Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Siti Juwariyah
Yayasan Cendekia Harapan
Computer Science & IT Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Enhanced Loan Prediction Performance Using Blending Model Approach Nur Haryadi; Siti Juwariyah; Muhammad Ricky Perdana Putra
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 3 (2026): Juni 2026 (in progress)
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i3.7242

Abstract

The loan approval process at financial institutions is carried out manually in a conventional manner by looking at the customer's track record. This process is ineffective because it takes a considerable amount of time. As a result, a machine learning (ML) model has been developed that can recognize certain patterns in datasets for automatic and rapid prediction. However, the problem is that a single ML model is still not optimal, so it needs to be improvised, one of which is with Ensemble Learning (EL), which combines more than one model. This study uses Blending EL (BEL), which is built on two layers: the first layer as a base model with KNN, DT, and NB algorithms, and the second layer as a meta layer built with XGBoost. Pre-processing uses MinMaxScaler for data normalization and SMOTE-ENN for data class balancing. Testing uses a confusion matrix covering accuracy, recall, precision, and F1-Score, as well as Area Under Curve (AUC) and execution time, then combined with K-Fold cross validation with k=10. The BEL model prediction results were 96.42% accuracy, 96.29% precision, 96.29% recall, 96.29% F1-Score, and 98.72% AUC. Meanwhile, the average matrix in K-Fold cross validation is accuracy 96.84%, precision 98.09%, recall 95.57%, F1-Score 96.70%, and AUC 99.32% as well as execution time 0.261 seconds.
Co-Authors Muhammad Ricky Perdana Putra Nur Haryadi