STOCK PRICE FORECASTING WITH COMPUTATIONAL INTELLIGENCE TECHNIQUES: ISE APPLICATION

The main aim of this study is to design an expert system where the intervene of the user to the complex forecasting system is minimized by employing computational intelligence techniques in financial markets. researchers are interested in forecasting stock prices by using technical indicators. artificial neural networks are one of the soft computing techniques that is used for forecasting stock prices. the user of the neural network must decide the size of the hidden layer and must select the optimal feature subset to obtain the best forecasting performance from network. in this study an expert system which is based on genetic algorithms is designed to optimize the parameters of the network. technical indicators are calculated using price and volume information of day t. feature selection and parameter optimization is handled simultaneusly by using genetic algorithms. expert system is used to forecast closing prices of day t+1. the results indicate that optimized model outperformed the alternative model in terms of statistical performance.