Current Adaptive and Personalised Learning Systems (APLS) face significant challenges in leveraging Machine Learning (ML), large language models (LLMs), and Artificial Intelligence (AI) effectively. These systems often lack the infrastructure for real-time adaptability and rely on incomplete or static data-driven methods, limiting their ability to meet diverse learner needs.

This research proposes a novel APLS that integrates ML algorithms, LLMs, and AI to deliver personalised learning experiences. By analysing both static and dynamic educational data, the system will utilise LLMs to provide adaptive content recommendations and generate feedback tailored to individual learner profiles. Advanced ML techniques will drive continuous improvements, enabling the system to adapt in real-time and personalise learning pathways based on progress and performance. Additionally, the system will employ predictive analytics to identify at-risk learners and prevent dropouts in Massive Open Online Courses (MOOCs), enhancing retention and engagement. This approach, built on an open architecture using the 1EdTech Learning Tools Interoperability (LTI) standard, aims to transform education by offering responsive, data-driven support validated across various educational contexts, significantly improving learning outcomes and course completion rates.