Premium
PREDICTING FINANCIAL DISTRESS IN THE AUSTRALIAN FINANCIAL SERVICE INDUSTRY
Author(s) -
YIM JULIANA,
MITCHELL HEATHER
Publication year - 2007
Publication title -
australian economic papers
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.351
H-Index - 15
eISSN - 1467-8454
pISSN - 0004-900X
DOI - 10.1111/j.1467-8454.2007.00326.x
Subject(s) - artificial neural network , financial distress , service (business) , warning system , financial services , business , finance , actuarial science , econometrics , economics , computer science , artificial intelligence , financial system , marketing , telecommunications
This paper looks at the ability of a relatively new technique, a non‐linear extension of the Granger thick model concept, hybrid ANN's, to predict failure of financial service firms in Australia. 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 failure for up to two years prior to the event. This suggests that for researchers, policymakers and others interested in early warning systems, hybrid network may be a useful tool for predicting firm failure.