A Learning Fuzzy Cognitive Map (LFCM) Approach to Predict Student Performance

Aim/Purpose: This research aims to present a brand-new approach for student performance prediction using the Learning Fuzzy Cognitive Map (LFCM) approach. Background: Predicting academic has long been an important topic in many disciplines. Different mathematical models have employed predict performance. Although available sets of common approaches, such as Artificial Neural Networks (ANN) and regression, work well with large datasets, they face challenges dealing small sample sizes, limiting their practical applications real practices. Methodology: Six distinct categories antecedents are adopted here course characteristics, LMS engagement, support, institutional factors, along measurement items within each category. Furthermore, we assessed student’s overall three satisfaction score, knowledge construction level, GPA. We collected longitudinal data from 30 postgraduates four subsequent semesters analyzed technique. Contribution: proposes brand new approach, (LFCM), Using this identified most influential determinants performance, engagement. Besides, depicts model interrelations among determinants. Findings: The results suggest that reasonably predicts incoming sequence when there is limited size. also reveal students’ total online time regularity learning interval largest effect on engagement category highest direct Recommendations Practitioners: Academic institutions can use developed paper identify antecedents, establish action plans resolve shortcomings term. Instructors adjust methods based feedback students short run operational level. Recommendation Researchers: Researchers proposed deal problems other domains, organizational/institutional education. focus specific dimensions model, exploring ways boost process. Impact Society: Our revealed at center degree which dedicated crucial determinant outcome. Therefore, learners should consider finding order gain value Future Research: As potential future works, could be used contexts test its applicability. studies improve level LFMC by tuning model’s elements.