Title :
A neural network based time series forecasting system
Author :
Kozarzewski, Bohdan
Author_Institution :
Univ. of Inf. Technol. & Manage., Rzeszów, Poland
Abstract :
Neural network based system is proposed as a tool supporting time series forecasting. Wavelets analysis is suggested for raw data preprocessing. The preprocessed data are fed into SOM neural networks for clustering. The system has been tested as a tool supporting stock market investment decisions and shows good prediction accuracy of the method. However effectiveness, measured by income from shares trading according to the system, is not satisfactory to the same extend.
Keywords :
forecasting theory; investment; self-organising feature maps; stock markets; time series; SOM neural networks; shares trading; stock market investment; time series forecasting system; wavelets analysis; Artificial neural networks; Autocorrelation; Data preprocessing; Economic forecasting; Information technology; Investments; Neural networks; Stock markets; Technology forecasting; Time series analysis; Artificial neural networks; stock market prediction; wavelets decomposition;
Conference_Titel :
Human System Interactions (HSI), 2010 3rd Conference on
Conference_Location :
Rzeszow
Print_ISBN :
978-1-4244-7560-5
DOI :
10.1109/HSI.2010.5514591
