Please use this identifier to cite or link to this item:

Title: Forecasting exchange rate using EMD and BPNN optimized by particle swarm optimization
Authors: Yang, Heng-Li;Lin, Han Chou;Huang, Stevenson
Contributors: 資管系
Keywords: Back-propagation neural networks;Empirical mode decomposition;Exchange rate forecasting;Exchange rates;Hilbert Huang transforms;Hybrid model;Intrinsic mode functions;Mean absolute percentage error;Random Walk;Backpropagation;Data mining;Forecasting;Functions;Information technology;Neural networks;Signal processing;Torsional stress;Particle swarm optimization (PSO)
Date: 2011
Issue Date: 2015-10-08 17:40:47 (UTC+8)
Abstract: This study applied back-propagation neural network (BPNN) and empirical mode decomposition (EMD) techniques and optimized the hybrid model by particle swarm optimization (PSO) to forecast exchange rate. The aim of this study is to examine the feasibility of the proposed EMD-BPNN-PSO model in exchange rate forecasting. In the first stage, the original exchange rate series were first decomposed into a finite, and often small, number of intrinsic mode functions (IMFs). In the second stage, kernel predictors such as BPNN are constructed for forecasting. Compared with traditional model (random walk), the proposed model performs best. The mean absolute percentage errors are significantly reduced. © 2011 AICIT.
Relation: Proceedings - 3rd International Conference on Data Mining and Intelligent Information Technology Applications, ICMIA 2011
Data Type: conference
Appears in Collections:[資訊管理學系] 會議論文

Files in This Item:

File Description SizeFormat

All items in 學術集成 are protected by copyright, with all rights reserved.

社群 sharing