Bankruptcy analysis using images and convolutional neural networks (2025)
- Authors:
- USP affiliated authors: PALETTA, FRANCISCO CARLOS - ECA ; MAZZON, JOSE AFONSO - FEA
- Unidades: ECA; FEA
- DOI: 10.1007/978-3-032-00206-8_15
- Subjects: ANÁLISE DE RISCO; REDES NEURAIS; MARKETING; INSTITUIÇÕES FINANCEIRAS
- Language: Inglês
- Abstract: The marketing departments of financial institutions strive to craft products and services that cater to the diverse needs of businesses of all sizes. However, it is evident upon analysis that larger corporations often receive a more substantial portion of available funds. This disparity arises from the relative ease of assessing the risk of default and bankruptcy in these more prominent companies. Historically, risk analysis studies have focused on data from publicly traded or stock exchange-listed companies, leaving a gap in knowledge about small and medium-sized enterprises (SMEs). Addressing this gap, this study introduces a method for evaluating SMEs by generating images for processing via a convolutional neural network (CNN). To this end, more than 10,000 images, one for each company in the sample, were created to identify scenarios in which the CNN can operate with higher assertiveness and reduced training error probability. The findings demonstrate a significant predictive capacity, achieving 97.8% accuracy, when a substantial number of images are utilized. Moreover, the image creation method paves the way for potential applications of this technique in various sectors and for different analytical purposes.
- Imprenta:
- Source:
- Este artigo NÃO possui versão em acesso aberto
-
Status: Nenhuma versão em acesso aberto identificada -
ABNT
TAVARES, Luiz Wanderley et al. Bankruptcy analysis using images and convolutional neural networks. Proceedings of the fifth France's International Conference on Complex Systems (FRCCS 2025). Tradução . Cham: Springer, 2025. . Disponível em: https://link.springer.com/chapter/10.1007/978-3-032-00206-8_15. Acesso em: 12 mar. 2026. -
APA
Tavares, L. W., Mazzon, J. A., Paletta, F. C., & Barros, F. M. de O. (2025). Bankruptcy analysis using images and convolutional neural networks. In Proceedings of the fifth France's International Conference on Complex Systems (FRCCS 2025). Cham: Springer. doi:10.1007/978-3-032-00206-8_15 -
NLM
Tavares LW, Mazzon JA, Paletta FC, Barros FM de O. Bankruptcy analysis using images and convolutional neural networks [Internet]. In: Proceedings of the fifth France's International Conference on Complex Systems (FRCCS 2025). Cham: Springer; 2025. [citado 2026 mar. 12 ] Available from: https://link.springer.com/chapter/10.1007/978-3-032-00206-8_15 -
Vancouver
Tavares LW, Mazzon JA, Paletta FC, Barros FM de O. Bankruptcy analysis using images and convolutional neural networks [Internet]. In: Proceedings of the fifth France's International Conference on Complex Systems (FRCCS 2025). Cham: Springer; 2025. [citado 2026 mar. 12 ] Available from: https://link.springer.com/chapter/10.1007/978-3-032-00206-8_15 - Vulnerabilidade ambiental
- Social marketing for women's health campaigns
- Plano de marketing social para a promoção da saúde: desenvolvimento de políticas de saúde pública orientada ao "cliente"
- A relação entre valores, práticas organizacionais e confiança de clientes no setor de serviços
- Modelo de suscetibilidade para a cultura de consumo global
- Electronic media use: towars and integrative model
- Programa de alimentacao do trabalhador: uma avaliacao historica e impactos socio-economicos
- Teste de um modelo teórico sobre o valor percebido do preço de um produto
- Política de atenção ao trabalho. [Depoimento]
- O relacionamento entre a administração estratégica e resultados empresariais: uma aplicação de modelos de PLS de segunda ordem a empresas brasileiras de software
Informações sobre a disponibilidade de versões do artigo em acesso aberto coletadas automaticamente via oaDOI API (Unpaywall).
Download do texto completo
| Tipo | Nome | Link | |
|---|---|---|---|
 |
003275382.pdf |
How to cite
A citação é gerada automaticamente e pode não estar totalmente de acordo com as normas
