Does ESG Predict Systemic Banking Crises? A Computational Economics Model of Early Warning Systems with Interpretable Multi-Variable LSTM based on Mixture Attention

Shu-Ling Lin and Xiao Jin ()
Additional contact information
Shu-Ling Lin: Department of Information and Finance Management, College of Management, National Taipei University of Technology, Taipei 10608, Taiwan
Xiao Jin: Department of Information and Finance Management, College of Management, National Taipei University of Technology, Taipei 10608, Taiwan

Mathematics, 2023, vol. 11, issue 2, 1-15

Abstract: Systemic banking crises can be very damaging to economic development, and environmental, social, and governance (ESG) can also damage national finances, but there is no research on whether ESG affects systemic banking crises, and we fill this gap. We first employ Fisher scores (FS) to select features and then use an interpretable multivariate long-short-term memory (IMV-LSTM) model with focal loss (FL) to account for class imbalance to model an early warning system (EWS) that can predict up to one year in advance. This study finds that ESG influences the occurrence of systemic banking crises, with our early warning system predicting each crisis a year in advance.

Keywords: systemic banking crisis; early warning system; environmental, social, and governance (ESG); deep learning; LSTM (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/11/2/410/pdf (application/pdf)
https://www.mdpi.com/2227-7390/11/2/410/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:11:y:2023:i:2:p:410-:d:1034021

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().