Abstract
This paper proposes MBTI-based recommendation system for extracurricular activities for high school students. The system extracts personality types from student profiles using feature engineering and utilizes machine learning algorithms to recommend relevant extracurricular activities. We evaluate the system's performance using precision, recall, and F1-score metrics and compare it with other state-of-the-art recommendation systems. Our results show that the MBTI-based recommendation system outperforms other systems and provides a more personalized approach to activity selection. We also discuss the potential impact and benefits of the system for high school students and identify areas for future research. Overall, this paper contributes to the growing body of literature on recommendation systems and highlights the importance of considering personality types in the recommendation process.