Student Performance Prediction Using Stacking Ensemble Learning

Student grade prediction is an important research topic in educational data mining. To address the issues of low prediction accuracy and poor generalization encountered by single models in predicting student grades, this paper proposes a Stacking ensemble learning model that integrates multiple individual models. The proposed model uses Support Vector Machine (SVM), Decision Tree, and Random Forest as base learners, with Logistic Regression (LR) serving as the metalearner, forming a two-layer Stacking ensemble learning framework. The results demonstrate that the Stacking ensemble learning model achieves an accuracy of 91.6%, precision of 92.1%, recall of 93.8%, and an F1-score of 93.0%. These performance metrics are significantly better than those of individual learning models, indicating that the proposed Stacking model can effectively predict students' academic performance.