TENDENCIAS EN LA DETECCIÓN DE QUIEBRAS CORPORATIVAS: UN ANÁLISIS ENTRE MODELOS
The objective of the research is to analyze 30 researches related with the detection of corporate bankruptcies through a visualization map under the criterion: type of model. The results indicate that the most used models are the statistical techniques followed by neural networks, while the theoreti...
| Autores: | , |
|---|---|
| Tipo de recurso: | artículo |
| Estado: | Versión publicada |
| Fecha de publicación: | 2018 |
| País: | México |
| Institución: | UNIVERSIDAD AUTÓNOMA METROPOLITANA |
| Repositorio: | Denarius |
| Idioma: | español |
| OAI Identifier: | oai:denarius.izt.uam.mx:article/368 |
| Acceso en línea: | https://denarius.izt.uam.mx/index.php/denarius/article/view/368 |
| Access Level: | acceso abierto |
| Palabra clave: | Corporative bankruptcy Multiple discriminant analysis Black-Scholes Artificial neural networks Quiebras corporativas Análisis discriminante múltiple Redes neuronales artificiales |
| Sumario: | The objective of the research is to analyze 30 researches related with the detection of corporate bankruptcies through a visualization map under the criterion: type of model. The results indicate that the most used models are the statistical techniques followed by neural networks, while the theoretical formulas showed a little frequency in the field. On the other hand, it is show that the hybrid models are the most recent trend, which show the possibility of permeating under an evolutionary dynamic. Additionally, the performance among the models indicates that neural networks often outperform statistical techniques, nevertheless the hybrid models surpass their counterpart without exception. The limitation is that the studies analyzed include different sizes of firms and of economies, so the results are generalized. Finally, it is concluded that the hybrid networks can´t overcome some “deficiencies” (lack of interpretation of parameters), which explains –at least in part- the high frequency of using the statistical techniques. |
|---|