Research on Physical Fitness and Health Improvement Strategies for Youth Basketball Players Based on Big Data Analysis

This paper aims to address the limitations of the traditional K-mean clustering algorithm, which does not account for the influence of both extremely poor and excellent physical fitness classmates on abnormality detection and the issue of high false detection rate. It bases its approach on three abnormality detection methods: K-mean clustering, distance, and density. These methods are used to determine the physical fitness test data outlying index (PFT-OI) and identify abnormal data. We used this algorithm to conduct research on the physical health of youth basketball players from a big data perspective. The differences between the mean values of height, weight, and BMI pre- and post-test scores of adolescent basketball players before and after the experiment were not significant (P > 0.05). The p-values of the pre- and post-test scores of 50 meters, standing long jump, and 1000 meters of male athletes after the experiment were 0.000**, 0.005**, and 0.029*, respectively. The absolute values of the pre- and post-test scores of female athletes differed by 1.05 seconds, 0.2 meters, 5 meters, and 8.12 seconds, respectively, except for the pre- and post-test differences of seated forward bends, which were not significant (P < 0.05). In the teaching of basketball, male adolescent basketball players can focus on practicing the 50-meter run and standing long jump and, at the same time, controlling body weight in order to maximize the possibility of achieving an excellent overall assessment score. Female athletes should prioritize 50 meters, 800 meters, and the standing long jump in their daily training regimen.