Development of an AI-Driven Adaptive Learning Management System Using Data Analytics

This study presents the development of an AI-driven Adaptive Learning Management System (LMS) that delivers personalized learning experiences using data analytics and natural language processing. The system addresses limitations of traditional LMS platforms by dynamically adapting content based on student performance in real-time. Designed with Object-Oriented Methodology and the CRISP-DM data analytics model, the system integrates Python, web technologies, and a BERT (Bidirectional Encoder Representations from Transformers)-based semantic engine. When students fail a quiz, the BERT model identifies knowledge gaps and retrieves tailored content through web scraping. A mixed-method evaluation combining interviews and performance metrics showed enhanced student engagement and academic outcomes. This adaptive feedback loop supports continuous learning and remediation. Evaluation results demonstrate improvements in learner engagement, satisfaction, and academic outcomes. The system’s ability to automate content adaptation and feedback makes it a robust solution for scalable, equitable education delivery. In conclusion, this study offers a practical and intelligent framework for next-generation LMS platforms, addressing critical gaps in adaptability, personalization, and real-time instructional support.