Stock price prediction by using a combination of neural networks and genetic algorithms

This paper presents a designed model to predict stock prices by using a combination of neural networks and genetic algorithms and reducing prediction errorusing this technique toward using artificial neural network techniques individually. After designing and implementation of this model, Using four criteria of error measurement the results of the two models are compared. The data of listed companies in Tehran Stock Exchange 2006 to 2010 is used for the input variables and Stock price. The results show that Hybrid model of neural networks and genetic algorithms had a much better predictor and higher speed than single neural networks to predict stock prices.