Recommendations for Personalised Learning Paths

Contemporary education systems face the challenge of meeting diverse learning needs. Traditional standardized curricula often fail to accommodate the unique learning pace and academic abilities of students, thus leading to the pursuit of personalized learning paths. This paper extensively investigates personalized learning path recommendation algorithms, addressing gaps and deficiencies in prior research. By combining collaborative filtering and deep learning models, we propose a novel personalized learning path recommendation algorithm. Experimental results demonstrate that the recommendation algorithm employing deep learning models outperforms traditional collaborative filtering methods in accuracy and recall. Our research fills existing gaps in the field and provides valuable insights and solutions for future developments in personalized learning path recommendation algorithms.