EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Exploring neural networks and machine learning in predicting personal loan defaults

Hang Thi Thanh Hoang, Nhat Nguyen, Duy Ngo

Risk Governance and Control Financial Markets & Institutions · 08.06.2026 · 16 (2) · 122

DOI: 10.22495/rgcv16i2p11 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Risk Governance and Control Financial Markets & Institutions, online erschienen am 08.06.2026. Verfasst von Hang Thi Thanh Hoang und 2 weiteren Autor:innen. Die Arbeit nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The ability to accurately forecast default risk for a personal loan is a critical factor for managing credit risks. In this context, developing an adequate risk assessment methodology for borrowers is especially important for emerging markets with diverse borrower features and behavior. Hence, the following paper aims to investigate the potential for applying machine learning approaches to improving default risk predictions for individual loans in Vietnam over 2012–2022. For the empirical analysis, the authors used a sample of 6,034 observations of retail loans to compare the performance of logistic regression (LR), k-nearest neighbors (KNN), artificial neural networks (ANNs), and random forest (RF). The methodological framework involves data preprocessing, balancing classes, optimization of parameters, and validation through the use of accuracy, precision, sensitivity, specificity, and F1 scores. As a result, RF demonstrates superior prediction performance with an accuracy of 97.56 percent, precision of 0.988, sensitivity of 0.987, specificity of 0.992, and F1 score of 0.987. Important predictors include months since last delinquency, credit history length, maximum credit limit, and open accounts count.

Zitieren

APA

Hoang, H. T. T., Nguyen, N., & Ngo, D. (2026). Exploring neural networks and machine learning in predicting personal loan defaults. Risk Governance and Control Financial Markets & Institutions, 16(2), 122. https://doi.org/10.22495/rgcv16i2p11

Vancouver

Hoang HTT, Nguyen N, Ngo D. Exploring neural networks and machine learning in predicting personal loan defaults. Risk Governance and Control Financial Markets & Institutions. 2026;16(2):122. doi:10.22495/rgcv16i2p11

BibTeX
@article{Hoang2026,
  author = {Hoang, Hang Thi Thanh and Nguyen, Nhat and Ngo, Duy},
  title = {Exploring neural networks and machine learning in predicting personal loan defaults},
  journal = {Risk Governance and Control Financial Markets & Institutions},
  year = {2026},
  volume = {16},
  number = {2},
  pages = {122},
  doi = {10.22495/rgcv16i2p11}
}
Kostenlos starten →