Machine learning methods for predicting failures of US commercial bank

Le Quoc Tuan, Chih Yung Lin*, Huei Wen Teng

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1 Scopus citations


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.

Original languageEnglish
JournalApplied Economics Letters
StateAccepted/In press - 2023


  • bank failure
  • banking system
  • financial indicators
  • financial safety
  • Machine learning


Dive into the research topics of 'Machine learning methods for predicting failures of US commercial bank'. Together they form a unique fingerprint.

Cite this