Neural Network Application in Financial Area

Abstract

Forecasting financial data is an extremely important issue and it is a good opportunity to demonstrate the capabilities of the neural networks. The objective of this study is to develop a neural network model for forecasting the direction of movement of financial data one step forward. The architecture of a neural network uses four different technical indicators, which are based on the raw data and the current day of the week. The training method is algorithm with back propagation of the error. The program realization and experimental results are considered in this article.