Presentation Optimization portfolio model from market index prediction model despite of the long term memory with neural network

The effect economic variables at investment markets is the important subject in financial theory. Tehran stock exchange to have special position in country financial system and efficiency development investment market is dependent being active this constitution in country. Two important function Tehran exchange market are gathering small savings and available liquidity in society and guide them to production process in country. In this way presentation optimization portfolio model from market index prediction model and exchange return rate is impact. One of the tools with high accuracy and applicable for predicting was neural network why so accuracy isnot decrease with increasing thesis data and its accuracy was very higher than regeression, linear and non linear for prediction. After some tests from artificial neural network and adaptive neuro fuzzy inference system and support vector regression with matlab software has been done. We design a model with high accurancy for predicting rate of liquidity index and total return index and then we design Ideal optimization portfolio.