AI-Enabled Quality Assurance in Madrasah: Reconfiguring Institutional Quality Management through Predictive Analytics

Abstract

This study aims to examine how AI-enabled predictive analytics can reconfigure institutional quality assurance in Islamic higher education and support proactive quality management. A qualitative case study design was employed to investigate how artificial intelligence, predictive indicators, and institutional quality practices are interpreted and implemented within a natural educational setting. The research was conducted at Madrasah Nurul Amin, selected because the institution provides a relevant context for examining digital transformation, quality assurance, and AI-supported management practices. Data were collected through semi-structured interviews, participant observation, and document analysis involving institutional leaders, quality assurance personnel, lecturers, and administrative staff. Data were analyzed through data condensation, data display, and verification. Findings indicate that AI-enabled quality assurance operates through data integration, predictive risk identification, human interpretation, targeted intervention, and continuous evaluation. The study concludes that predictive analytics can shift quality assurance from retrospective compliance toward proactive improvement, provided that models remain interpretable, ethical, and human-supervised. The implication is that Islamic higher education institutions need integrated data governance, AI literacy, ethical safeguards, and continuous quality-monitoring mechanisms.