Deep learning model fragility and implications for financial stability and regulation

Rishabh Kumar, Adriano Koshiyama (), Kleyton da Costa (), Nigel Kingsman (), Marvin Tewarrie (), Emre Kazim (), Arunita Roy (), Philip Treleaven () and Zac Lovell ()
Additional contact information
Adriano Koshiyama: University College London
Kleyton da Costa: University College London
Nigel Kingsman: University College London
Marvin Tewarrie: Bank of England, Postal: Bank of England, Threadneedle Street, London, EC2R 8AH
Emre Kazim: University College London
Arunita Roy: Reserve Bank of Australia
Philip Treleaven: University College London
Zac Lovell: Bank of England, Postal: Bank of England, Threadneedle Street, London, EC2R 8AH

No 1038, Bank of England working papers from Bank of England

Abstract: Deep learning models are being utilised increasingly within finance. Given the models are opaque in nature and are now being deployed for internal and consumer facing decisions, there are increasing concerns around the trustworthiness of their results. We test the stability of predictions and explanations of different deep learning models, which differ between each other only via subtle changes to model settings, with each model trained over the same data. Our results show that the models produce similar predictions but different explanations, even when the differences in model architecture are due to arbitrary factors like random seeds. We compare this behaviour with traditional, interpretable, ‘glass-box models’, which show similar accuracies while maintaining stable explanations and predictions. Finally, we show a methodology based on network analysis to compare deep learning models. Our analysis has implications for the adoption and risk management of future deep learning models by regulated institutions.

Keywords: Deep neural networks; fragility; robustness; explainability; regulation (search for similar items in EconPapers)
JEL-codes: C45 C52 G18 (search for similar items in EconPapers)
Pages: 49 pages
Date: 2023-09-01
New Economics Papers: this item is included in nep-big, nep-cmp, nep-ger and nep-reg
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.bankofengland.co.uk/-/media/boe/files/ ... ility-regulation.pdf Full text (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:boe:boeewp:1038

Access Statistics for this paper

More papers in Bank of England working papers from Bank of England Bank of England, Threadneedle Street, London, EC2R 8AH. Contact information at EDIRC.
Bibliographic data for series maintained by Digital Media Team ().