9th Joint International Conference on Information Sciences (JCIS-06)

Neural-Network-based Metamodeling for Financial Time Series Forecasting

Authors
Kin Keung Lai 0, Lean YU, Shouyang Wang, Chengxiong Zhou
Corresponding Author
Kin Keung Lai
0City University of Hong Kong
Available Online undefined NaN.
DOI
https://doi.org/10.2991/jcis.2006.172How to use a DOI?
Keywords
Metamodeling, neural network, financial time series forecasting, cross-validation
Abstract
In the financial time series forecasting field, the problem that we often encountered is how to increase the predict accuracy as possible using the noisy financial data. In this study, we discuss the use of supervised neural networks as the metamodeling technique to design a financial time series forecasting system to solve this problem. First of all, a cross-validation technique is used to generate different training subsets. Based on the different training subsets, the different neural predictors with different initial conditions or training algorithms is then trained to formulate different forecasting models, i.e., base models. Finally, a neural-network-based metamodel can be produced by learning from all base models so as to improve the model accuracy. For verification, two real-world financial time series is used for testing.
Open Access
This is an open access article distributed under the CC BY-NC license.

Download article (PDF)

Proceedings
9th Joint International Conference on Information Sciences (JCIS-06)
Publication Date
undefined NaN
ISBN
978-90-78677-01-7
DOI
https://doi.org/10.2991/jcis.2006.172How to use a DOI?
Open Access
This is an open access article distributed under the CC BY-NC license.

Cite this article

TY  - CONF
AU  - Kin Keung Lai
AU  - Lean YU
AU  - Shouyang Wang
AU  - Chengxiong Zhou
PY  - NaN/NaN
DA  - NaN/NaN
TI  - Neural-Network-based Metamodeling for Financial Time Series Forecasting
BT  - 9th Joint International Conference on Information Sciences (JCIS-06)
PB  - Atlantis Press
UR  - https://doi.org/10.2991/jcis.2006.172
DO  - https://doi.org/10.2991/jcis.2006.172
ID  - LaiNaN/NaN
ER  -