Evaluation of training effect and competitive level of track and field athletes based on big data analysis

The purpose of this paper is to explore the use of big data analysis methods and techniques to collect, integrate, process, analyze and visualize the training data and competition data of track and field athletes, and extract valuable information and knowledge from them, so as to provide a scientific basis and guidance for the assessment and improvement of the training effect and competitive level of track and field athletes. In this paper, 20 athletes from the Chinese national track and field team are selected as the experimental subjects, divided into two phases: baseline test and intervention test, collecting and analyzing the data of athletes’ physical fitness, technique, training and competition, respectively, and constructing prediction models using machine learning algorithms to assess and optimize the training effect and competitive level of athletes. The experimental results show that the assessment model of training effect and competitive level of track and field athletes based on big data analysis has a significant effect on the physical fitness, technique, training, and competition of the experimental subjects, and all of them have significant differences compared with the baseline test. This study confirms the validity and applicability of the training effect and competitive level assessment model of track and field athletes based on big data analysis, which provides scientific data support and guidance for the training and competition of track and field athletes, and contributes to the scientific development and level improvement of track and field sports.