Author/Authors :
Salehi، Adele Amini نويسنده Department of Accounting, Mashhad Branch, Islamic Azad University, Mashhad, Iran Salehi, Adele Amini , Shiri، Mahmuod Muosavi نويسنده Department of Management, Economics and Accounting, Payame Noor University, Mashhad, Iran Shiri, Mahmuod Muosavi , Yazdi، Hoda Majbouri نويسنده Department of Accounting, Mashhad Branch, Islamic Azad University, Mashhad, Iran Yazdi, Hoda Majbouri , Filsaraei، Mahdi نويسنده Department of Accounting, Bojnourd Branch, Islamic Azad University, Bojnourd, Iran Filsaraei, Mahdi
Abstract :
Nowadays, many studies have been conducted on corporate financial distress anticipation using data mining techniques. Artificial Neural Networks, Support Vector Machine and Decision Tree Algorithms are three current methods for data mining to anticipate corporate financial distress. This study compares the anticipation accuracy of these three methods in anticipation of corporate financial distress. The effect of combining these three methods is also studied through relative majority voting method to improve anticipation of corporate financial distress.
Statistical population of this study includes 100 sound companies and 100 distressed companies, active in Tehran Stock Exchange Market between 2005 and 2011, which were studied for the two years of t and t-1. Findings of the study show that decision tree with 95.95% accuracy for the year t and artificial neural network with 89.92% accuracy for the year t-1 have the highest level of efficiency to anticipate corporate financial distress. The results also show that combination of relative majority voting with 93.89% accuracy in the year t and 89.89% accuracy in the yea t-1 is able to anticipate corporate financial distress.
