2011
DOI: 10.1016/j.eswa.2011.04.222
|View full text |Cite
|
Sign up to set email alerts
|

Forecasting stock indices with back propagation neural network

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

1
143
0
16

Year Published

2014
2014
2024
2024

Publication Types

Select...
6
3
1

Relationship

0
10

Authors

Journals

citations
Cited by 401 publications
(160 citation statements)
references
References 22 publications
1
143
0
16
Order By: Relevance
“…The month to month shutting value information with the Shanghai Composite Index from January 1993 to December 2009 are utilized to represent the utilization of the WDBP neural system based calculation in anticipating the stock record. To demonstrate the benefit of this new approach for stock file conjecture, the WDBP neural system is contrasted and the single Back Propagation neural system utilizing the genuine information set [4][5][6][7][8][9][10].…”
Section: Literature Reviewmentioning
confidence: 99%
“…The month to month shutting value information with the Shanghai Composite Index from January 1993 to December 2009 are utilized to represent the utilization of the WDBP neural system based calculation in anticipating the stock record. To demonstrate the benefit of this new approach for stock file conjecture, the WDBP neural system is contrasted and the single Back Propagation neural system utilizing the genuine information set [4][5][6][7][8][9][10].…”
Section: Literature Reviewmentioning
confidence: 99%
“…Initially, the segmentation of the database is done randomly in a training group (80% of the data), a test group (10% of the data) and a validation group (10% of the data). The random segmentation of networks for training is based on work published by several researchers [4,[15][16][17].…”
Section: A Hybrid Modelmentioning
confidence: 99%
“…In the last decades, several approaches have been proposed for time series analysis and forecasting. Two major classes of these approaches are the traditional statistical models and the soft computing approaches [2]. Statistical models generally assume that the time series under study is generated from a linear process [3].…”
Section: Introductionmentioning
confidence: 99%