Machine Learning-Based Personalized Learning Path Decision-Making Method on Intelligent Education Platforms

Abstract

With the rapid development of information technology, the application of intelligent education platforms has become increasingly widespread. Traditional teaching methods struggle to meet the demands for personalized learning. Personalized learning path decision-making methods, which analyze learners’ behavioral data and mastery of knowledge points, tailor learning paths for each individual. Current research indicates that these methods can significantly improve learning efficiency and effectiveness. However, existing personalized learning path decision-making methods still have shortcomings in predicting the difficulty of knowledge points and dynamically adjusting path recommendations. This paper proposes a machine learning-based personalized learning path decision-making method, focusing on two main aspects: predicting the difficulty of knowledge points for personalized learning and integrating knowledge point localization for personalized learning path decisions. Through accurate prediction of knowledge point difficulty and dynamically optimized learning path recommendations, this method provides more refined and personalized learning support on intelligent education platforms, aiming to enhance learners’ learning experience and outcomes.