Fuzzy C4.5 Decision Tree Model for Effect Analysis and Optimization of College Physical Education Courses

In studying college physical education course effect analysis and optimization, the traditional C4.5 algorithm has weak processing capabilities for fuzzy data. It is prone to imprecise decision tree nodes and cannot effectively handle the complex relationship between multiple related features, resulting in the final course effect analysis and optimization suggestions lacking practical significance. This paper uses the improved fuzzy C4.5 algorithm to clean and standardize various data of college physical education courses and applies fuzzy logic to transform the data to ensure that precise data does not limit the comparison and processing between different features. The improved fuzzy C4.5 algorithm is used to construct the decision tree. Based on the fuzzy set theory, the uncertainty in the training data is modeled to enhance the accuracy of the decision tree nodes. When constructing the decision tree, the features of the physical education course are combined, and multiple features related to the course effect are selected. After obtaining the decision tree model, the influence of each feature on the course effect is analyzed, and specific optimization suggestions are put forward. Experimental results show that the prediction accuracy of the fuzzy C4.5 decision tree model in this paper is between 0.85 and 0.90 in the test set of 10 training, and it can effectively handle uncertain data. After evaluating the importance of the feature, endurance, strength, flexibility, speed, attendance and participation frequency are selected as key factors that significantly impact course effects. After course effect optimization, the proportions of students with excellent and good grades increase significantly to 18% and 32%, and those with average and poor grades decrease to 44% and 6%. These results show that course optimization measures effectively improve student’s performance.