A neural-network-based nonlinear metamodeling approach to financial time series forecasting
文献类型：期刊论文
| 作者 | Yu, Lean1; Wang, Shouyang1 ; Lai, Kin Keung2
|
| 刊名 | APPLIED SOFT COMPUTING
 |
| 出版日期 | 2009-03-01 |
| 卷号 | 9期号:2页码:563-574 |
| 关键词 | Artificial neural networks Metamodeling Data sampling Meta-learning PCA Financial time series forecasting |
| ISSN号 | 1568-4946 |
| DOI | 10.1016/j.asoc.2008.08.001 |
| 英文摘要 | In financial time series forecasting, the problem that we often encounter is how to increase the prediction accuracy as possible using the financial data with noise. In this study, we discuss the use of supervised neural networks as a meta-learning technique to design a financial time series forecasting system to solve this problem. In this system, some data sampling techniques are first used to generate different training subsets from the original datasets. In terms of these different training subsets, different neural networks with different initial conditions or training algorithms are then trained to formulate different prediction models, i.e., base models. Subsequently, to improve the efficiency of predictions of metamodeling, the principal component analysis (PCA) technique is used as a pruning tool to generate an optimal set of base models. Finally, a neural-network-based nonlinear metamodel can be produced by learning from the selected base models, so as to improve the prediction accuracy. For illustration and verification purposes, the proposed metamodel is conducted on four typical financial time series. Empirical results obtained reveal that the proposed neural-network-based nonlinear metamodeling technique is a very promising approach to financial time series forecasting. (c) 2008 Elsevier B.V. All rights reserved. |
| 资助项目 | National Natural Science Foundation of China[70601029] ; National Natural Science Foundation of China[70221001] ; Knowledge Innovation Program of Chinese Academy of Sciences[3547600] ; Strategic Research Grant of City University of Hong Kong[7001807] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:000262888100012 |
| 出版者 | ELSEVIER SCIENCE BV |
| 源URL | [http://ir.amss.ac.cn/handle/2S8OKBNM/7082]  |
| 专题 | 系统科学研究所 |
| 通讯作者 | Yu, Lean |
| 作者单位 | 1.Chinese Acad Sci, Acad Math & Syst Sci, Inst Syst Sci, Beijing 100190, Peoples R China 2.City Univ Hong Kong, Dept Management Sci, Kowloon, Hong Kong, Peoples R China |
| 推荐引用方式 GB/T 7714 | Yu, Lean,Wang, Shouyang,Lai, Kin Keung. A neural-network-based nonlinear metamodeling approach to financial time series forecasting[J]. APPLIED SOFT COMPUTING,2009,9(2):563-574. |
| APA | Yu, Lean,Wang, Shouyang,&Lai, Kin Keung.(2009).A neural-network-based nonlinear metamodeling approach to financial time series forecasting.APPLIED SOFT COMPUTING,9(2),563-574. |
| MLA | Yu, Lean,et al."A neural-network-based nonlinear metamodeling approach to financial time series forecasting".APPLIED SOFT COMPUTING 9.2(2009):563-574. |
入库方式： OAI收割
来源：数学与系统科学研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。