Using genetic algorithms grey theory to forecast high technology industrial output

被引:150
作者
Wang, Chao-Hung [1 ]
Hsu, Li-Chang [2 ]
机构
[1] Ling Tung Univ, Dept Internatl Business, Taichung 40852, Taiwan
[2] Ling Tung Univ, Dept Finance, Taichung 40852, Taiwan
关键词
forecasting; integrated circuit; grey theory; genetic algorithms;
D O I
10.1016/j.amc.2007.04.080
中图分类号
O29 [应用数学];
学科分类号
070104 ;
摘要
This paper presents an improved method to forecast the output and trends of high technology industry in Taiwan. High technology industry plays a pivotal role in this country's economy and the social change. The characteristics of high technology industry include rapidly progressive of production techniques, fluctuating market demand, high investment capital, etc. These factors directly affect the difficulty of forecasting trends in this industry. The goal of this study is to overcome these constraints and establish a high-precision forecasting model. To do so, this paper proposes the combined use of grey theory and genetic algorithms. The former is used to forecast the outputs of high tech industry and latter is used to estimate the parameters of a forecasting model based on the minimization of forecasting error. The study uses the example of Taiwan's integrated circuit industry. Results are very encouraging as this forecasting model clearly helps obtaining precision outcomes. The authors discuss implications of these findings for theory and practice. (c) 2007 Elsevier Inc. All rights reserved.
引用
收藏
页码:256 / 263
页数:8
相关论文
共 46 条
[1]   Using genetic algorithms to find technical trading rules [J].
Allen, F ;
Karjalainen, R .
JOURNAL OF FINANCIAL ECONOMICS, 1999, 51 (02) :245-271
[2]  
[Anonymous], 1975, Adaptation in neural and artificial systems
[3]  
Back T., 1992, P 2 C PAR PROBL SOLV
[4]   Evolving neural network for printed circuit board sales forecasting [J].
Chang, PC ;
Wang, YW ;
Tsai, CY .
EXPERT SYSTEMS WITH APPLICATIONS, 2005, 29 (01) :83-92
[5]   A variable P value rolling Grey forecasting model for Taiwan semiconductor industry production [J].
Chang, SC ;
Lai, HC ;
Yu, HC .
TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE, 2005, 72 (05) :623-640
[6]  
Chang SS, 1999, MOL UROL, V3, P313
[7]  
CHEN G, 1998, MAT SCI SEMICON PROC, V1, P141
[8]   Genetic algorithms for optimisation of predictive ecosystems models based on decision trees and neural networks [J].
D'heyere, Tom ;
Goethals, Peter L. M. ;
De Pauw, Niels .
ECOLOGICAL MODELLING, 2006, 195 (1-2) :20-29
[9]   CONTROL-PROBLEMS OF GREY SYSTEMS [J].
DENG, JL .
SYSTEMS & CONTROL LETTERS, 1982, 1 (05) :288-294
[10]   Extracting rules from trained neural network using GA for managing e-business [J].
Elalfi, AE ;
Haque, R ;
Elalami, ME .
APPLIED SOFT COMPUTING, 2004, 4 (01) :65-77