AI-Driven Learning Path Optimizer Using Performance Analytics

The rapid growth of online learning platforms has increased the need for personalized learning experiences that adapt to individual student performance and learning behaviour. Traditional e- learning systems typically follow a static learning path that does not consider the learner’s knowledge level, learning speed, or conceptual understanding. This limitation often results in inefficient learning and reduced student engagement. This research proposes an AI-driven adaptive learning path optimizer that dynamically personalizes the learning sequence for each student. The system integrates Retrieval Augmented Generation (RAG) with Large Language Models (LLMs) to analyze learner performance data, identify knowledge gaps, and recommend optimized learning paths. The proposed framework calculates mastery levels based on quiz accuracy, learning consistency, response time, and retention metrics. Using a customized educational dataset, the system predicts the learner’s skill level and automatically adjusts the difficulty of upcoming topics. The integration of RAG enables the system to retrieve relevant learning materials while the LLM generates intelligent feedback and explanations tailored to the learner’s needs. Experimental evaluation demonstrates that the proposed system improves learning efficiency, enhances engagement, and supports personalized knowledge acquisition. The proposed model provides a scalable solution for intelligent tutoring systems and adaptive educational platforms.