AI-DRIVEN PERSONALIZED LEARNING ENVIRONMENT BASED ON LEARNING ANALYTICS

This comprehensive study establishes an advanced, automated framework for implementing an Artificial Intelligence-Driven Personalized Learning Environment (AI-PLE) optimized through real-time Learning Analytics (LA). Traditional learning environments deliver static, generalized instructional materials that fail to capture the highly fluid, idiosyncratic cognitive states and behavioral paces of individual learners. To overcome this systemic pedagogical bottleneck, this paper develops a data-driven model that integrates student footprint tracking logs from digital platforms into a dynamic machine learning pipeline. Utilizing Markov Decision Processes (MDP) for adaptive navigation and personalized feedback orchestration, the system dynamically scales learning pathways. Empirical results from a longitudinal pilot involving 120 technical institute students demonstrate that the proposed framework yields a 91.5% knowledge retention rate while significantly reducing cognitive drift.