A Data Warehousing Framework for Predictive Analytics in Higher Education: A Focus on Student at-Risk Identification

This paper will examine the development of a data warehouse aimed at improving decision-making in higher education, which focuses on the identification of students at-risk of academic failure through machine learning techniques. This research utilizes South East European University (SEEU) as a case study to show how data warehousing can integrate various student data—including demographics, academic performance, grades, attendance, and engagement—into an integrated framework that enables predictive analytics.

The overall approach allows SEEU decision-makers, administrators, and faculty to proactively identify and assist at-risk students, which improves student retention and their academic success. The results underscore the crucial role of data warehousing in enhancing student achievement and facilitating informed decision-making in higher education.

The paper concludes with concrete suggestions for leveraging data to enhance decision-making processes in a digital educational institution.