Research on Predicting the Winning Rate of Momentum Tennis Athletes

Authors

  • Jie He
  • Chengjie Yang
  • Mingcheng Cai

DOI:

https://doi.org/10.54097/81wj0761

Keywords:

Momentum Quantification, Permutation Test, Correlation Analysis, Decision Tree.

Abstract

In tennis, "momentum" usually refers to the momentum or trend formed by a series of events (such as consecutive scoring) in a game, which can have a significant impact on the outcome of the game. After gaining motivation, players or teams often exhibit higher morale and confidence, and are more likely to win consecutive points or games. Specifically, momentum may be reflected in indicators such as continuous scores and break points. In a game, the server is usually more likely to win points, so evaluating momentum requires considering the influence of various factors. The paper believe that athletes are primarily influenced by the psychological impact of momentum, but psychological factors are also an abstract concept. Therefore, the paper have turned our attention to the various behaviors of athletes on the field. Therefore, the paper used five indicators to quantify the momentum score of athletes. To address the coach's concerns, the paper use random testing and correlation analysis to verify the statistical significance of attempting to score and win games, rather than random events. This article uses learning algorithms such as decision tree models to predict the value of target variables at turning points based on feature data. Analyze the contribution of each feature to advantage transformation and ultimately identify the relevant factors that affect advantage transformation.

Downloads

Download data is not yet available.

References

[1] Dietl H M, Nesseler c. Momentum in tennis: Controlling the match [J]. international journal of sport psychology, 2017, 48(4): 459-471.

[2] Briki w. Rethinking the relationship between momentum and sport performance: Toward an integrative perspective [J]. psychology of sport and exercise, 2017, 30: 38-44.

[3] Kim I, Neykov M, Balakrishnan S,Wasserman L.local permutation tests for conditional independence [J]. annals of statistics, 2023, 50(6): 3388-3414.

[4] Hemerik J, Thoresen M,Finos L.Permutation testing in high-dimensional linear models: an empirical investigation [J]. journal of statistical computation and simulation, 2021, 91(5): 897-914.

[5] Dehghan S. Permutation tests of multivariate location using data depth [J]. journal of statistical computation and simulation, 2024.

[6] Johnson E N, Richter S J .Permutation tests for mixed paired and two-sample designs[J]. computational statistics, 2022,37(2):739-750.

[7] Toth D. A permutation test on complex sample data [J]. journal of survey statistics and methodology, 2020, 8(4): 772-791.

[8] Hu J,Chen Y, Leng C L, Tang C Y. Applied regression analysis of correlations for correlated data [J]. annals of applied statistics, 2024, 18(1): 184-198.

[9] Lipovetsky s. Canonical concordance correlation analysis [J]. mathematics, 2023, 11(1).

[10] Lu H F, Ma X, Hybrid decision tree-based machine learning models for short-term water quality prediction [J]. chemosphere, 2020, (249).

Downloads

Published

28-10-2024