Improving Random Forest Algorithm for University Academic Affairs Management System Platform Construction

Abstract

Using the data of students’ learning process recorded in the network teaching platform to predict students’ learning performance, assist teachers to analyze learning situation, formulate teaching strategies, and warn about students’ learning state is a hot spot in the field of mixed curriculum research in recent years. In view of the complexity, heterogeneity, and security of college educational administration data and the difficulty of predicting and analyzing college students’ achievements, this paper designs a college educational administration management system platform based on improved random forest algorithm. Combining the advantages of three data-driven prediction algorithms, namely, random forest, extreme gradient boosting (XGBoost), and gradient boosting decision tree (GBDT), a model based on improved random forest algorithm is proposed. It is proved that this method is a noninferior prediction method. Secondly, the model is applied to practical problems to solve the problem of predicting college students’ grades. An experiment is carried out on the real data set provided by a municipal education bureau. The results show that the proposed model not only achieves good prediction accuracy, but also solves the stability problem of the model after adding new data, which will contribute to the iterative optimization of the model, improve the universality of the model, and help continuously track the learning behavior characteristics of college students in different semesters.