British Journal of Economics, Finance and Management Sciences 37
October 2011, Vol. 2 (1)
© 2011 British Journals ISSN 2048-125X
Hybrid Financial Analysis Model for Predicting Bankruptcy
Gholamreza Jandaghi, Ph.D.
Professor, University of Tehran, Iran
Reza Tehrani, Ph.D.
Associate Professor, University of Tehran, Iran
Parvaneh Pirani, M.Sc.
University of Tehran, Qom College, Iran
Ali Mokhles, M.Sc.
University of Shahid Bahonar, Kerman, Iran
Abstract
The incidence of important bankruptcy cases has led to a growing interest in developing bankruptcy
prediction models. Bankruptcy is a defective process and incurs costs on different stakeholders. By this time,
several methods have been developed for predicting bankruptcy, including statistical and artificial
intelligence techniques. Hybrid models have proven be a promising approach for classification system for
predicting bankruptcy. This paper proposes a hybrid financial analysis model including static and trend
analysis models to construct and train a back-propagation neural network (BPN) model.BPN model was
applied to classify bankrupt and non-bankrupt Iranian firms listed in Tehran stock exchange (TSE) which
provides a high predication rate. Sensitivity analysis determines that leverage financial ratio play important
role in predicting bankruptcy.
Keywords: Financial distress, Hybrid financial analysis, artificial neural network
Introduction
Prediction and analysis of corporate financial performance is a crucial phenomenon in a developing country
like Iran. The health and success of the firms are of widespread concern to policy makers, industry
participants, investors, and managers. (O‟Leary, 1998) The prediction of bankruptcy is one of the major
activities to audit enterprise risks and/or uncertainties. Business failure can be defined as a situation that a
firm cannot pay lenders, preferred stock shareholders, and suppliers, a bill is overdraw, or the law makes the
firm go bankruptcy (Dimitras, Zanakis, & Zopounidis, 1996). Bankruptcy is a defective process which
disturbs utilization of investment opportunity and waste resources. Bankruptcy incurs costs on beneficiary as
investing bank, stakeholders, debtors, and business partner and company staff.
Bankruptcy is not an impulsive outcome and it grows constantly in stages. Thus, the development of
financial analysis models to predict business failures can be thought of as „early warning systems‟, which
proves to be very helpful for managers, and relevant authorities who can prevent the occurrence of failures.
(Atiya, 2001) In addition, these models are able to assist the decision-makers of financial institutions to
evaluate, assess and select the firms to collaborate with or invest in (Ahn,Cho, & Kim, 2000; Balcaen &
Ooghe, 2006, Etemaid,et.al 2009)