Self-Converged Ensemble Deep RNN Classifier for Student Performance Prediction in Academics

Education institutes have been gaining major improvisation due to the establishment of virtual learning techniques which provide the pupils and staff with enormous information and knowledge that accessed from anywhere at any time virtually, which eventually. The virtual learning environment provides datasets for examining the learning methods of pupils and their evolution as well as their performance in academics. This paper proposed a Self-converged Ensemble Deep RNN Classifier that included an activation ensemble for the prediction and analysis of student performance and explores the moment to establish the relevant methods for student performance prediction by utilizing deep learning techniques. The proposed model self-converged ensemble deep learning RNN classifier, that enhances the MAE is 2.82, MSE is 12.07 and RMSE is 3.47 based on the mathematical dataset.