Employing Deep Neural Network for Early Prediction of Students’ Performance

Educational institutions aim to deliver quality education and motivate students to perform better in academic examinations. The early prediction of students’ performance helps to identify the low-performing students who may fail in exams, thus allowing institutions to help such students for performing better. Traditional machine learning methods utilize the academic attributes of students to predict their academic performance. Accuracy in the prediction of students’ performance is very crucial. This article employs deep neural network (DNN), a contemporary technique of deep learning, to predict students’ academic performance. The dataset utilized for prediction is prepared with the academic attributes of students. Comparison has been made with prominent machine learning methods, viz. support vector machine (SVM), naive Bayes (NB), k-nearest neighbors (kNN), decision trees (DT), random forest (RF), and artificial neural networks (ANN). The results show that the proposed model obtains 98% accuracy, which is better than the accuracy of the other compared methods.