The value of text for small business default prediction: a deep learning approach
The value of text for small business default prediction: a deep learning approach
Compared to consumer lending, Micro, Small and Medium Enterprise (mSME) credit risk modelling is particularly challenging, as, often, the same sources of information are not available. Therefore, it is standard policy for a loan officer to provide a textual loan assessment to mitigate limited data availability. In turn, this statement is analysed by a credit expert alongside any available standard credit data. In our paper, we exploit recent advances from the field of Deep Learning and Natural Language Processing (NLP), including the BERT (Bidirectional Encoder Representations from Transformers) model, to extract information from 60000 textual assessments provided by a lender. We consider the performance in terms of the AUC (Area Under the receiver operating characteristic Curve) and Brier Score metrics and find that the text alone is surprisingly effective for predicting default. However, when combined with traditional data, it yields no additional predictive capability, with performance dependent on the text’s length. Our proposed deep learning model does, however, appear to be robust to the quality of the text and therefore suitable for partly automating the mSME lending process. We also demonstrate how the content of loan assessments influences performance, leading us to a series of recommendations on a new strategy for collecting future mSME loan assessments.
Deep Learning, OR in banking, Risk analysis, Small business lending, Text mining
758-771
Stevenson, Matthew Paul
c11bc02f-acf9-4e13-a703-8ed273bcd4e8
Mues, Christophe
07438e46-bad6-48ba-8f56-f945bc2ff934
Bravo, Cristián
d2e3a1d8-74fa-4300-ad91-26856eca161c
1 December 2021
Stevenson, Matthew Paul
c11bc02f-acf9-4e13-a703-8ed273bcd4e8
Mues, Christophe
07438e46-bad6-48ba-8f56-f945bc2ff934
Bravo, Cristián
d2e3a1d8-74fa-4300-ad91-26856eca161c
Stevenson, Matthew Paul, Mues, Christophe and Bravo, Cristián
(2021)
The value of text for small business default prediction: a deep learning approach.
European Journal of Operational Research, 295 (2), .
(doi:10.1016/j.ejor.2021.03.008).
Abstract
Compared to consumer lending, Micro, Small and Medium Enterprise (mSME) credit risk modelling is particularly challenging, as, often, the same sources of information are not available. Therefore, it is standard policy for a loan officer to provide a textual loan assessment to mitigate limited data availability. In turn, this statement is analysed by a credit expert alongside any available standard credit data. In our paper, we exploit recent advances from the field of Deep Learning and Natural Language Processing (NLP), including the BERT (Bidirectional Encoder Representations from Transformers) model, to extract information from 60000 textual assessments provided by a lender. We consider the performance in terms of the AUC (Area Under the receiver operating characteristic Curve) and Brier Score metrics and find that the text alone is surprisingly effective for predicting default. However, when combined with traditional data, it yields no additional predictive capability, with performance dependent on the text’s length. Our proposed deep learning model does, however, appear to be robust to the quality of the text and therefore suitable for partly automating the mSME lending process. We also demonstrate how the content of loan assessments influences performance, leading us to a series of recommendations on a new strategy for collecting future mSME loan assessments.
Text
The value of text for small business default prediction
- Accepted Manuscript
More information
Accepted/In Press date: 5 March 2021
e-pub ahead of print date: 13 March 2021
Published date: 1 December 2021
Additional Information:
Funding Information:
This work was supported by the Economic and Social Research Council [grant number ES/P000673/1]. The last author acknowledges the support of the Natural Sciences and Engineering Research Council of Canada (NSERC) [Discovery Grant RGPIN-2020-07114]. This research was undertaken, in part, thanks to funding from the Canada Research Chairs program. The authors acknowledge the use of the IRIDIS High Performance Computing Facility, and associated support services at the University of Southampton, in the completion of this work.
Funding Information:
This work was supported by the Economic and Social Research Council [grant number ES/P000673/1 ]. The last author acknowledges the support of the Natural Sciences and Engineering Research Council of Canada (NSERC) [Discovery Grant RGPIN-2020-07114 ]. This research was undertaken, in part, thanks to funding from the Canada Research Chairs program.
Publisher Copyright:
© 2021 Elsevier B.V.
Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.
Keywords:
Deep Learning, OR in banking, Risk analysis, Small business lending, Text mining
Identifiers
Local EPrints ID: 448067
URI: http://eprints.soton.ac.uk/id/eprint/448067
ISSN: 0377-2217
PURE UUID: 1e31b765-da72-4410-ad31-ba16d7494e78
Catalogue record
Date deposited: 01 Apr 2021 15:41
Last modified: 26 Jul 2024 01:57
Export record
Altmetrics
Contributors
Author:
Matthew Paul Stevenson
Author:
Cristián Bravo
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics