A Predictive Analysis of Triple Jump Outcomes Using Anthropometric and Biomechanical Profiles in Under-17 Male Athletes

Abstract

BACKROUND. The triple jump is a highly technical and physically demanding event in track and field athletics, where performance is strongly influenced by an athlete’s physical and biomechanical attributes.
AIM. This study presents a predictive analysis aimed at determining the relationship between anthropometric characteristics and triple jump performance in under-17 (U-17) male athletes.
METHODOLOGY. Anthropometric measurements such as height, leg length, arm span, body mass, and body mass index (BMI) were collected from a cohort of U-17 national-level athletes. Performance outcomes were recorded based on the combined distance of the hop, step, and jump phases. Using statistical correlation, multiple linear regression, and machine learning models including Support Vector Regression and Decision Tree Regression, we analysed how these physical attributes affect jump distance.
RESULTS. Results revealed that leg length, arm span, and height exhibited the strongest positive correlations with total jump distance, while BMI showed a moderate negative impact. The Support Vector Regression model achieved the highest predictive accuracy with an R² score of 0.87.
CONCLUSION. This research demonstrates the feasibility of using anthropometric profiles to predict athletic performance in youth triple jumpers and provides valuable insights for coaches, talent scouts, and sports scientists in optimizing training programs and early talent identification.