Article Per Year (5 Year)
p-Index From 2020 - 2025
2.083
P-Index
This Author published in this journals
All Journal JURNAL SISTEM INFORMASI BISNIS Jurnal Manajemen Teori dan Terapan JOIN (Jurnal Online Informatika) Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) CARADDE: Jurnal Pengabdian Kepada Masyarakat AkMen JURNAL ILMIAH EDUKATIF : JURNAL ILMU PENDIDIKAN Celebes Computer Science Journal Al-Khidmat : Jurnal Ilmiah Pengabdian Kepada Masyarakat Jurnal Sains Manajemen dan Bisnis Indonesia Jurnal Komunitas: Jurnal Pengabidian Kepada Masyarakat LOSARI: Jurnal Pengabdian Kepada Masyarakat Jurnal Visi Pengabdian Kepada Masyarakat Jurnal Ilmiah Bongaya (JIB)
Astuti, Niken Probondani
STIEM Bongaya Makassar
Religion Agriculture, Biological Sciences & Forestry Arts Humanities Computer Science & IT Decision Sciences, Operations Research & Management Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Health Professions Languange, Linguistic, Communication & Media Library & Information Science Mathematics Mechanical Engineering Public Health Social Sciences Transportation Other

Published : 21 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 21 Documents
Search

 1   2   3 
Optimizing Machine Learning Models for Graduation on Time Prediction: A Comparative Study with Resampling and Hyperparameter Tuning Bakri, Rizal; Alam, Syamsu; Astuti, Niken Probondani; Bakhtiar, Muhammad Ilham
JOIN (Jurnal Online Informatika) Vol 10 No 2 (2025)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v10i2.1590

Abstract

Timely graduation prediction is a crucial issue in higher education, especially when academic, demographic, and behavioral factors interact in complex ways. However, many previous studies rely on default machine learning (ML) parameters and fail to consider the class imbalance problem, leading to suboptimal predictions. This study aims to build a comprehensive framework to evaluate the effectiveness of seven ML algorithms, which are AdaBoost, K-Nearest Neighbors, Naïve Bayes, Neural Network, Random Forest, SVM-RBF, and XGBoost, for predicting graduation on time by incorporating five resampling techniques and hyperparameter tuning. Resampling methods include Random Undersampling (RUS), Random Oversampling (ROS), SMOTENC, and two hybrid approaches (RUS-ROS and SMOTENC-RUS). Hyperparameter tuning was conducted using Grid Search, and model performance was evaluated through cross-validation and hold-out methods. The results show that Random Forest combined with RUS-ROS achieved the best performance, with an average metric score of 0.948. Statistical analysis using PERMANOVA (p = 0.009) and Bonferroni's post-hoc pairwise tests confirmed significant differences between certain models. This study contributes to the educational data mining literature by demonstrating that combining resampling and hyperparameter tuning improves classification performance in imbalanced educational datasets.
Co-Authors Ahmar, Ansari Saleh Amin, Asbi Anggraeni, Iluh Riang Ardiansyah Halim Asbi Amin Basir, Asri Rahmat Data, Umar Djaharuddin, Dharmawaty Hadji, Alimuddin Hartoto Hartoto Hasbiyadi, Hasbiyadi Hasyim Mochtar Heslina, Heslina Iluh Riang Anggraeni Muhammad Ilham Bakhtiar Nabila Putri Fiamanila Razak, Nurlaely Riswan Riswan Rizal Bakri Rusdi, Pertiwi Sandi, Esti Singh, Pawan Kumar Sjahruddin, Herman Sobirov, Bobur Subandi, Tiara Suprianto, Satria SYAMSU ALAM Tafsir, Muhammad Wiyana, Anim Yusuf, Marwah