Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.14279/29870
Title: A Deep Learning Approach for Dynamic Balance Sheet Stress Testing
Authors: Petropoulos, Anastasios 
Siakoulis, Vasilis 
Panousis, Konstantinos P. 
Papadoulas, Loukas 
Chatzis, Sotirios P. 
Major Field of Science: Engineering and Technology
Field Category: Mechanical Engineering
Keywords: Bayesian Model Averaging;Bayesian Model Averaging;Constant balance sheet;Deep Learning;Dynamic balance sheet;Forecasting;Neural Networks;Stress Testing
Issue Date: 2-Nov-2022
Source: Proceedings of the 3rd ACM International Conference on AI in Finance, 2022, 2-4 November, New York, pp. 53 - 61
Start page: 53
End page: 61
Conference: 3rd ACM International Conference on AI in Finance, ICAIF 
Abstract: In the aftermath of the financial crisis, supervisory authorities have considerably altered the mode of operation of financial stress testing. Despite these efforts, significant concerns and extensive criticism have been raised by market participants regarding the considered unrealistic methodological assumptions and simplifications. Current stress testing methodologies attempt to simulate the risks underlying a financial institution's balance sheet by using several satellite models. This renders their integration a really challenging task, leading to significant estimation errors. Moreover, advanced statistical techniques that could potentially capture the non-linear nature of adverse shocks are still ignored. This work aims to address these criticisms and shortcomings by proposing a novel approach based on recent advances in Deep Learning towards a principled method for Dynamic Balance Sheet Stress Testing. Experimental results on a newly collected financial/supervisory dataset, provide strong empirical evidence that our paradigm significantly outperforms traditional approaches; thus, it is capable of more accurately and efficiently simulating real world scenarios.
URI: https://hdl.handle.net/20.500.14279/29870
ISBN: 9781450393768
DOI: 10.1145/3533271.3561656
Rights: © Copyright held by the owner/author(s).
Type: Conference Papers
Affiliation : Cyprus University of Technology 
Appears in Collections:Άρθρα/Articles

Files in This Item:
File Description SizeFormat
a deep Learning.pdf720.66 kBAdobe PDFView/Open
CORE Recommender
Show full item record

Page view(s)

172
Last Week
3
Last month
7
checked on Nov 6, 2024

Download(s)

86
checked on Nov 6, 2024

Google ScholarTM

Check

Altmetric


This item is licensed under a Creative Commons License Creative Commons