IZUNWANNE, NELSON CHISOM (2026) PREDICTING STUDENT ACADEMIC OUTCOMES USING MACHINE LEARNING. Other thesis, GODFREY OKOYE UNIVERSITY, ENUGU.
![[img]](https://eprints.gouni.edu.ng/style/images/fileicons/text.png) |
Text
CORRECTED_PROJECT__2_.pdf Download (3MB) |
Abstract
A dropout prediction system is a data-driven tool that uses machine learning algorithms to analyze student data and classify whether a student is likely to complete their academic programme or leave before graduation. In the context of Nigerian higher education, where manual monitoring lacks predictive capability, this study developed a predictive analytics system for final-year Computer Science students at Godfrey Okoye University. The study employed a CRISP-DM approach to examine 3,630 student records with 37 features covering academic, demographic and lifestyle details. The Decision Tree Classifier performed best in terms of accuracy (94.21%), recall (100.00%) and F1-Score (92.95%) among the five classification algorithms tested. The trained model was deployed as a batch and interactive Streamlit web application, which provides visual analytics and compares model performance. Finally, this system gives administrators an efficient and data-based resource to proactively identify students at risk and take effective retention measures.
| Item Type: | Thesis (Other) |
|---|---|
| Subjects: | H Social Sciences > H Social Sciences (General) |
| Divisions: | Faculty of Computing And Information Technology (FACIT) |
| Depositing User: | CHIBUEZE EZE |
| Date Deposited: | 27 Jul 2026 12:46 |
| Last Modified: | 27 Jul 2026 12:46 |
| URI: | http://eprints.gouni.edu.ng/id/eprint/6042 |
Actions (login required)
 |
View Item |
