ageneralapproachbasedonautocorrelationtodetermineinputvariablesofneuralnetworksfortimeseriesforecasting

CSpace > 系统科学研究所

	ageneralapproachbasedonautocorrelationtodetermineinputvariablesofneuralnetworksfortimeseriesforecasting
	Huang Wei 1; Nakamori Yoshiteru 1; Wang Shouyang2
	2004
发表期刊	journalofsystemsscienceandcomplexity
ISSN	1009-6124
卷号	017 期号:003 页码:297
摘要	Input selection is probably one of the most critical decision issues in neural network designing, because it has a great impact on forecasting performance. Among the many applications of artificial neural networks to finance, time series forecasting is perhaps one of the most challenging issues. Considering the features of neural networks, we propose a general approach called Autocorrelation Criterion (AC) to determine the inputs variables for a neural network. The purpose is to seek optimal lag periods, which are more predictive and less correlated. AC is a data-driven approach in that there is no prior assumptiona bout the models for time series under study. So it has extensive applications and avoids a lengthy experimentation and tinkering in input selection. We apply the approach to the determination of input variables for foreign exchange rate forecasting and conductcomparisons between AC and information-based in-sample model selection criterion. The experiment results show that AC outperforms information-based in-sample model selection criterion.
语种	英语
文献类型	期刊论文
条目标识符	http://ir.amss.ac.cn/handle/2S8OKBNM/41206
专题	系统科学研究所
作者单位	1.北陆先端科学技术大学院大学 2.中国科学院数学与系统科学研究院
推荐引用方式 GB/T 7714	Huang Wei,Nakamori Yoshiteru,Wang Shouyang. ageneralapproachbasedonautocorrelationtodetermineinputvariablesofneuralnetworksfortimeseriesforecasting[J]. journalofsystemsscienceandcomplexity,2004,017(003):297.
APA	Huang Wei,Nakamori Yoshiteru,&Wang Shouyang.(2004).ageneralapproachbasedonautocorrelationtodetermineinputvariablesofneuralnetworksfortimeseriesforecasting.journalofsystemsscienceandcomplexity,017(003),297.
MLA	Huang Wei,et al."ageneralapproachbasedonautocorrelationtodetermineinputvariablesofneuralnetworksfortimeseriesforecasting".journalofsystemsscienceandcomplexity 017.003(2004):297.