AKINODE, J.L and BADA, O (2021) STUDENT ENROLLMENT PREDICTION USING MACHINE LEARNING TECHNIQUES. In: Presented at the 5th National Conference of the School of Pure & Applied Sciences Federal Polytechnic Ilaro held between 29 and 30th September, 2021. Theme: Food Security and Safety: A Foothold for Development of Sustainable Economy in Nigeria, 29th – 30th September, 2021, The Federal Polytechnic, Ilaro.
![[img]](http://eprints.federalpolyilaro.edu.ng/style/images/fileicons/text.png) |
Text
SPA_21_067.pdf Download (471kB) |
Abstract
Higher Institutions of learning are constantly looking for factors that maximize enrollment of students in their citadel of learning. These factors provide academic management, information on the applicants that will likely enroll at their institutions. This paper explores the effect of the various pre-admission factors (WAEC grades, JAMB Scores etc.), that may influence the enrollment of student in a Federal Polytechnic in South west Nigeria. The research employed the field survey approach. A data set of 560 students enrolled in various courses at a Federal Polytechnic in South-West Nigeria from 2017 to 2018 was used to validate the proposed methodology The study adopts Machine learning methods to analyse the correlation of different factors on student’s enrolment. Decision tree algorithm (ID3) and support vector machine (SVM) techniques were used for the analysis. The pre-processing, processing and experimenting was conducted using Scikit-learn tool. Results obtained by comparing ID3 Decision Algorithm with other ML Algorithms such as Artificial Neural Network, Logistics Regression shows that ID3 algorithm outperforms other ML Algorithms. The Decision Tree has the highest accuracy of 97% while SVM, KNN and Naïve Bayes has an accuracy of 95%, 85% and 88% respectively. The results demonstrate that applicants’ suitability for admission can be predicted based on certain pre-admission criteria (high school grade average (WAEC and NECO) and JAMB Scores). This study will help academic administrators in higher institutions of learning in admissions decision making.
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software |
| Divisions: | Faculty of Engineering, Science and Mathematics > School of Electronics and Computer Science |
| Depositing User: | Mr. Bolanle Yisau I. |
| Date Deposited: | 02 Mar 2022 11:16 |
| Last Modified: | 02 Mar 2022 11:16 |
| URI: | http://eprints.federalpolyilaro.edu.ng/id/eprint/1972 |
Actions (login required)
 |
View Item |
