| Pub. Date | : April, 2021 |
|---|---|
| Product Name | : The IUP Journal of Computer Sciences |
| Product Type | : Article |
| Product Code | : IJCS30421 |
| Author Name | : Ogwueleka Francisca Nonyelum, Lydia Mohammed and Irhebhude Martins Ekata |
| Availability | : YES |
| Subject/Domain | : Management |
| Download Format | : PDF Format |
| No. of Pages | : 12 |
The performance of students is an aspect of principal importance to educational institutions, as it determines the ranking and continuity of academic programs offered. The paper investigates the performance of students in a polytechnic institution, Department of Nigerian Education. Different factors that affect the performance of students were identified and classified. The factors considered include: National Diploma (ND) grade, time elapsed before admission for Higher National Diploma (HND), age, marital status, gender, region of origin and Polytechnic attended for ND. The seven factors were categorized and used to develop the models for the analysis. Three hundred and thirty-four (334) student records, after preprocessing, were reduced to 261 and used for the study. The data was collected directly from the examination and record office of the department and analyzed using the WEKA data mining tool to determine which classification algorithm model performs best on the dataset. Out of the three classification algorithms used, Support Vector Machine (SVM), outperformed both neural network and K-nearest neighbor classifiers with accuracy of 97.7%, precision of 97.8%, recall of 97.7% and f-measure of 97.7%. A comparative analysis of the three algorithms using accuracy, precision and recall and f-measure was done.
Students' performance plays a very important role in any educational institution of learning. This is because one of the criteria for a high-quality institution is based on its excellent record of student academic achievement. Recent advancement in various
Student performance, Data Mining Technique, WEKA tool, Predictive model, Neural Network, Support Vector Machine (SVM), K-Nearest Neighbor (KNN)