THE ROLE OF SPORTS DATA ANALYSIS USING PYTHON IN IMPROVING THE PHYSICAL PERFORMANCE OF UNDER-20 SOCCER PLAYERS

Povzetek

This study aims to highlight the role of sports data analysis using the Python language in improving the physical performance of under-20 football players. It relies on modern statistical methods and predictive models. The study adopts an applied quantitative approach, where quantitative data were collected from a sample of players, then processed and analyzed using Python through a set of statistical libraries and machine learning algorithms, such as linear regression and the random forest model, The analysis process involved multiple stages, starting from data cleaning and exploratory data analysis, to building predictive models and evaluating them using statistical indicators such as the coefficient of determination (R²) and the root mean square error (RMSE). The results of the study showed a statistically significant relationship between physical variables and overall performance. Endurance and muscular strength were found to be among the most influential factors in improving performance, while speed and agility showed an inverse relationship due to the nature of their time-based measurement. The findings also demonstrated the effectiveness of predictive models, particularly the linear regression model, which achieved high accuracy in explaining and predicting physical performance. The study concluded that employing data analysis techniques using Python represents an effective tool for transitioning from traditional evaluation to predictive analysis, thereby contributing to improving the quality of training decision-making and enhancing players’ physical performance based on precise scientific foundations.