Forecasting Stock Exchange Movements Using Neural Networks: A Case Study

Author

Tahersima, Hanif ; Tahersima, Mohammadhossein ; Fesharaki, Morteza ; Hamedi, Navid

Author_Institution

Eng. Dev., RIPI, Tehran, Iran

fYear

2011

fDate

18-19 June 2011

Firstpage

123

Lastpage

126

Abstract

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.

Keywords

multilayer perceptrons; stock markets; time series; EURJPY closing price movements; Euro; Japanese Yen; financial time series; multilayer perceptron; neural network; stock exchange movement forecasting; Artificial neural networks; Complexity theory; Data models; Forecasting; Predictive models; Stock markets; Time series analysis; Exchange market; MLP neural network; Moving avrage filter; Step ahead predicton;

fLanguage

English

Publisher

ieee

Conference_Titel

Future Computer Sciences and Application (ICFCSA), 2011 International Conference on

Conference_Location

Hong Kong

Print_ISBN

978-1-4577-0317-1

Type

conf

DOI

10.1109/ICFCSA.2011.35

Filename

5968041