Learning Analytics and Educational Data Mining: Transforming Student Success in Higher Education
DOI:
https://doi.org/10.63163/srh434Keywords:
Learning Analytics, Educational Data Mining, Student Success, Higher Education, Predictive Analytics, Personalized Learning, Artificial Intelligence in Education.Abstract
Digital learning environments have experienced exponential growth, resulting in an unprecedented amount of educational data that can be used to transform student success in higher education. This comprehensive review discusses the convergence of Learning Analytics (LA) and Educational Data Mining (EDM) as complementary techniques to understanding, predicting and improving student learning outcomes. In Higher Education, data analytics offers a particular promise in the domains of analysis, understanding and modelling of pedagogical processes, and methodologies can lead to the emergence of highly correlative terms like Learning Analytics, Academic Analytics and Educational Data Mining, where the result of one can feed into the next. This review aims to provide a synthesis of evidence on the applications, techniques, theory and empirical effects of these data-driven approaches by systematically analysing peer-reviewed literature published from 2020 to 2025. The key findings include that early warning systems, predictive analytics, and personalized learning interventions can have a significant impact on student retention, engagement, and achievement. Research shows that students who were exposed to AI-based adaptive feedback made a 28% increase in conceptual understanding, whereas the control group made a 14% increase; student engagement rose by 35%, and cognitive overload decreased by 22%. Nevertheless, there are significant challenges, such as digital divides, especially in developing nations, algorithmic bias, data privacy considerations and ethical governance. The review suggests an integrated LA-EDM approach to improving student success and pinpoints methodological, geographic and policy gaps that need further research. The synthesis offers practical guidance to educators, administrators, policymakers, and researchers looking to leverage data-driven practices without compromising ethical considerations and equity in education.
Downloads
Downloads
Published
Issue
Section
License
All articles published in The Study of Religion and History (SRH) are licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
This license permits unrestricted use, distribution, reproduction, and reuse in any medium, provided the original author(s) and the source are properly cited.



