The Development of Forecasting Model for Coherent Risk in Exchange Companies: Accounting data Approach

Iran Stock Exchange has developed a lot in recent years. Today, the importance of forecasting and its benefits for decision-making and policy-making from various dimensions, especially in the field of investment, is not hidden from anyone. Risk is one of the first concerns of investors and is an important criterion in decision making. Value at risk as a risk measure has given way to measuring a variety of risks, but despite the high efficiency of this model due to some shortcomings, including the lack of aggregation feature of a coherent risk measure. Conditional Risk Value (CvaR) is considered as a coherent risk measure that has recently been welcomed and has been proposed as a useful tool for measuring risk.To predict the risk, various models have been presented so far, each of which has its strengths and weaknesses. Some of them are weak in terms of lack of appropriate theoretical foundations and others have not shown proper efficiency in practice despite using appropriate theoretical foundations. Provide adequate empirical risk assessment that helps both investors and anticipate unexpected risks that may threaten companies. In recent years, much attention has been paid to the application of neural network models and hybrid models. In the present study, a combined model of coherent risk prediction is presented and developed using fuzzy neural network inference system (ANFIS) based on Markov switching models and Garch family models.