum on the player's victory or defeat in tennis matches. Through the preprocessing and comprehensive analysis of the match data, the Topsis model based on the entropy weighting method was used to quantify the momentum index, and the visual analysis of the change of players' momentum was realized. Further, the strong correlation between the momentum and the player's score was verified by the Pearson correlation coefficient method. The correlation analysis and CRNN neural network model were utilized to successfully predict the momentum fluctuation, which was validated by logistic regression model with an accuracy of 78.4%. This study provides a reference for coaches to customize better tactics and important suggestions for improving players' competitive level and game performance. By deeply exploring the influencing factors and prediction model of momentum, this study provides new perspectives and methods for the analysis of sports game data and player training.


Topsis, CRNN Neural Networks, Logistic Regression

Cite This Paper

Zehao Qu. Momentum Study Based on CRNN Neural Network and Logistic Regression. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 5: 152-158. https://doi.org/10.25236/AJCIS.2024.070520.


[1] Hu Y, Wang Z, Li X. Impact of policies on electric vehicle diffusion: An evolutionary game of small world network analysis [J]. Journal of Cleaner Production, 2020, 265: 121703.

[2] Tian C, Song M, Tian J, et al. Evaluation of Air Combat Control Ability Based on Eye Movement Indicators and Combination Weighting GRA-TOPSIS[J]. Aerospace, 2023, 10(5): 437.

[3] Armstrong R A. Should Pearson's correlation coefficient be avoided? [J]. Ophthalmic and Physiological Optics, 2019, 39(5): 316-327.

[4] Fu X, Ch'ng E, Aickelin U, et al. CRNN: a joint neural network for redundancy detection[C]//2017 IEEE international conference on smart computing (SMARTCOMP). IEEE, 2017: 1-8.

[5] Landwehr N, Hall M, Frank E. Logistic model trees[J]. Machine learning, 2005, 59: 161-205.