PREDICTION OF FINANCIAL TIME SERIES USING ARTIFICIAL NEURAL NETWORKS

摘要

With the development of information technology, modern methods of soft computing for analysing financial time series are at the forefront. The aim of the paper is to analyse the predictive ability of artificial neural networks in predicting the stock indices. The performance of dynamic nonlinear autoregressive networks with a different number of time delays were analysed. It can be stated that this type of neural network should be incorporated into the technical analysis of stock markets.