The evaluation of students is essential to comprehending and enhancing successful learning in an educational setting. In the era of information technology, the use of decision tree algorithms has become increasingly pertinent in this sphere. This study seeks to identify the student assessment factors that have the greatest impact on learning success when using the Decision Tree algorithm. The collection and analysis of student assessment data, including test scores, class participation, and other variables Modeling the relationship between these factors and student learning outcomes using decision trees. The results of the analysis permit the identification of the most influential factors in predicting the success of student learning. The findings of this study can aid educators, schools, and educational institutions in designing learning strategies that are more effective and tailored to the specific needs of each student, as well as in identifying students who are at high risk and require special attention. The implementation of the Decision Tree algorithm in student evaluation is a crucial step toward a more individualized and effective educational approach.