FINANCIAL KNOWLEDGE OF SECURITY ANALYSIS (FINANCIAL STUDIES)
Year:2016 | Volume:9 | Issue:29|Papers Count:8

This study tends to model Gordon relation using feed forward neural network approach for Tehran Stock Exchange listed companies. In this research, the examination of Gordon model with a nonlinear approach is discussed and the results are compared with linear regression. The examination of nonlinear Gordon model using neural network has not been considered in the studies as yet. In this research, data for 247 companies and 1135 observations (firm- year) between 2006- 2013 are used (unbalanced panel). Comparative analysis of results for linear regression and nonlinear neural network approaches shows that the coefficient of determination for neural network approach is higher than the coefficient of determination for linear regression, so using nonlinear model can improve prediction power of model and lead to more profitable investment strategies. In the modeling procedure, various structures of network are tested by changing the number of neurons for getting optimal network.

In this study, Discriminant Analysis (DA) model are used to estimate manipulation of stock prices in Tehran Stock Exchange. In this study, first by using screening data method, a sample of 345 companies listed in Tehran Stock Exchange were selected and then information about the 'TEDPIX' index, closing price, volatility of closing price and trading volume in the time frame years 1387 to 1391 were collected. Afterwards the selected companies categorized into manipulated and non-manipulated groups by using duration dependence test and skewness & kurtosis test. Then with scrutiny of the trend of Tedpix's chart and volume chart of the manipulated group, Start of price manipulation is determined. In next step by using Linear Discriminant Function (LDF) and Quadratic Discriminant Function (QDF) and by using closing price, volatility of closing price and trading volume variables and also using information in range one year before starting manipulation group and in range four years for non-manipulation group, designed models for forecasting manipulation. At the end, the prediction ability of the models was examined. According to the results, the prediction ability of LDF model is 56% and the prediction ability of QDF model is 73%.

Markowitz optimization problem and to determine the efficient frontier of investment, when the number of assets and restrictions on investment in the market is low, the mathematical model is solved. But this mathematical approach can reply different provider that sometimes it is more accurate and more complete. In this paper, we examine the dependence structure between time series Tehran Stock Exchange market indices and exchange rate of the dollar and its impact on the efficient frontier portfolios have covered.The results show that the upper tail dependence indices is less than the lower tail dependence, this means that the decline in the dollar exchange rate indices are reduced, but with the rise in the dollar exchange rate accepted in Tehran stock Exchange index increase is lower. We also propose a new optimization program where the risk is worth the risk and return of joint function is estimated. The results show that the upper tail dependence indices is less than the lower tail dependence.

This article uses copula-GARCH model and semi parametric approach to detach non-Gaussian conditional distribution to marginal densities and copula functions. This statistical characteristic conceives analysis of dynamic and extreme dependency in nonlinear and asymmetric structure. This modern statistical tool uses to study structure of Iran financial market dependency to domestic and international market during period of 3 August 2013 to 16 August 2015.Daily observations consist of Free Float Index, official exchange rate(Rial/Dollar), international gold price(in terms of Dollar), and OPEC Basket Price(Barrel/Dollar). Results show that stock exchange dependency to the markets is completely dynamic and there is non-correlation only in some time point. Structure of tail distribution dependency implies that there is asymmetric extreme dependency in a way that stock exchange dependency to the markets is stronger during expansion rather than recession. This findings show that investors are optimistic and more sensitive to good news during the period under study.

The optimal portfolio selection problem to find an optimal way to allocate a fixed amount of capital to a set of available asset swhich aims to maximize expected returns and minimize risk at the same time, to take place. In this Study is shown that an investor with n risky share, how to reach certain profits with minimal risk. Such a portfolio, efficient portfolio is called. For this purpose, the study of evolutionary algorithms, Genetic Algorithm, Imperialist Competitive Algorithm and Particle Swarm Optimization algorithm, also with regard to the basic constraints on the investment, we use these practical methods to solve the portfolio optimization problem. Practical results for the portfolio optimization problem in the Tehran Stock Exchange, of the30 company' sactivein the industry with the selection of20companies along with their validation, is obtained. Aims to help investors better and more practical to select different stocks and thus is an effective investment.

Identifying the important factors of risk and return and optimal resources is one of the most important element to reach the maximum return. This would help individuals and institutions investors searching the best strategy to help them reaching this. This research try to study the five factor arbitrage pricing model based on the Cerhat four factor model plus stock liquidity and testing the empirical model in Iran Stock Exchange.For do that we have used the panel data model for the period of 2008-2012 for 173 active unit in Tehran Stock Exchange.

The purpose of this research is testing of existence explosive behavior and identifying periods with price bubbles in stock market of Iran in January 2008 until September 2014. In periods that multiple price bubbles occurs, process of time series change from random walk to an explosive behavior. In this cases most of the traditional unit roots tests has less power in detecting bubbles because It is necessary that unit root test is able to detecting changes in time series from I(0) to I(1) during bubbles and changing I(1) to I(0) during collapse. For this reason, in the present study Sup ADF and Generalized SADF tests that’s based on right tail augmented Dickey-Fuller unit root test that recently Introduced by Phillips et.al (2014) was applied for testing explosive behavior. According to the results, existence of bubbles in the 15 months of samples, and specially July 2013 until December 2013 is confirmed.