Utilizing the random forest method for predicting student dropout risk in madrasah environments

Mahsun, Muhammad, Hariyadi, M. Amin ORCID: https://orcid.org/0000-0001-9327-7604 and Harini, Sri ORCID: https://orcid.org/0000-0001-9664-027X (2025) Utilizing the random forest method for predicting student dropout risk in madrasah environments. Journal of Information Systems and Informatics (ISI), 7 (4). pp. 3434-3453. ISSN 2656-4882

Preview

Text 28026.pdf - Published Version Available under License Creative Commons Attribution. Download (4MB) | Preview

Abstract

The phenomenon of school dropout is a crucial issue that negatively impacts the performance of educational institutions, social stability, and human resource development. Therefore, early detection of high-risk students is a strategic preventative measure. This research aims to develop an accurate predictive model using a Machine Learning approach, by conducting a comparative evaluation of the Random Forest algorithm. The research dataset originates from Madrasah Miftahul Ulum, Sidogiri Islamic Boarding School, and comprises 1,763 student records. The experimental results indicate that Random Forest provides the best performance with an accuracy of 82%, precision of 83.8%, recall of 79%, and an F1-score of 80%. The model was trained using 4 scenarios with Random state configurations of 40, 60, and 75 to ensure the consistency of the evaluation results. These metrics indicate that the model performs in a balanced manner between sensitivity and prediction accuracy, and is effective in identifying internal and external factors contributing to the risk of dropout. Based on the model evaluation results, Random Forest is recommended as a decision support instrument to facilitate more targeted interventions, such as academic support, economic aid, or student counseling guidance. This research has a limitation because the model was only tested at the Madrasah Miftahul Ulum, Sidogiri Islamic Boarding School institution, thus its application in other contexts needs further study.

Item Type:	Journal Article
Keywords:	student dropout prediction; random forest; machine learning; Madrasah Miftahul Ulum
Subjects:	08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080105 Expert Systems
Divisions:	Graduate Schools > Magister Programme > Graduate School of Informatics Engineering
Depositing User:	Mokhamad Amin Hariyadi
Date Deposited:	13 Jul 2026 09:21

Downloads

Origin of downloads

Actions (login required)

View Item