AI -Based Adaptive Learning Framework for Enhancing Educational Management in Malaysia Using the EduAdaptNet Model

In the rapidly evolving landscape of education, the integration of artificial intelligence (AI) offers transformative potential for personalized learning, effective administrative planning, and strategic educational policy implementation. This research presents EduAdaptNet, an AI-driven adaptive learning framework developed to enhance educational management systems in Malaysia. With the rising demand for personalized learning and real-time academic insights, the proposed model integrates Deep Neural Networks (DNNs), Reinforcement Learning (RL), and Natural Language Processing (NLP) to deliver dynamic curriculum adjustments, accurate performance predictions, and effective student engagement tracking. Data collected from top Malaysian universities-including Universiti Malaya and Universiti Teknologi MARA-was preprocessed using imputation, normalization, and time-series segmentation. Key features such as engagement scores, weekly study time, and teacher feedback sentiment were engineered and selected using Autoencoders and correlation analysis. Upon training with adaptive optimizers, the model achieved remarkable results with an average accuracy of 95.4%, a precision of 93.1%, and a recall of 91.8% across 10 institutions. Real-time deployment showcased significant improvements in engagement scores post-intervention. The study underscores the potential of AI in transforming traditional educational systems into intelligent, responsive, and student-centric environments. EduAdaptNet not only elevates academic outcomes but also aids administrators and policymakers in data-driven decision-making.