Deep Neural Networks for Predicting Students' Performance

Abstract

Students are facing various difficulties in courses like Programming and Data Structure through undergraduate programs, which is why failure rates and dropouts in these courses are high. Identifying students at risk of failure at an early stage of a semester is a serious challenge in higher education, so predicting students' academic performance is one of the most essential research topics to reduce failure rates, and to improve the performance of students by the end of a semester. We are developing a predictive model based on a deep artificial neural network to predict students' academic performance of upcoming courses based on their grades in previous courses of the first academic year. We have used one of the most common resampling methods, which is the SMOTE approach to handle the problem of the imbalanced dataset. The preliminary results show that our proposed model has achieved 86% accuracy. To put our system in context, we compared our results to some traditional machine learning techniques such as Decision Tree, K-Nearest Neighbor, and Random Forest, which were applied to an online dataset that has been widely used in some previous works. The comparison showed that our experimental results have achieved better results than the other traditional models. In future work, we will use a larger dataset to improve the accuracy of our models. Using other oversampling techniques such as SVM-SMOTE and Random Over Sampler will be used to evaluate their performance in comparison to the algorithms used in our work.