Predicting Stock Market Risk Using Machine Learning Classification Models
Risks · 17.04.2026 · 14 (4) · 92
DOI: 10.3390/risks14040092 ↗Kurz gefasst
Fachartikel in der Zeitschrift Risks, online erschienen am 17.04.2026. Verfasst von Seol-Hyun Noh. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Hongik University.
Abstract (Originalsprache)
This study aims to predict stock market risk and improve preparedness for potential economic crises by identifying sharp declines in stock returns using classification-based machine learning models. Using ten years of KOSPI 200 index data (2015 to 2024), a daily return series was constructed. A day was labeled a risk event (1) if its return fell below the 5th percentile of the returns observed over the preceding 100 trading days, indicating a sharp decline. Nine classification models—Logistic Regression, k-nearest Neighbor, Decision Tree, Random Forest, Linear Discriminant Analysis, Naive Bayes, Quadratic Discriminant Analysis, AdaBoost, and Gradient Boosting—were trained and validated. Among these, Logistic Regression demonstrated the strongest overall performance across multiple evaluation metrics, including accuracy, non-risk F1 score, risk F1 score, and AUC.
Förderung
- Hongik University
Zitieren
APA
Noh, S. (2026). Predicting Stock Market Risk Using Machine Learning Classification Models. Risks, 14(4), 92. https://doi.org/10.3390/risks14040092
Vancouver
Noh S. Predicting Stock Market Risk Using Machine Learning Classification Models. Risks. 2026;14(4):92. doi:10.3390/risks14040092
BibTeX
@article{Noh2026,
author = {Noh, Seol-Hyun},
title = {Predicting Stock Market Risk Using Machine Learning Classification Models},
journal = {Risks},
year = {2026},
volume = {14},
number = {4},
pages = {92},
doi = {10.3390/risks14040092}
}
EUVIMED