Learning Analytics in Islamic Religious Education: Predicting Students’ Learning Achievement through Educational Data Mining

Abstract

The increasing availability of educational data has opened new opportunities for improving instructional decision-making through learning analytics. However, its application in Islamic Religious Education (IRE) remains limited, particularly in predicting students’ academic achievement and learning behavior. This study aims to develop a learning analytics model capable of identifying learning patterns and predicting students’ performance in IRE. A quantitative research design employing Educational Data Mining (EDM) techniques was conducted using learning management system (LMS) data from 512 secondary school students. Data included attendance records, assignment completion, online participation, quiz scores, and learning engagement indicators. Machine learning algorithms, including Decision Tree, Random Forest, and Support Vector Machine, were employed to develop predictive models. The findings reveal that learning engagement, assignment consistency, and reflective participation significantly predict students’ academic achievement. Furthermore, predictive analytics enables teachers to identify at-risk learners early and provide personalized interventions to improve learning outcomes. The novelty of this study lies in proposing the Islamic Learning Analytics Framework, integrating educational data mining, predictive modeling, and Islamic pedagogical principles to support evidence-based instructional decision-making