This study proposes the development of a Decision Tree-Based Advisory Recommendation System designed to enhance the educational experience of dental students by effectively matching them with suitable advisors. Inadequate guidance from mismatched advisors often leads to suboptimal academic and practical performance, which can hinder students' overall progress. The research focuses on identifying the key factors that influence advisor-student relationships, such as advisor roles, essential qualities, and valuable behaviors. By utilizing data mining classification techniques, the study analyzes data collected from questionnaires to assess the alignment between students' expectations and advisor behaviors. Machine learning models, including Random Forest, Decision Tree, Stacking Classifier, and Voting Classifier, are employed to categorize and optimize the advisor-student matching process, aiming to improve academic outcomes and practical training. The model’s results are anticipated to provide a data-driven approach for more effective advisor-student pairings in dental education, leading to better guidance and enhanced student performance.

Keywords: Decision Tree, Dental Education, Advisor-Student Matching, Data Mining, Classification Techniques, Machine Learning, Random Forest, Stacking Classifier, Voting Classifier, Academic Performance.