Claim Missing Document
Check
Articles

Explainable AI for Student Dropout Prediction: A Hierarchical LightGBM Approach Ismail Setiawan; Rahmat Gernowo; Budi Warsito
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 5 (2026): October 2026
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i5.7793

Abstract

The high dropout rate in health science programs not only affects the efficiency of educational management but also threatens the stability of the professional medical workforce. This research proposes a Hierarchical Early Warning System (HEWS) framework using the Light Gradient Boosting Machine (LightGBM) algorithm to predict student dropout risks at an early stage, utilizing a primary dataset of academic and demographic records from an Indonesian health sciences faculty. While previous studies predominantly utilized full-trajectory academic records, this study compares the model's performance across two temporal scenarios: early detection using historical data up to the second semester and full-trajectory evaluation. The Synthetic Minority Over-sampling Technique (SMOTE) is applied to address the extreme class imbalance inherent in educational datasets. Experimental results demonstrate that the proposed model achieves an F1-Score of 0.95 for the minority class in both internal scenarios and maintains a robust F1-Score of 0.91 when validated against an international dataset. Furthermore, SHapley Additive exPlanations (SHAP) is integrated to dissect the algorithm's black-box nature. The SHAP analysis reveals a critical shift in risk drivers: high school education quality and first-semester grades dominate the early detection phase, whereas fourth-semester grades and sick leave frequencies become primary predictors in the full-trajectory phase. These findings provide actionable insights for university management to design targeted academic and psychological interventions, thereby supporting the achievement of Sustainable Development Goals (SDG) 3 and 4.
Co-Authors Adi Wibowo Afwan, Teuku M Arief Aghus Sofwan Agus Setyawan Agus Sutejo Ahmad Lubis Ghozali Andryani, Ria Annisa Luthfianti Panular Arfriandi, Arief Ari Bawono Putranto Aria Hendrawan, Aria Aries Dwi Indriyanti, Aries Dwi Aris Sugiharto Atik Zilziana Muflihati Noor Basworo Ardi Pramono Bayong Tjasyono H. Kasih Bayu Surarso Beta Noranita Budi Prasetiyo, Budi Budi Warsito Budi Warsito Catur Edi Widodo Cholil, Saifur Rohman Christine Dewi D Febrianty Dafiz Adi Nugroho Dedy Kurniadi Edi Surya Negara Eko Nur Hidayat Eko Sediyono F M Arif Faliha Muthmainah Fauzan Ishlakhuddin Frysca Putti Muviana Ghufron Ghufron Gumay, Naretha Kawadha Pasemah Helmie Arif Wibawa Hengki Hengki Heri Mulyanti Hidayat, Agung Rahmad I. Istadi Ikhthison Mekongga Iryanto Iryanto Ismail Setiawan Ismi Dian Kusumawardhani Isnain Gunadi I’tishom Al Khoiry Khusnah, Miftakhul Koesuma, Sorja Kuresih, Kuresih Kurnia Adi Cahyanto Kusworo Adi M. Solehuddin Mahrus Ali Michael Andreas Purwoadi Moh Ali Fikri Muchammad A Rofik Mulyani, Esti Munengsih Sari Bunga Munji Hanafi Nabiel Putra Adam Novita Mariana Nuriyana Muthia Sani Nuriyana Muthia Sani Nursamsiah Nursamsiah Oky Dwi Nurhayati Prayitno R. Rizal Isnanto Radini Sinta, Radini Ratih Rundri Utami Rosyalia, Syofi Sakhina, Friska Ayu Shahmirul Hafizullah Imanuddin Siti Yuniar Pangestu Slamet, Vincencius Gunawan Soni Adiyono Suryono Suryono Tri Mulyono Triyono, Liliek Victor Gayuh Utomo Wahyu Jatmiko Wahyul Amien Syafei Wicaksana, Hilman Singgih Widagdo, Krisan Aprian Wulandari, Rosita Ayu Yenny Ernitawati Zaenal Arifin