The purpose of the study was to predict the success of a football team’s competitive season by integrating innovative technologies and data analysis. Data from Global Positioning System/Inertial Measurement Unit sensors (speed, distance, Player Load), smart balls (impact force, accuracy of passes), video analytics (positioning, group actions), wearable devices (heart rate variability, pulse), and external sources (Opta, Wyscout) were used. It was found that the accuracy of passes increased from 78% to 85%, the impact force – by 15% (from 80 N to 92 N), and the number of counterattacks increased by 30%. A correlation was found between a 10% decrease in heart rate variability and a 25% increase in the risk of injury (correlation coefficientr= 0.81). A 12% improvement in maximum oxygen consumption and a 20% reduction in joint load confirmed the effectiveness of training programmes. Based on the XGBoost machine learning algorithm, a predictive model was developed with an accuracy of 92%, which determined the probability of a team entering the top 3 of the leagues (68%) and relegation (12%). Analysis of the opponents’ weaknesses (60% of goals conceded through the flanks) allowed formulating tactical recommendations, in particular, an emphasis on flank attacks (an increase in efficiency by 25%). The results confirmed that integrating data from different sources is a key tool for improving team performance in competitions. Practical significance lies in optimising training by monitoring heart rate variability (reducing injuries by 20%) and adapting game strategies
Dmytro Zelenyi (Sun,) studied this question.