This paper focuses on a model that can capture match points in real time, record the scoring flow during the match, and determine the highlight moment of each player in real time. We apply this model to one or more competitions to better optimize the model by varying the proportion of weight factors and introducing more complex factors to adjust the value of momentum. Statistical distribution fitting as well as the Pearson correlation coefficient were used to assess the correlation between player momentum and match outcome, thus assessing the stochasticity of the transition between momentum and match situations. Using the random forest distribution algorithm to predict the turning point and evaluate the generalizability of the model gives a reasonable scheme. This article constructs two mathematical models for calculating momentum: a basic model and an optimized and improved model, to obtain the relationship between score and momentum in the game. In the basic model, this article sets up a function model to solve the problem under hypothetical conditions. Introduce weight parameters to adjust the degree of impact of winning or losing on momentum. But there are more complex factors, so we changed the function model to a state space model.

Xiaoqi Yu, Min Yu, Xinping Liu, Rong Guo. Research on the Role of Predicting Momentum in Competition Based on Random Forest Algorithm. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 6: 58-64. https://doi.org/10.25236/AJCIS.2024.070609.

[1] Shou Kui, Sun Xijing, mathematical modeling algorithm and application [M]. Beijing: National Defense Industry Press, 2021.

[2] Hu Xiaodong, Dong Chenhui, METLAB from entry to mastery [M]. Beijing: People's Posts and Telecommunications Press, 2018.

[3] Wu Xingyong. The Application of Artificial Intelligence in Computer Network Technology in the Era of Big Data [J]. Information and Computer (Theoretical Edition), 2023,35 (22): 167-169

[4] Shuai Anqi. Social Media Data Analysis: Integration of Internet and Big Data [J]. Internet Weekly, 2024 (05): 37-39

[5] Shi Zhilong, Chen Gan, Xie Guoliang. Research on an edge cloud big data analysis algorithm based on Spark [J]. Changjiang Information and Communication, 2024, 37 (02): 183-185. 

[6] Du Jiang, Dai Jun, Cao Ruiyuan. Optimization and Design of Practical Teaching System for Statistics in the Context of Artificial Intelligence and Digital Technology [J]. Journal of Higher Education, 2024, 10 (09): 115-118. 

[7] Chen Mengna, strengthen the application of artificial intelligence and big data technology in the "champion model" scenario [J]. Shanghai Securities News, 2024,08 (3):78-79

[8] Morgulev E , Azar O H , Galily Y ,et al.The role of initial success in competition: An analysis of early lead effects in NBA overtimes[J].Journal of Behavioral and Experimental Economics (formerly The Journal of Socio-Economics), 2020, 89.DOI:10.1016/j.socec.2020.101547.

[9] Abdoh H , Varela O .Competition and exposure of returns to the C-CAPM[J].Studies in Economics and Finance, 2018, 35(4):525-541.DOI:10.1108/SEF-02-2018-0038.

[10] Yue Feng, the role of psychological quality in tennis competition [J]. Tennis world. 2024(01):58-60