Hybrid ML–Fuzzy Systems for Student Academic Performance Prediction

View at publisher Summarise with VIRAT
Authors: R. Saraswathy, Shaik Balkhis Banu
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Rapid expansion of digital learning environments and academic information systems has generated large volumes of educational data that create new opportunities for intelligent academic analytics and data-driven decision making. Accurate prediction of student academic performance plays a crucial role in identifying learning difficulties, supporting early intervention strategies, and improving overall educational outcomes. Conventional machine learning approaches demonstrate strong capability in discovering complex patterns within educational datasets, yet limited interpretability and difficulty in managing uncertain or linguistic educational variables reduce practical effectiveness in academic decision-support environments. Fuzzy logic reasoning provides a complementary analytical framework through linguistic rule representation and the ability to model imprecise educational attributes such as learning engagement, participation intensity, and study consistency. Integration of machine learning techniques with fuzzy inference mechanisms forms hybrid intelligent systems capable of combining predictive accuracy with transparent reasoning. This book chapter presents a comprehensive exploration of hybrid machine learning–fuzzy systems for student academic performance prediction within modern educational analytics frameworks. Fundamental concepts of machine learning and fuzzy reasoning are examined in relation to educational data analysis, followed by discussion of hybrid architectures that integrate fuzzy feature transformation, rule-based inference structures, and machine learning prediction algorithms. Key aspects including educational data sources, feature selection strategies, data preprocessing procedures, model training mechanisms, and validation strategies are examined to support the development of reliable predictive systems. Hybrid ML–fuzzy frameworks enable effective modeling of complex learning behaviors while producing interpretable decision rules that assist educators and academic administrators in monitoring student progress. Early identification of academically at-risk students, enhanced academic monitoring, and improved institutional decision support emerge as important outcomes of hybrid intelligent educational systems. Analytical insights generated through such approaches contribute to the advancement of intelligent learning analytics and strengthen the role of computational intelligence in modern education.

Fields of Study & Subjects

Online Learning and Analytics Artificial Intelligence in Healthcare Edcuational Technology Systems

Publication details

Pages
145–171
Publication date
19 March 2026
Language
EN
Document type
Book chapter