Application of Transformers and Machine Learning Methods in the System of Recommendations of Academic Supervisor

This paper proposes a recommendation system for academic supervisor selection based on transformer architecture and modern machine learning methods. The system analyzes a student’s academic data, including courses studied and grades for them, as well as the professional characteristics of teachers. The results of the experiment demonstrate a significant superiority of the proposed approach over traditional methods: during testing, the achieved accuracy of recommendations was 0.3230 versus 0.1106 (method based on the frequency of positive grades) and 0.1637 (approach using classification through machine learning). The obtained results confirm the effectiveness of the system in optimizing the process of selecting a supervisor, which helps to improve the quality of students’ research activities through a personalized comparison of competencies.