Article Per Year (5 Year)
p-Index From 2021 - 2026
1.578
P-Index
This Author published in this journals
All Journal Jurnal Computech & Bisnis (e-Journal) Nuansa Informatika JTERA (Jurnal Teknologi Rekayasa) Jurnal Pengabdian Masyarakat Tapis Berseri SisInfo : Jurnal Sistem Informasi dan Informatika Coreid Journal INTERNAL (Information System Journal) Bulletin of Intelligent Machines and Algorithms
Nugraha, Arif Bakti
Fakultas Teknologi Dan Informatika, Universitas Informatika Dan Bisnis Indonesia
Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Education Electrical & Electronics Engineering Industrial & Manufacturing Engineering Library & Information Science Mechanical Engineering Other

Published : 11 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 11 Documents
Search

 1   2 
Ensemble Learning for Early Warning Systems in Higher Education: A Comparative Study of Student Attrition Arifudin, Muhamad Achya; Setiana, Elia; Nugraha, Arif Bakti
Bulletin of Intelligent Machines and Algorithms Vol. 1 No. 3 (2026): BIMA March 2026 Issue
Publisher : Maheswari Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65780/bima.v1i3.19

Abstract

Student attrition poses a substantial challenge to higher education institutions, affecting their reputation and financial sustainability. Conventional single machine learning models often exhibit limited sensitivity when analyzing educational data, which is typically marked by severe class imbalance favoring graduating students over dropouts. This study introduces an Early Warning System based on a Hybrid Stacking Ensemble framework to improve student attrition prediction. The approach leverages complementary biases from Bagging and Boosting as base learners, which are then combined using a Logistic Regression meta-learner to refine prediction weights. To counteract class imbalance and majority-class bias, the Synthetic Minority Over-sampling Technique was employed during preprocessing. Empirical evaluations reveal that the Hybrid Stacking Ensemble attains a classification accuracy of 88.81% and a Recall of 80.99%, surpassing standalone models and other ensemble methods. Feature importance rankings highlight second-semester academic performance and administrative-financial factors—particularly tuition payment punctuality—as key dropout predictors. These results affirm the value of integrating diverse classifiers to discern intricate, nonlinear student behavior patterns. In essence, this work establishes a reliable, evidence-based framework enabling administrators to shift from reactive to proactive, precision-targeted strategies that foster student retention and institutional success.
Co-Authors Akbar, Imannudin Anggraeni, Hilma Arifudin, Muhamad Achya Habibi, Chairul Pangestu, Idham Azis Putra, Raka Deny Adi Rizcky Hikmawan, Muhammad Saputra, Naufal Fajar Setiana, Elia Venia Restreva Danestiara