خلاصة:
The analysis of financial distress is considered an important phenomenon for investors, creditors, and other users of financial information. Determining the probability of a company becoming distressed before the occurrence of distress is a very interesting and attractive subject and can be useful for both managers and investors and creditors. In this research, using information from 1350 companies over the period from 1387 to 1395 in the industry and mining sector of the Iranian capital market, the factors affecting financial distress and its prediction using artificial intelligence algorithms (Decision Tree method, Support Vector Machine, and Naive Bayes classification) using MATLAB 2017 software has been addressed. The results of the research indicate the direct impact of inflation and financial risk and the inverse impact of the ratio of non-executive managers, annual stock return, and operating cash flow ratio on financial distress. Additionally, the results show that the Decision Tree algorithm, using financial and economic data, has higher efficiency in predicting financial distress compared to the Naive Bayes and Support Vector Machine methods.
ملخص الجهاز:
"Investigating the relationship between corporate governance and systematic risk with the financial distress of companies listed on the Tehran Stock Exchange".
Given the preliminary results of the research which showed that the variables of non-employee director ratio, financial leverage (financial risk), annual stock return, inflation, and operating cash flow ratio have the highest importance in predicting financial distress, therefore, managers of the industry and mining sector of the capital market are advised to consider the mentioned variables for decision-making regarding the continuity of company activities.
Given the secondary results of the research which show that decision tree, support vector machine, and Naive Bayes algorithms have high power in predicting financial distress in the industry and mining sector, therefore, capital owners and company decision-makers are advised to use the predictive power of artificial intelligence algorithms, especially the decision tree method, in their decisions regarding investment in the industry and mining sector of the capital market.
Also, the results of this research can be practically considered by the managers of the industry and mining sector of the Iranian capital market, such that by predicting financial distress in companies 1.
In this research, binary logistic regression analysis was used via the input method at a five percent error level to identify factors affecting financial distress in the industry and mining sector of the capital market, and the results of this analysis were used as input variables to predict financial distress using artificial intelligence algorithms.
Ahmadi (2016) conducted a study on the relationship between corporate governance and systematic risk with the financial distress of companies listed on the Tehran Stock Exchange in the time period 2010 to 2014.
(
, 
, 
)
