فهرست مطالب saeed falahatgar mottahedjoo

The purpose of this study is to develop a new approach to select effective variables in predicting financial distress using experts’ judgment and decision-making algorithms. Twenty nine financial ratios of financially distressed manufacturing companies according to Article 141 of the business Law were selected and the same number of healthy firms have been randomly selected from the companies which were listed in Tehran Stock Exchange between 1385 and 1395 using audited financial statements of one, two and three years before getting distressed. Then, using the statistical test and Dematel and Todim Fuzzy decision-making algorithms, the best financial ratios and their respective importance coefficients were selected and the prediction of financial distress was made using a support vector machine. Paired T-test results showed that accuracy difference of proposed model in predicting financial distress has been statistically significant in 5% level comparing to Altman Model and Logistic Regression Method for the years t-1, t-2, and t-3. The findings of the study showed that the proposed model has a significantly better performance in predicting distress than the Logistic regression method and Altman model in one, two and three years before financial distress.