文章基本信息

标题：Foreign Exchange Rate Prediction using Computational Intelligence Methods
本地全文：下载
作者：V. Ravi ; Ramanuj Lal ; N. Raj Kiran 等
期刊名称：International Journal of Computer Information Systems and Industrial Management Applications
印刷版ISSN：2150-7988
电子版ISSN：2150-7988
出版年度：2012
卷号：4
页码：659-670
出版社：Machine Intelligence Research Labs (MIR Labs)
摘要：This paper presents the application of sixnonlinear ensemble architectures to forecasting the foreignexchange rates in the computational intelligence paradigm.Intelligent techniques such as Backpropagation neural network(BPNN), Wavelet neural network (WNN), Multivariateadaptive regression splines (MARS), Support vector regression(SVR), Dynamic evolving neuro-fuzzy inference system(DENFIS), Group Method of Data Handling (GMDH) andGenetic Programming (GP) constitute the ensembles. The dataof exchange rates of US dollar (USD) with respect to DeutscheMark (DEM), Japanese Yen (JPY) and British Pound (GBP) isused for testing the effectiveness of the ensembles. To accountfor the auto regressive nature of the time series problem, weconsidered lagged variables in the experimental design. All thetechniques are compared with normalized root mean squarederror (NRMSE) and directional statistics ( stat D ) as theperformance measures. The results indicate that GMDH andGP based ensembles yielded the best results consistently over allthe currencies. GP based ensembling emerged as the clearwinner based on its consistency with respect to both stat D andNRMSE, but GMDH outperforms it in one of the currencies(DEM). Based on the numerical experiments conducted, it isinferred that using the correct sophisticated ensemblingmethods in the computational intelligence paradigm canenhance the results obtained by the extant techniques toforecast foreign exchange rates.
关键词：Foreign Exchange Rate forecasting;Computational intelligence; Ensemble; Intelligent techniques;Market risk