Supervised Learning Evaluation Model of Students' Sports Training Efficiency Based on Random Forest Model

Abstract

Supervised learning algorithm is widely used in industry and manufacturing. For many years,
the effect evaluation of sports training only stays on the basis of qualitative experience. With the
advent of high-tech era, sports training is a complex system engineering, which has been
recognized by experts all over the world. Random forest has fast operation speed and excellent
performance in processing big data. The existing random forest software package gives the
importance of all variables. Motion analysis requires more and more quantitative analysis of the
factors that restrict the influence. In order to accurately quantify and achieve the purpose of
macro-control and micro analysis, this paper expounds the algorithm of supervised learning to
evaluate the efficiency of students' sports training. In view of the lack of operability of some
theories in the current research of sports training benefit evaluation, this paper discusses the
meaning of sports training benefit, the evaluation index system of competitive benefit, and the
lag of sports training "input" and "output". Based on the method of supervised learning, this
paper puts forward some ideas to solve the above problems. The experimental data show that
the model of evaluating the efficiency of students' sports training based on supervised learning
can improve the accuracy of the evaluation of the efficiency of sports training, and provide
some reference for guiding students' sports training.