Back to Search
Start Over
Machine learning methods for predicting failures of US commercial bank.
- Source :
- Applied Economics Letters; Sep2024, Vol. 31 Issue 15, p1353-1359, 7p
- Publication Year :
- 2024
-
Abstract
- In this paper, we attempt to study the effectiveness of various simple machine learning methods in the prediction of bank failures. From a raw dataset of 10,938 US banks during the period of 2000–2020, we find that machine learning approaches do not really outperform the benchmark of conventional statistical method, logistic regression. However, using PCA to retain relevant variance in variables significantly improve the performance of machine learning methods and raise the out-of-sample accuracy of those method to over 70% to over 80%. Of all the machine learning methods used in this paper, the simple KNN seems to be the best model in forecasting bank failure in the United States. [ABSTRACT FROM AUTHOR]
- Subjects :
- MACHINE learning
BANKING industry
BANK failures
SIMPLE machines
MACHINE performance
Subjects
Details
- Language :
- English
- ISSN :
- 13504851
- Volume :
- 31
- Issue :
- 15
- Database :
- Complementary Index
- Journal :
- Applied Economics Letters
- Publication Type :
- Academic Journal
- Accession number :
- 178652043
- Full Text :
- https://doi.org/10.1080/13504851.2023.2186353