Early Warning Models for Bank Supervision: Simpler Could Be Better

Abstract

Can computer-based models, using publicly available information, be used as off-site early warning systems (EWS) to identify banks that will become inadequately capitalized in the near future? The EWS models analyzed in this article are able to detect the early onset of financial distress one year in advance with a reasonable degree of accuracy. Although simple EWS models do as well as or better than more sophisticated ones, more sophisticated models could provide detailed information about individual bank strengths and weaknesses.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 46 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.