Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/286257 
Title (translated): 
The usefulness of Deep Learning in the prediction of business failure at the European level
Year of Publication: 
2021
Citation: 
[Journal:] Revista de Métodos Cuantitativos para la Economía y la Empresa [ISSN:] 1886-516X [Volume:] 32 [Year:] 2021 [Pages:] 392-414
Publisher: 
Universidad Pablo de Olavide, Sevilla
Abstract (Translated): 
In this paper we intend to substantiate the usefulness of Deep Learning, especially feedforward neuronal networks, in the prediction of business failure. This methodology provides very good results in terms of predictive performance when large sample sizes are available. Therefore, we have developed a business failure prediction model for European companies, based on this algorithm on a sample of 61,624 companies, of which 12,128 were declared bankrupt in 2016. As independent variables were considered ratios, and economic and financial data obtained from the financial statements for the year preceding the date of failure. Deep Learning achieves a predictive performance of 94%, where companies with larger size and lower solvency are more prone to failure. The obtained results have been tested on an independent test sample, different from that used to estimate and train the model.
Subjects: 
business failure
Deep Learning
machine learning
financial ratios
prediction model
JEL: 
C53
Persistent Identifier of the first edition: 
Creative Commons License: 
cc-by-sa Logo
Document Type: 
Article

Files in This Item:
File
Size
809.59 kB





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.