Intelligent Adaptive Learning Management System for Students with Special Needs in Higher Education: A Machine Learning-Based Framework for Inclusive Management Education

Abstract

As increasing number of students with special educational needs (SEN) enter higher education institutions (HEIs), it has become evident that there is a critical technology gap: conventional Learning Management Systems (LMS) are not built to support the various cognitive, sensory and physical learning processes that may be observed in management education programs. This study represents an interdisciplinary research effort, drawing on computer science, special education, cognitive psychology and management education to address an inclusive learning challenge. This research aims to suggest an intelligent adaptive learning management system (IALMS) based on machine learning that provides personalized, inclusive and scalable management education to SEN students at the university and college level. The IALMS is built on the foundations of Universal Design for Learning (UDL), Vygotsky's Zone of Proximal Development (ZPD) and Cognitive Load Theory (CLT), and combines five modules of computation: a Learner Profile Engine, Content Adaptation Engine, ML-Based Recommendation and Pathway Engine, a Real-Time Learning Analytics Dashboard and a Faculty Coordination Interface. This approach, which uses K-means clustering, Random Forest classification, Long Short-Term Memory (LSTM) networks, Natural Language Processing (NLP) pipelines, and Reinforcement Learning (RL) agents, is designed to support all SEN profiles in management curricula. Three representative learner personae for SEN learners are used to illustrate module-level adaptive responses by disability. A 24-month implementation roadmap is provided and a disability specific accommodation matrix is provided for institutional deployment.