Optimizing Financial Risk Prediction for Loan Approval Decisions
JISKA (Jurnal Informatika Sunan Kalijaga) · 25.05.2026 · 11 (2) · 225-236
DOI: 10.14421/jiska.6071 ↗Kurz gefasst
Fachartikel in der Zeitschrift JISKA (Jurnal Informatika Sunan Kalijaga), online erschienen am 25.05.2026. Verfasst von Khalifatur Rauf und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Accurate financial risk prediction is essential for effective loan approval decision-making, particularly in data-driven financial systems. This study investigates the influence of feature selection strategies on the performance of machine learning models for loan approval prediction using the publicly available Kaggle "Financial Risk for Loan Approval" synthetic dataset, which contains 20,000 applications. Experiments evaluated multiple feature selection paradigms, including filter-based, wrapper-based, embedded, and PCA-informed approaches across six classification models using stratified 10-fold cross-validation and imbalance-aware metrics. The results show that feature selection consistently improves predictive robustness and minority class recognition. Contrary to assumptions favoring complex models, Logistic Regression combined with Lasso regularization achieved the best overall predictive performance, yielding an ROC-AUC of 99.41% and an F1-score of 91.72%. Embedded feature selection methods provided the most favorable balance between accuracy and computational efficiency. These findings indicate that the effectiveness of feature selection depends heavily on its interaction with model complexity, providing empirical guidance for designing robust, interpretable financial risk prediction systems.
Zitieren
APA
Rauf, K., Kuswijayanto, A. C., & Susan, E. K. (2026). Optimizing Financial Risk Prediction for Loan Approval Decisions. JISKA (Jurnal Informatika Sunan Kalijaga), 11(2), 225-236. https://doi.org/10.14421/jiska.6071
Vancouver
Rauf K, Kuswijayanto AC, Susan EK. Optimizing Financial Risk Prediction for Loan Approval Decisions. JISKA (Jurnal Informatika Sunan Kalijaga). 2026;11(2):225-236. doi:10.14421/jiska.6071
BibTeX
@article{Rauf2026,
author = {Rauf, Khalifatur and Kuswijayanto, Adi Cahyo and Susan, Ella Kristiantini},
title = {Optimizing Financial Risk Prediction for Loan Approval Decisions},
journal = {JISKA (Jurnal Informatika Sunan Kalijaga)},
year = {2026},
volume = {11},
number = {2},
pages = {225--236},
doi = {10.14421/jiska.6071}
}
EUVIMED