Recalculation of the first Hungarian bankruptcy-prediction model using neural networks

• Authors: Virag M. , Kristof T.
• Languages of publication: HU

Abstracts

EN

The article attempts to say whether the latest bankruptcy prediction techniques are more reliable in Hungary's case than traditional mathematical/statistical ones. Simulation experiments carried out on the database of the first domestic bankruptcy-prediction model show clearly that neural-network models possess greater classification accuracy than the models based on discriminant analysis and logistic regression analysis elaborated in the 1990s. The article presents the main results, analyses the reasons for differences, and draws up constructive proposals for further development of domestic bankruptcy-prediction practice.

Keywords

EN

BANKRUPTCY PREDICTION TECHNIQUES; FINANCIAL ANALYSIS; NEURAL- NETWORK MODELS

Discipline

• ECONOMICS: ECONOMICS

• Publisher: Committee for Economic Sciences of the Hungarian Academy of Sciences
• Journal: Kozgazdasagi Szemle (Economic Review)
• Year: 2005
• Volume: 52
• Issue: 2
• Pages: 144-162
• Document type: ARTICLE

Contributors

author

Virag M.

author

Kristof T.

• M. Virag, no address given, contact the journal editor

Identifiers

CEJSH db identifier

07HUAAAA02956032