Forecasting Stock Exchange Movements Using Neural Networks: A Case Study

Financial time series are very complex and dynamic, so they are characterized as chaotic time series. The major aim of this research is to forecast the stock exchange of Euro vs. Japanese Yen (EURJPY) closing price movements using hourly dataset from September 20, 2010 to January 21, 2011. One neural network (MLP) is used to predict the EURJPY closing price movements. The results of this study show that neuro-computational models are useful tools in forecasting stock exchange movements in emerging markets. These results also indicate that filtering of noises have an enormous effect on prediction improvements.