The Impact Factors of Neural Network Based Time Series Prediction: Taking Stock Price as an Example

Yue Hou; Heng Liu; Bin Xie; Feng Ding

doi:10.1007/978-3-030-15235-2_134

The Impact Factors of Neural Network Based Time Series Prediction: Taking Stock Price as an Example

Yue Hou^*, Heng Liu, Bin Xie, Feng Ding

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Compared with the traditional time series prediction model, neural network has obvious advantages for the analysis of nonlinear time series data. However, the topology structure and the training algorithm of neural network have a great influence on the prediction accuracy. Taking stock data as an instance, this paper analyzes the impacts factors of prediction ability of neural network such as topology structure, training algorithm and dataset. The experimental results show that the training algorithm and the size of dataset have significant influence on the performance of neural network.

Original language	English
Title of host publication	Cyber Security Intelligence and Analytics
Editors	Zheng Xu, Kim-Kwang Raymond Choo, Ali Dehghantanha, Mohammad Hammoudeh, Reza Parizi
Publisher	Springer Verlag
Pages	1007-1014
Number of pages	8
ISBN (Print)	9783030152345
DOIs	https://doi.org/10.1007/978-3-030-15235-2_134
Publication status	Published - 2020
Externally published	Yes
Event	International Conference on Cyber Security Intelligence and Analytics, CSIA 2019 - Shenyang, China Duration: 21 Feb 2019 → 22 Feb 2019

Publication series

Name	Advances in Intelligent Systems and Computing
Volume	928
ISSN (Print)	2194-5357
ISSN (Electronic)	2194-5365

Conference

Conference	International Conference on Cyber Security Intelligence and Analytics, CSIA 2019
Country/Territory	China
City	Shenyang
Period	21/02/19 → 22/02/19

Keywords

Impact factors
Neural network
Time series prediction

Access to Document

10.1007/978-3-030-15235-2_134

Cite this

Hou, Y., Liu, H., Xie, B., & Ding, F. (2020). The Impact Factors of Neural Network Based Time Series Prediction: Taking Stock Price as an Example. In Z. Xu, K.-K. R. Choo, A. Dehghantanha, M. Hammoudeh, & R. Parizi (Eds.), Cyber Security Intelligence and Analytics (pp. 1007-1014). (Advances in Intelligent Systems and Computing; Vol. 928). Springer Verlag. https://doi.org/10.1007/978-3-030-15235-2_134

Hou, Yue ; Liu, Heng ; Xie, Bin et al. / The Impact Factors of Neural Network Based Time Series Prediction : Taking Stock Price as an Example. Cyber Security Intelligence and Analytics. editor / Zheng Xu ; Kim-Kwang Raymond Choo ; Ali Dehghantanha ; Mohammad Hammoudeh ; Reza Parizi. Springer Verlag, 2020. pp. 1007-1014 (Advances in Intelligent Systems and Computing).

@inproceedings{bc0738bba6564a018684039fa84e2aad,

title = "The Impact Factors of Neural Network Based Time Series Prediction: Taking Stock Price as an Example",

abstract = "Compared with the traditional time series prediction model, neural network has obvious advantages for the analysis of nonlinear time series data. However, the topology structure and the training algorithm of neural network have a great influence on the prediction accuracy. Taking stock data as an instance, this paper analyzes the impacts factors of prediction ability of neural network such as topology structure, training algorithm and dataset. The experimental results show that the training algorithm and the size of dataset have significant influence on the performance of neural network.",

keywords = "Impact factors, Neural network, Time series prediction",

author = "Yue Hou and Heng Liu and Bin Xie and Feng Ding",

note = "Publisher Copyright: {\textcopyright} 2020, Springer Nature Switzerland AG.; International Conference on Cyber Security Intelligence and Analytics, CSIA 2019 ; Conference date: 21-02-2019 Through 22-02-2019",

year = "2020",

doi = "10.1007/978-3-030-15235-2_134",

language = "English",

isbn = "9783030152345",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer Verlag",

pages = "1007--1014",

editor = "Zheng Xu and Choo, {Kim-Kwang Raymond} and Ali Dehghantanha and Mohammad Hammoudeh and Reza Parizi",

booktitle = "Cyber Security Intelligence and Analytics",

address = "Germany",

}

Hou, Y, Liu, H, Xie, B & Ding, F 2020, The Impact Factors of Neural Network Based Time Series Prediction: Taking Stock Price as an Example. in Z Xu, K-KR Choo, A Dehghantanha, M Hammoudeh & R Parizi (eds), Cyber Security Intelligence and Analytics. Advances in Intelligent Systems and Computing, vol. 928, Springer Verlag, pp. 1007-1014, International Conference on Cyber Security Intelligence and Analytics, CSIA 2019, Shenyang, China, 21/02/19. https://doi.org/10.1007/978-3-030-15235-2_134

The Impact Factors of Neural Network Based Time Series Prediction: Taking Stock Price as an Example. / Hou, Yue; Liu, Heng; Xie, Bin et al.
Cyber Security Intelligence and Analytics. ed. / Zheng Xu; Kim-Kwang Raymond Choo; Ali Dehghantanha; Mohammad Hammoudeh; Reza Parizi. Springer Verlag, 2020. p. 1007-1014 (Advances in Intelligent Systems and Computing; Vol. 928).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - The Impact Factors of Neural Network Based Time Series Prediction

T2 - International Conference on Cyber Security Intelligence and Analytics, CSIA 2019

AU - Hou, Yue

AU - Liu, Heng

AU - Xie, Bin

AU - Ding, Feng

PY - 2020

Y1 - 2020

N2 - Compared with the traditional time series prediction model, neural network has obvious advantages for the analysis of nonlinear time series data. However, the topology structure and the training algorithm of neural network have a great influence on the prediction accuracy. Taking stock data as an instance, this paper analyzes the impacts factors of prediction ability of neural network such as topology structure, training algorithm and dataset. The experimental results show that the training algorithm and the size of dataset have significant influence on the performance of neural network.

AB - Compared with the traditional time series prediction model, neural network has obvious advantages for the analysis of nonlinear time series data. However, the topology structure and the training algorithm of neural network have a great influence on the prediction accuracy. Taking stock data as an instance, this paper analyzes the impacts factors of prediction ability of neural network such as topology structure, training algorithm and dataset. The experimental results show that the training algorithm and the size of dataset have significant influence on the performance of neural network.

KW - Impact factors

KW - Neural network

KW - Time series prediction

UR - http://www.scopus.com/inward/record.url?scp=85065529751&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-15235-2_134

DO - 10.1007/978-3-030-15235-2_134

M3 - Conference contribution

AN - SCOPUS:85065529751

SN - 9783030152345

T3 - Advances in Intelligent Systems and Computing

SP - 1007

EP - 1014

BT - Cyber Security Intelligence and Analytics

A2 - Xu, Zheng

A2 - Choo, Kim-Kwang Raymond

A2 - Dehghantanha, Ali

A2 - Hammoudeh, Mohammad

A2 - Parizi, Reza

PB - Springer Verlag

Y2 - 21 February 2019 through 22 February 2019

ER -

The Impact Factors of Neural Network Based Time Series Prediction: Taking Stock Price as an Example

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this