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

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

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

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.

源语言英语
主期刊名Cyber Security Intelligence and Analytics
编辑Zheng Xu, Kim-Kwang Raymond Choo, Ali Dehghantanha, Mohammad Hammoudeh, Reza Parizi
出版商Springer Verlag
1007-1014
页数8
ISBN(印刷版)9783030152345
DOI
出版状态已出版 - 2020
已对外发布
活动International Conference on Cyber Security Intelligence and Analytics, CSIA 2019 - Shenyang, 中国
期限: 21 2月 201922 2月 2019

出版系列

姓名Advances in Intelligent Systems and Computing
928
ISSN(印刷版)2194-5357
ISSN(电子版)2194-5365

会议

会议International Conference on Cyber Security Intelligence and Analytics, CSIA 2019
国家/地区中国
Shenyang
时期21/02/1922/02/19

指纹

探究 'The Impact Factors of Neural Network Based Time Series Prediction: Taking Stock Price as an Example' 的科研主题。它们共同构成独一无二的指纹。

引用此