Predictive modeling of tennis matches: a review

Šarčević, Ana; Vranić, Mihaela; Pintar, Damir; Krajna, Agneza

doi:10.23919/mipro55190.2022.9803645

Cited by 6 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ana Šarčević [1] et al proposed a combinatorial approach in predicting the outcome of tennis matches. This article proposes a more efficient alternative, using a combination method that relies on the binomial distribution, which achieves the same accuracy as the recursive method.…”

Section: Introductionmentioning

confidence: 99%

Research on score prediction in sports competitions——based on PSO-BP neural network and ARIMAX hybrid prediction model

Shi

2024

HSET

View full text Add to dashboard Cite

Predicting match results has always been an important problem in the field of sports. Athletes and coaches can benefit from accurately predicting the path of a match, allowing them to strategize ahead of time and take control during the match. The PSO-BP neural network combines the advantages of particle swarm optimization and backpropagation neural networks to improve the accuracy of the model in processing complex nonlinear data interactions. ARIMAX is ideal for evaluating data that exhibits linear trends and seasonality. The model combines an autoregressive synthetic moving average component with external variables to account for linear trends, seasonality, and external influences in the data. Through the data in https://github.com/JeffSackmann/tennis_wta, this article establishes a combination of two models to predict game scores. Variables include advantage, turnover, lead, distance traveled, and serve. Using K-fold cross-validation, the accuracy rates of the PSO-BP neural network and ARIMAX prediction model were measured to be 82.89% and 80.12% respectively. Then bringing this model into the basketball game, we get its prediction accuracy: 77.12% and 76.21%. A random forest analysis method was used to evaluate the significance of each variable in prediction. The significance of each indicator is as follows: 0.33, 0.26, 0.17, 0.15 and 0.09.

show abstract

Section: Introductionmentioning

confidence: 99%

Research on score prediction in sports competitions——based on PSO-BP neural network and ARIMAX hybrid prediction model

Shi

2024

HSET

View full text Add to dashboard Cite

show abstract

“…Establishing a reliable competition prediction model requires comprehensive consideration of factors such as athlete history, opponent competition, and competition environment. Using machine learning algorithms combined with large amounts of data to train models can improve prediction accuracy [5] . This not only helps fans better understand the trend of the game, but also provides coaches with more tactics.…”

Section: Introductionmentioning

confidence: 99%

Evaluating the role of momentum in tennis based on neural network models

Zhang,

Dong,

Tang

2024

HSET

View full text Add to dashboard Cite

The research on the evaluation mechanism and prediction model of tennis player performance is of great significance and value for improving the quality of matches and cultivating excellent athletes. Firstly, by establishing a scientific and reasonable evaluation mechanism, the technical, physical, and psychological performance of athletes in competitions can be objectively analyzed, providing a basis for developing personalized training plans. Firstly, this article selects five parameters representing the stage performance status of athletes and extracts parameter data. Use clustering algorithm (K-means) to classify data. Based on the calculation of weights for different parameters, a score evaluation formula was established. It also provides indicators for the range of athlete evaluation scores, so that status data can be updated to obtain evaluation values at different times. It also provides a momentum evaluation score calculation function. Based on the calculation function, the total integrated momentum of 100 matches was simulated, combined with the logistic regression algorithm, and the results were compared. It has been found that the use of momentum accumulation evaluation mechanism can predict the success probability of players. Meanwhile, Monte Carlo simulation methods were used to simulate the number of player games under random probabilities. It was found that in 100 games, the performance of players fluctuated and contradicted the actual situation. Therefore, the momentum evaluation mechanism is of great significance for predicting the progress of athletes in competitions.

show abstract

“…Although machine learning has changed various aspects of sports science, including talent identification, injury prevention, match outcome prediction, and training optimization, its application in optimizing tennis performance remains an under-explored topic. While several systematic reviews have explored various applications of machine learning in tennis [29][30][31], a comprehensive understanding of how machine learning can be applied across various aspects of tennis performance is lacking in the literature. Therefore, the aims of this study are: (i) to comprehensively analyze machine learning applications in tennis performance, focusing on psychological and affective states, talent identification, match outcome prediction, spatial and tactical analysis, and injury prevention and training effects, and (ii) to provide practical insights for coaches, trainers, and athletes on how machine learning can be used to optimize training and enhance performance.…”

Section: Introductionmentioning

confidence: 99%

Applications of Machine Learning to Optimize Tennis Performance: A Systematic Review

Sampaio,

Oliveira,

Marinho

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

(1) Background: Tennis has changed toward power-driven gameplay, demanding a nuanced understanding of performance factors. This review explores the role of machine learning in enhancing tennis performance. (2) Methods: A systematic search identified articles utilizing machine learning in tennis performance analysis. (3) Results: Machine learning applications show promise in psychological state monitoring, talent identification, match outcome prediction, spatial and tactical analysis, and injury prevention. Coaches can leverage wearable technologies for personalized psychological state monitoring, data-driven talent identification, and tactical insights for informed decision-making. (4) Conclusions: Machine learning offers coaches insights to refine coaching methodologies and optimize player performance in tennis. By integrating these insights, coaches can adapt to the demands of the sport by improving the players’ outcomes. As technology progresses, continued exploration of machine learning’s potential in tennis is warranted for further advancements in performance optimization.

show abstract

Predictive modeling of tennis matches: a review

Cited by 6 publications

References 22 publications

Research on score prediction in sports competitions——based on PSO-BP neural network and ARIMAX hybrid prediction model

Research on score prediction in sports competitions——based on PSO-BP neural network and ARIMAX hybrid prediction model

Evaluating the role of momentum in tennis based on neural network models

Applications of Machine Learning to Optimize Tennis Performance: A Systematic Review

Contact Info

Product

Resources

About