<![CDATA[The development of educational technology has witnessed the use of machine learning as a basis for data-driven decision making in the education sector. The objective of this research is to build a predictive model of admission of high school students at State Universities (PTN) using a machine learning method based on the Cross Industry Standard Process for Data Mining (CRISP-DM) framework. The data was obtained from the Student Center tutoring institution and consisted of academic, non-academic, and socio-economic attributes. Three classification algorithms i.e. Decision Tree, Random Forest, Naive Bayes were used. The split percentage method was employed in the model evaluation with the training and testing data division schemes of 70:30, 80:20, and 90:10. The results indicated that the Random Forest algorithm had the highest average accuracy at 96.63%, followed by the Decision Tree with 95.48% and the Naive Bayes with 94.06%. It was found that class ranking, try-out scores, school accreditation and attendance rate are several variables that significantly affect the students’ chances to be accepted in PTN. These findings demonstrate that academic success is determined not only by learning achievement, but also by study discipline and educational environment quality. This research contributes to the advancement of educational data mining and supports educational innovation by using machine learning as a decision support system for student guidance and academic evaluation.]]>
Copyrights © 2026
