Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal Teknik Informatika (JUTIF)
Anton Yudhana
Electrical Engineering Department, Universitas Ahmad Dahlan, Indonesia
Computer Science & IT

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

Found 1 Documents
Search

 1 
Building a Trustworthy Credit Default Classification Model using Interpretable Machine Learning Haikal Djauhari; Anton Yudhana; Sunardi Sunardi
Jurnal Teknik Informatika (Jutif) Vol. 7 No. 4 (2026): JUTIF Volume 7, Number 4, August 2026
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2026.7.4.5149

Abstract

In peer-to-peer lending, a single misjudged borrower can result in significant investor losses and erode the platform's credibility. Although machine learning models have demonstrated superior predictive performance in identifying potential loan defaults, their opaque decision-making process creates mistrust and regulatory friction, impeding their trustworthy adoption. This study addresses the critical trade-off between accuracy and interpretability by proposing an interpretable machine learning framework for trustworthy credit default classification using Bondora peer-to-peer lending data. We deploy and benchmark three classifiers —Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Random Forest (RF) — to assess their predictive effectiveness. To overcome the black-box nature of these models, we integrate two complementary interpretability techniques: SHapley Additive exPlanations (SHAP) for global feature attribution and Local Interpretable Model-agnostic Explanations (LIME) for granular, instance-level decision insights. The high AUC, which exceeds 0.96, and F1 score (0.937-0.940) show that all models can effectively support risk management. Our results also demonstrate that pairing high-performing classifiers with interpretability tools enhances model transparency, fosters accountability, and promotes the responsible use of machine learning in credit risk assessment.
Co-Authors Haikal Djauhari Sunardi Sunardi