Forecasting stock price using soft computing techniques

Forecasting stock price is a important challenging task in the real world because more and more money is involved and they are affected by many social, economic, political and psychological factors. Numerous machine learning procedures have been used to fore see developments in stock cost. Machine learning classifiers include expanding the past encounters into the future actives. The proposed framework presents another hereditary calculation for forecast of monetary execution with information sets from a known source. The objective is to deliver a GA-based procedure for expectation of securities exchange execution alongside an acquainted principle classifier from an information set. We developed a genetic fuzzy based model with the ability of rule based extraction to predict next day stock price. We evaluate capacity of the proposed approach by applying it to the banking sector stocks and compare the outcome with the previous models.