A comparison of corporate distress prediction models in Brazil: hybrid neural networks, logit models and discriminant analysis

Juliana Yim () and Heather Mitchell
Additional contact information
Juliana Yim: RMIT University
Heather Mitchell: RMIT University

Nova Economia, 2005, vol. 15, issue 1, pages 73-93

Abstract: This paper looks at the ability of a relatively new technique, hybrid ANN's, to predict corporate distress in Brazil. These models are compared with traditional statistical techniques and conventional ANN models. The results suggest that hybrid neural networks outperform all other models in predicting firms in financial distress one year prior to the event. This suggests that for researchers, policymakers and others interested in early warning systems, hybrid networks may be a useful tool for predicting firm failure.

Keywords: hybrid neural networks; corporate failures (search for similar items in EconPapers)
JEL-codes: G33 C45 (search for similar items in EconPapers)
Date: 2005

Downloads: (external link)
http://www.face.ufmg.br/novaeconomia/sumarios/v15n1/150103.pdf (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: http://EconPapers.repec.org/RePEc:nov:artigo:v:15:y:2005:i:1:p:73-93

Ordering information: This journal article can be ordered from
Av. Antonio Carlos, 6627 - Predio da FACE Belo Horizonte, 31270-901 Brazil
http://www.face.ufmg.br/novaeconomia/

Access Statistics for this article

Nova Economia is edited by Hugo E. A. da Gama Cerqueira

More articles in Nova Economia from Economics Department, Universidade Federal de Minas Gerais (Brazil)
Address: Av. Antonio Carlos, 6627 - Predio da FACE Belo Horizonte, 31270-901 Brazil
Contact information at EDIRC.
Series data maintained by Hugo Cerqueira ().