Abstract
The purpose of the study is to investigate comparative ability of accounting information to predict indices volatility of companies listed in Tehran Stock Exchange using intelligent methods including Support Vector Machine, Artificial Neural Network and classic Logistic Regression model. Sample of study ...
Read More
The purpose of the study is to investigate comparative ability of accounting information to predict indices volatility of companies listed in Tehran Stock Exchange using intelligent methods including Support Vector Machine, Artificial Neural Network and classic Logistic Regression model. Sample of study includes 91 companies listed in Tehran Stock Exchange which have been classified in 9 industry group during time period of 2003-3013. Considering 11 corporate financial variables, study results show that despite predicting ability of around 60% by Support Vector Machine and Artificial Neural Network, there is significant difference between actual and predicted results. Also, classic Logistic Regression model can explain only 4% industries’ indices volatility using selected 11 corporate financial variables. Finally, although intelligent methods are superior to classic methods, accounting information solely aren’t well-explainer variables for predicting industry index volatility and variety of variables such as financial, political, economical … are effective in predicting industry index volatility.
H etemadi; H farzani; A rahmani
Volume 9, Issue 36 , January 2012, , Pages 23-51
Abstract
Choosing between debt financing and capital financing influenced by internal and external factors impacting companies' capital structure. The main goal of determining capital structure is to recognize the combination of financial resources to maximize stockholders' wealth. Because of the qualitative ...
Read More
Choosing between debt financing and capital financing influenced by internal and external factors impacting companies' capital structure. The main goal of determining capital structure is to recognize the combination of financial resources to maximize stockholders' wealth. Because of the qualitative aspects of capital formation in high-tech companies, there has been huge investments in these companies which doesn’t seem to be a rational behavior in the investment community; Therefore it seems necessary to compare high-tech and traditional company’s capital structure. In this paper, in order to investigate the capital structure of high-tech and traditional companies and also comparing linear and non-linear models, companies are divided into two groups, high-tech and traditional companies. We collected year-company data of 378 companies during 2004- 2009 for the analysis using multiple regression and artificial neural network. The findings of this study indicate that liability ratio and financial leverage decisions in two above mentioned companies are different. The capital structure criterion in both industries has significantly different and non-linear models of capital structure in comparison with linear ones are more powerful in prediction
