Prediction of Financial Crisis Using Imperialist Competitive Algorithm: Evidence from Tehran Stock Exchange

摘要

Since the accuracy of corporate financial crisis prediction is very important for financialinstitutions, investors and governments, many methods have been employed fordeveloping effective prediction models. The aim of this research was twofold: (1)propose a new classification method following the artificial intelligence, whichemploys an Imperialist Competitive Algorithm (ICA) to the problem, (2) predict thefinancial crisis in Iranian firms listed inTehran stock exchange (TSE) using principalcomponent analysis Imperialist Competitive Algorithm (PCAICA) model and itsrelated financial ratios.For this purpose the sample was 60 registered firms in TehranStock Exchange and the financial information was gathered with use of their financialreports within 21 years beginning from 1991 and ending to 2012 and desired financialratios were extracted. The experimental results show that the proposed model is goodalternative for financial crisis prediction.