Using Analytics to Uncover Early Determinants of Academic Performance for Adult Learners

Abstract

By and large, the arrival of the digital age have accelerated the development of analytics to guide data-informed efforts in teaching and learning. This has also transformed the way how higher education institutions look to optimize student success. In this study, through the use of data mining techniques, the UNIVERSITY* gained a better understanding of variables that influenced the adult learners first year academic performance. In particular, the results from the CHAID (or Chi-squared Automatic Interaction Detector) model highlighted the importance of previous academic performance and behavioural variables such as credit units taken and withdrawn in predicting learners at risk. The findings resonated with the opinion that an adult learner may find it challenging to juggle the demands of higher education, work-life, and family-life concurrently, at the onset. Henceforth, this group of struggling adult learners may benefit from a better management of course loading, as early as possible.



Author Information
Sylvia Chong, Singapore University of Social Sciences, Singapore
Yew Haur Lee, Singapore University of Social Sciences, Singapore

Paper Information
Conference: CHER-HongKong2019
Stream: Questing for innovation and entrepreneurship: Curriculum design and student learning

This paper is part of the CHER-HongKong2019 Conference Proceedings (View)
Full Paper
View / Download the full paper in a new tab/window

Posted by amp21