- : Ms Word, Ms Word Format
- : 67 Pages
- : ₦5,000
- : 1-5 Chapters
- Click to DOWNLOAD Materials
The Design and Development of a Predictive Model to Determine Higher Education Students’ Academic Status Using Data Mining Technology
ABSTRACT
Currently, student attrition has become a widespread issue in higher education institutions. To address this problem and improve student retention, it is essential to grasp the underlying complexities causing student attrition. Private higher institution education (PHIE) is particularly impacted by a diverse range of factors, including demographic, social, economic, academic, and institutional aspects, which significantly influence student attrition and retention.
The primary aim of this study is to develop a predictive model using data mining technology to determine undergraduate students' likelihood of attrition or retention in higher education. The study follows a hybrid data mining process model, comprising six steps: problem understanding, data comprehension, data preparation, data mining, evaluation of discovered knowledge, and practical application of the findings.
Based on a thorough understanding of the problem, 15 attributes were selected, and 7361 instances were utilized for experimenting with the predictive model's design, capable of determining students' status. In this study, classification algorithms, including decision tree (J48), rule induction (PART and JRIP), and Bayes classifier (naïve Bayes), were employed during the model-building process. The classifier model was trained and tested using 10-fold cross-validation and a 66% split test option.
Among the four algorithms tested, the decision tree classifier (J48) demonstrated the highest accuracy, reaching 91.40%, followed by PART, JRIP, and naïve Bayes algorithms, respectively. The extracted hidden patterns using the J48 algorithm identified several major contributing factors behind student attrition and retention, including financial sources (self-sponsored, parent-sponsored, and scholarship), division (regular and extension), types of preparatory attended school (private and public), department (computer science, accounting, marketing management, hotel and tourism, and management), background of study (social and natural), and preparatory completion year (before 1994EC-2001EC and after 2002EC-2009EC).
One of the significant challenges faced during the study was merging data obtained from the student record management information system (SRMIS), as it was in two table formats. Furthermore, acquiring well-organized, accurate, and high-quality data for mining tasks posed difficulties. As a recommendation, educational institutions are advised to maintain their data symmetrically to facilitate data analyses.
The Design and Development of a Predictive Model to Determine Higher Education Students’ Academic Status Using Data Mining Technology, GET MORE COMPUTER SCIENCE PROJECT TOPICS AND MATERIALS
