Olabanjo, O.A.; Wusu, A.S.; Manuel, M. A Machine Learning Prediction of Academic Performance of Secondary School Students Using Radial Basis Function Neural Network. Trends in Neuroscience and Education 2022, 29, 100190, doi:10.1016/j.tine.2022.100190.
Olabanjo, O.A.; Wusu, A.S.; Manuel, M. A Machine Learning Prediction of Academic Performance of Secondary School Students Using Radial Basis Function Neural Network. Trends in Neuroscience and Education 2022, 29, 100190, doi:10.1016/j.tine.2022.100190.
Olabanjo, O.A.; Wusu, A.S.; Manuel, M. A Machine Learning Prediction of Academic Performance of Secondary School Students Using Radial Basis Function Neural Network. Trends in Neuroscience and Education 2022, 29, 100190, doi:10.1016/j.tine.2022.100190.
Olabanjo, O.A.; Wusu, A.S.; Manuel, M. A Machine Learning Prediction of Academic Performance of Secondary School Students Using Radial Basis Function Neural Network. Trends in Neuroscience and Education 2022, 29, 100190, doi:10.1016/j.tine.2022.100190.
Abstract
Introduction: Academic success is primary goal of every student. It is described as the extent to which a student has successfully achieved his or her short and long-term educational goals. Several factors have been established to predict academic performance of students. Machine learning techniques have been employed in predicting students’ performance, but it has not been prevalent in developing countries like Nigeria and most studies did not consider class teachers’ end-of-the-year rating. Aim: The aim of this work is to develop a Radial Basis Function Neural Network (RBFNN) for prediction of secondary school students’ performance. Materials and Methods: We obtained data from school repository containing students’ raw score and classteachers’ rating from year one to year six. The data was labelled into pass or fail given the actual outcome of their examinations. Subjects were categorized into Mathematics, English and major, depending on the student’s specialization. Class-teachers’ ratings were also included in the dataset. The preprocessed dataset was used to train the RBFNN model. The impact of Principal Component Analysis (PCA) was also measured. Results: We set up four experiments in order to achieve our aim. The best result gave the sensitivity of 93.49%, specificity of 75%, accuracy of 86.59% and an AUC score of 94%. Other experiments gave a relatively low performance. Conclusion: This study helps students to get a projection of academic success even before sitting for the examination. This will also help parents and counsellors in knowing the direction of their counseling to each student. Teachers and parents should pay attention to class teacher ratings of the students as this is discovered to affect the prediction accuracy of their examination success.
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.