Machine learning algorithms to optimize the training effect of table tennis players

Abstract

At present, the problem of lack of personalized and scientific training programs for traditional table tennis (TT) athletes is very prominent. This paper uses machine learning (ML) algorithms and support vector machine (SVM) algorithms to optimize the training effect of TT athletes using personalized data. First of all, it collected personalized data such as technical indicators, physical fitness, and training performance of TT players and can clean and normalize the collected data to prepare the data for the training of ML algorithms. Then, a SVM model suitable for the characteristics of TT training data was selected to build a predictive model of personalized training schemes, and then the SVM model was trained on the prepared data to establish the correlation between athletes’ training needs and performance. The experimental results show that the SVM model has a prediction accuracy of 88% and a recall rate of 91%, which indicates that the model has a good effect in the optimization of TT training effect. The significance of this study lies in that the application of SVM algorithm effectively optimizes the training effect of table tennis players and provides a reliable method for the implementation of personalized and scientific training programs.