Predicting Student Academic Performance Using Artificial Neural Network.
Loading...
Date
2021-03-23
Journal Title
Journal ISSN
Volume Title
Publisher
LASU Journal of Research and Review in Science. 8(1): 1-7. Published by Lagos State University.
Abstract
Abstract
Introduction: 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.
Aim: This study aims to accurately predict and identify student
academic performance using an Artificial Neural Network in
educational institutions.
Materials and Methods: Artificial Neural network was employed to
compute the performance procedure over the MATLAB simulation
tool. The performance of the 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.
Results: Findings revealed that the Neural network has the highest
prediction accuracy by (98%) followed by the decision tree by (91%).
Support vector machine and k-nearest neighbor had the same
accuracy (83%), while naive Bayes gave lower prediction accuracy
(76%).
Conclusion: This work has helped to analyze the capabilities of an
Artificial Neural Network in the accurate prediction of students’
academic performance using Regression and feed-forward neural
network (FFNN) as evaluation metrics.
Description
Keywords
Citation
Olaniyan, O. M., Oloyede, A. O., Aremu, I. A., Babatunde, R. S., and Adeyemi, B.M. (2021)