STUDENT GRADUATION PREDICTION USING DECISION TREE ALGORITHM WITH CRISP-DM METHOD (CASE STUDY: ITB AHMAD DAHLAN)

Kholilah Husni (Institut Teknologi dan Bisnis Ahmad Dahlan Jakarta)
Elliya Sestri (Institut Teknologi dan Bisnis Ahmad Dahlan Jakarta)
Vany Terisia (Institut Teknologi dan Bisnis Ahmad Dahlan Jakarta)

Journal of Computer Science Advancements
Vol. 3 No. 5 (2025)

On-time graduation is an important indicator of higher education effectiveness; however, delays in student graduation are still observed at ITB Ahmad Dahlan Jakarta. This study develops a student graduation prediction system using the Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology and the Decision Tree algorithm based on historical academic data. The model was built through six CRISP-DM stages, including problem understanding, data preparation, modeling, and evaluation. Testing results indicate high performance with an Accuracy of 97.44%, Precision of 97.14%, Recall of 100%, and F1-Score of 98.55%. This system has the potential to support strategic decision-making to enhance academic quality through data-driven approaches.