DocumentCode
3068900
Title
A Novel Approach for Time Series Analysis Based RBF Neural Network
Author
Zou, Kaiqi ; Dong, Renfei
Author_Institution
Coll. of Inf. Eng., Univ. Key Lab. of Inf. Sci. & Eng., Dalian, China
Volume
3
fYear
2010
fDate
16-18 July 2010
Firstpage
139
Lastpage
142
Abstract
In this paper, we analyzed the highly nonlinear characteristics of the stock market and proposed a novel approach for time series analysis. This method is the use of RBF neural network analysis of time series and analysis of the initial analysis of the error also, and then combined with the analysis of two results to obtain new results. Using this method, we forecasted the trend of shares of China Unicom and achieved satisfactory results.
Keywords
forecasting theory; radial basis function networks; stock markets; time series; China Unicom; RBF neural network analysis; error analysis; stock market; time series analysis; Analytical models; Artificial neural networks; Biological neural networks; Predictive models; Radial basis function networks; Stock markets; Time series analysis; RBF; nonlinear; stock market; time series analysis;
fLanguage
English
Publisher
ieee
Conference_Titel
Information Technology and Applications (IFITA), 2010 International Forum on
Conference_Location
Kunming
Print_ISBN
978-1-4244-7621-3
Electronic_ISBN
978-1-4244-7622-0
Type
conf
DOI
10.1109/IFITA.2010.37
Filename
5634700
Link To Document