Current stance on predictive analytics in higher education: opportunities, challenges and future directions

ABSTRACT

Predictive models on students’ academic performance can be built by using historical data for modelling students’ learning behaviour. Such models can be employed in educational settings to determine how new students will perform and in predicting whether these students should be classed as at-risk of failing a course. Stakeholders can use predictive models to detect learning difficulties faced by students and thereby plan effective interventions to support students. In this paper, we present a systematic literature review on how predictive analytics have been applied in the higher education domain. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, we conducted a literature search from 2008 to 2018 and explored current trends in building data-driven predictive models to gauge students’ performance. Machine learning techniques and strategies used to build predictive models in prior studies are discussed. Furthermore, limitations encountered in interpreting data are stated and future research directions proposed.

KEYWORDS:

• Early alert system
• e-learning
• data mining
• drop-out prediction
• learning management system
• literature review
• performance prediction
• predictive analytic

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Rahila Umer

Rahila Umer is a graduate from the University of Georgia, America. She is currently a Ph. D candidate at Massey University, Auckland, New Zealand. Her research interest is in the area of data mining, process mining and machine learning. Rahila can be contacted at [email protected]

Teo Susnjak

Dr Teo Susnjak is a senior lecturer in information technology in the Institute of Natural and Mathematical Sciences at Massey University, Auckland, New Zealand. His research interests include Data science, machine learning, data mining, pattern recognition, artificial intelligence, expert systems, decision support systems, software engineering.

Anuradha Mathrani

Dr Anuradha Mathrani is a senior lecturer in information technology in the Institute of Natural and Mathematical Sciences at Massey University, Auckland, New Zealand. Her research interests include software quality and reliability measurements, distributed software architectures, application lifecycle management, technology-enhanced teaching/learning practices and e-commerce governance methods. Anuradha can be contacted at [email protected].

Lim Suriadi

Dr Suriadi Lim is a senior lecturer at Queensland University of Technology. From 2014 to 2016, he was Lecturer at the College of Sciences of Massey University, New Zealand. He obtained his PhD degree in the discipline of Information Security in late 2010 from the Queensland University of technology (QUT). Since 2007, he has been involved in a number of research projects in the area of information security. From 2011 to late 2014, he was Research Fellow within the Business Process Management discipline at Queensland University of Technology Brisbane, Australia. He enjoys working in collaborative, cross-domain research projects that allow the application of research outcomes to address real-world problems. His main research interests are in the area of process mining, data analytics and information security.