Evaluating the Efficiency of Student Sports Training Based on Supervised Learning

Abstract

The empirical evaluation of the success of a participant is critical for a thorough assessment of sporting events. Evaluating students' efficiency or scripting in sports is limited, even if skilled experts do it. In this paper, support vector machine-assisted sports training (SVMST) has been proposed to evaluate student sports efficiency. Sports training prototypes are based on different criteria that participate in the matches, traditional game statistics, person quality measures, and opposing data. The success of students is divided into two grades: moderate and large. The primarily supervised learning-based classification method is used to create a template for identifying student sports training efficiency. SVM implements learning methods, data collection methods, effective model assessment methods, and particular difficulties in predicting sports performance. The experimental results show SVMST to high student performance of 98.7%, a low error rate of 9.8%, enhanced assessment ratio of 97.6%, training outcome of 95.6%, and an efficiency ratio of 96.8%.