PREDICTING STUDENT ACADEMIC PERFORMANCE USING ARTIFICIAL NEURAL NETWORK
Predicting student academic performance plays an important role in academics. Classifying students using conventional techniques cannot give the desired level of accuracy, while doing it with the use of soft computing techniques may prove to be beneficial. Accurate prediction and early identification of student at-risk are of high concern for educational institutions. Artificial Neural network was employed to complete the performance procedure over MATLAB simulation tool. The performance of Neural Network was evaluated by accuracy and Mean Square Error (MSE). This tool has a simple interface and can be used by an educator for classifying students and distinguishing students with low achievements or at-risk students who are likely to have low performance. Findings revealed that Neural network has the highest prediction accuracy by (98%) followed by decision tree by (91%). Support vector machine and k-nearest neighbor had the same accuracy (83%), while naive Bayes gave lower prediction accuracy (76%).
MATLAB, Artificial Neural Network, and K-nearest neighbor