Emotional intelligence (EI) has been increasingly recognized as a critical factor influencing
academic success among college students. This study investigates the impact of EI
components—self-awareness, self-regulation, motivation, empathy, and social skills—on
academic achievements using the XGBoost algorithm, a powerful machine learning technique
known for its high predictive accuracy. The primary objective of this work is to determine the
relative importance of EI traits in predicting academic performance and to develop a robust
model that can identify key emotional intelligence factors contributing to student success. A
dataset comprising EI assessments and academic records of college students is analyzed, with
XGBoost employed for feature importance analysis and predictive modeling. The findings
reveal which EI dimensions most significantly influence academic outcomes, providing
actionable insights for educators and policymakers to enhance student support programs. This
research contributes to the growing body of literature on EI in education by leveraging
advanced machine learning to quantify its impact, offering a data-driven approach to improving
academic interventions.