Abstract
This article introduces a novel method that integrates collaborative filtering into the naive Bayes model to enhance predicting student academic performance. The combined approach leverages collaborative user behavior analysis and probabilistic modeling, showing promising results in improved prediction precision. Collaborative Filtering explores user behavior patterns, while Naive Bayes employs Bayes' theorem for probabilistic data classification. Focused on predicting academic success, the integration incorporates collaborative patterns from student data for increased accuracy. The method considers similar students' performance and behavior for nuanced, personalized predictions. Starting with diverse data collection, including collaborative patterns among students, Collaborative Filtering identifies relationships and patterns among those with similar academic histories. These insights enrich the naive Bayes algorithm, creating a holistic approach for more accurate predictions, and contributing to ongoing machine learning initiatives in education.