ECB perception of non-banks: a machine learning-based approach

Anisa Tiza Mimun and Ami Dalloul

No 3304, Working Paper Series from European Central Bank

Abstract: This paper studies the European Central Bank’s (ECB) perception of non-bank financial intermediaries (NBFIs) and how this perception is publicly communicated. We construct a perception index based on ECB speeches over the period 1998–2025. Sentiment in references to non-banks is classified by a large language model that we fine-tune on our own hand-labeled dataset constructed for this purpose. The resulting index reveals a predominantly negative and declining perception over time, particularly since the Global Financial Crisis. Negative sentiment is primarily associated with concerns related to financial stability and regulatory needs, whereas positive sentiment reflects the role of non-banks in fostering financial innovation and supporting market functioning. The index is made publicly available for future research. JEL Classification: E44, E52, C80

Keywords: ECB speeches; large language models; machine learning; non-bank financial intermediation; sentiment analysis (search for similar items in EconPapers)
Date: 2026-11
New Economics Papers: this item is included in nep-eec and nep-fdg
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.ecb.europa.eu//pub/pdf/scpwps/ecb.wp3304~9082a5f181.en.pdf (application/pdf)

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:ecb:ecbwps:20263304

Access Statistics for this paper

More papers in Working Paper Series from European Central Bank 60640 Frankfurt am Main, Germany. Contact information at EDIRC.
Bibliographic data for series maintained by Official Publications ().