Forecasting of Financial Markets via Neural Network

Artificial neural network is one of the intelligent methods in Artificial Intelligence. There are many decisions of different tasks using neural network approach. The forecasting problems are high challenge and researchers use different methods to solve them. The financial tasks related to forecasting, classification and management using artificial neural network are considered. The technology and methods for prediction of financial data as well as the developed system for forecasting of financial markets via neural network are described in the paper. The designed architecture of a neural network using four different technical indicators is presented. The developed neural network is used for forecasting movement of stock prices one day ahead and consists of an input layer, one hidden layer and an output layer. The training method is a training algorithm with back propagation of the error. The main advantage of the developed system is self-determination of the optimal topology of neural network, due to which it becomes flexible and more precise. The proposed system with neural network is universal and can be applied to various financial instruments using only basic technical indicators as input data. Key-Words: neural networks, forecasting, training algorithm, financial indicators, backpropagation