EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Metaheuristic-Driven Feature Selection for Machine Learning-Based Credit Scoring

Chinh Xuan Pham, Huynh Ngoc Trinh, Long Quoc Tran

Engineering, Technology & Applied Science Research · 09.02.2026 · 16 (1) · 31540-31548

DOI: 10.48084/etasr.15590 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Engineering, Technology & Applied Science Research, online erschienen am 09.02.2026. Verfasst von Chinh Xuan Pham und 2 weiteren Autor:innen. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The recurrence of financial and debt crises in recent years has underscored the critical importance of effective credit risk management in financial research. Within this context, credit scoring is a critical tool for financial institutions to evaluate loan applications and has received extensive attention in both statistical and machine learning research. This study proposes a novel credit scoring framework that integrates metaheuristic-driven feature selection with machine learning classifiers. Three metaheuristic algorithms, namely Particle Swarm Optimization (PSO), Simulated Annealing (SA), and Tabu Search (TS), are employed to identify the most relevant subset of features, whereas a wide range of machine learning models is trained to determine the most effective combination for credit scoring. The framework is evaluated on three benchmark datasets, namely Australian, German, and Japanese datasets, from the UCI Machine Learning Repository. Experimental results show that metaheuristic-based feature selection consistently improves model performance compared to the baseline without feature selection and conventional methods such as Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), and Stepwise Selection, demonstrating its effectiveness and robustness in credit scoring tasks.

Zitieren

APA

Pham, C. X., Trinh, H. N., & Tran, L. Q. (2026). Metaheuristic-Driven Feature Selection for Machine Learning-Based Credit Scoring. Engineering, Technology & Applied Science Research, 16(1), 31540-31548. https://doi.org/10.48084/etasr.15590

Vancouver

Pham CX, Trinh HN, Tran LQ. Metaheuristic-Driven Feature Selection for Machine Learning-Based Credit Scoring. Engineering, Technology & Applied Science Research. 2026;16(1):31540-31548. doi:10.48084/etasr.15590

BibTeX
@article{Pham2026,
  author = {Pham, Chinh Xuan and Trinh, Huynh Ngoc and Tran, Long Quoc},
  title = {Metaheuristic-Driven Feature Selection for Machine Learning-Based Credit Scoring},
  journal = {Engineering, Technology & Applied Science Research},
  year = {2026},
  volume = {16},
  number = {1},
  pages = {31540--31548},
  doi = {10.48084/etasr.15590}
}
Kostenlos starten →