Student's Performance Evaluation Using Ensemble Machine Learning Algorithms

This study explores the critical domain of predicting students' academic performance in educational institutions. By harnessing the potential of machine learning algorithms, specifically Random Forest, KNN, and XGBoost, and leveraging data collected through technology-enhanced learning applications, the research aims to provide valuable insights into the factors influencing academic outcomes based on the dataset obtained from Kaggle. It is important to note that these models were also hybridized using the stacking ensemble approach. The performances of the algorithm were evaluated using the Root Mean Squared Error (RMSE), Mean Squared Error (MSE), Mean Absolute Error (MAE), and R-squared (R2) score. Resultively, the stacked ensemble model displayed remarkable results, with an impressively low RMSE of 0.1768, MSE of 0.0312, MAE of 0.1247, and a high R2-score of 0.9705. This finding showed that the Ensemble model, which combines the strengths of the Random Forest, KNN, and XGBoost algorithms, provides the best overall prediction accuracy, with a high degree of correlation between predicted and actual student performance.