Low-Code Automation for Scalable, Bespoke Interventions in Private Higher Education

Abstract

Modern higher education institutions are rich in student performance data, yet a persistent action gap remains between identifying at-risk students and delivering timely, bespoke support. This paper presents an operational case study from a private higher education institution that bridged this threshold by pairing Microsoft Power BI with Power Automate. Rather than merely flagging at-risk cohorts, this system transforms post-assessment data into immediate operational workflows. Using multi-layered criteria, such as failing module sub-minimums or tracking within 10% of exam exclusion thresholds after the initial assessment, the architecture generates customized, actionable intelligence. It automatically alerts lecturers regarding polar-performing cohorts, updates academic heads on course delivery health while accounting for staff-to-student volumes and content difficulty and directly issues targeted intervention invitations to students. Crucially, this low-code infrastructure alleviates the administrative burden on academic operations, providing a sustainable, scalable roadmap for improving core cohort throughput rates without worsening faculty burnout.