Visual analytic of UMP attrition

The increasing pattern of student enrollment at University Malaysia Pahang (UMP) due to more programs have been offered as well as increasing number of causing the increasing number of students attrition. To respond with Malaysia Higher Education Blueprint, UMP need to provide more access to higher...

Full description

Bibliographic Details
Main Author: Nur Alnisa’ Anis Alanna, Ruzelan
Format: Undergraduates Project Papers
Language:English
Published: 2019
Subjects:
Online Access:http://umpir.ump.edu.my/id/eprint/26960/
http://umpir.ump.edu.my/id/eprint/26960/
http://umpir.ump.edu.my/id/eprint/26960/1/Visual%20analytic%20of%20UMP.pdf
Description
Summary:The increasing pattern of student enrollment at University Malaysia Pahang (UMP) due to more programs have been offered as well as increasing number of causing the increasing number of students attrition. To respond with Malaysia Higher Education Blueprint, UMP need to provide more access to higher education and more new programs need to be offered to embrace a new digital economy. To do so, smarter approach with the use of data analytics is a must in managing student attrition cases. Therefore, this study aims to investigate the academic factors based on the standard Program Learning Outcomes (PLO) that highly influence or affecting the attrition cases. By using simple linear regression, analysis of the correlation between Cumulative Grade Point Average (CGPA) and its performance pattern against eight program learning outcomes were measured by calculating Pearson correlation coefficient of the attrition case specifically of the dropout student. The value of all eight program outcomes were standardized with standard scale between 0-1 by calculating the ration between the total marks awarded against the total of full mark of each program learning outcomes. The findings from the analysis show there are strong positive correlation between CGPA and PLO. This study shows there is possibility how risky students can be properly monitored by developing predictive model based on program learning outcomes performances.