Wavelet De-noised Artificial Neural Network (WDANN) for Exchange Rate Predication

This research describes the exchange rate which plays a decisive role in the flow of foreign capital, international banking, international trade and risk management. It briefly reviews the development of exchange rate forecasting models and techniques for financial time series of de-noising wavelet...

Full description

Bibliographic Details
Main Author: Hu, Qiongjie
Format: Dissertation (University of Nottingham only)
Language:English
Published: 2010
Online Access:https://eprints.nottingham.ac.uk/23530/
_version_ 1848792584335392768
author Hu, Qiongjie
author_facet Hu, Qiongjie
author_sort Hu, Qiongjie
building Nottingham Research Data Repository
collection Online Access
description This research describes the exchange rate which plays a decisive role in the flow of foreign capital, international banking, international trade and risk management. It briefly reviews the development of exchange rate forecasting models and techniques for financial time series of de-noising wavelet analysis, and then to analyze the applications of the neural network for exchange rate predication. Combined with the advantages of the neural network and wavelet analysis in non-linear forecasting and de-noising respectively, a combinative model wavelet de-noised artificial neural network (WDANN) is developed. This model is tested by empirical researches using GBP/USD exchange rate data. The de-noising performances of the wavelet with different wavelet functions, decomposition levels and wavelet threshold are also tested using experiments respectively. The results indicate that out-of-sample performance is improved by the combinative model. And the following parameters yield more accurate forecasts: coifN wavelet function, decomposing level of three, and sqtwolog threshold.
first_indexed 2025-11-14T18:46:43Z
format Dissertation (University of Nottingham only)
id nottingham-23530
institution University of Nottingham Malaysia Campus
institution_category Local University
language English
last_indexed 2025-11-14T18:46:43Z
publishDate 2010
recordtype eprints
repository_type Digital Repository
spelling nottingham-235302018-01-06T03:47:28Z https://eprints.nottingham.ac.uk/23530/ Wavelet De-noised Artificial Neural Network (WDANN) for Exchange Rate Predication Hu, Qiongjie This research describes the exchange rate which plays a decisive role in the flow of foreign capital, international banking, international trade and risk management. It briefly reviews the development of exchange rate forecasting models and techniques for financial time series of de-noising wavelet analysis, and then to analyze the applications of the neural network for exchange rate predication. Combined with the advantages of the neural network and wavelet analysis in non-linear forecasting and de-noising respectively, a combinative model wavelet de-noised artificial neural network (WDANN) is developed. This model is tested by empirical researches using GBP/USD exchange rate data. The de-noising performances of the wavelet with different wavelet functions, decomposition levels and wavelet threshold are also tested using experiments respectively. The results indicate that out-of-sample performance is improved by the combinative model. And the following parameters yield more accurate forecasts: coifN wavelet function, decomposing level of three, and sqtwolog threshold. 2010 Dissertation (University of Nottingham only) NonPeerReviewed application/pdf en https://eprints.nottingham.ac.uk/23530/1/final_dddd_.pdf Hu, Qiongjie (2010) Wavelet De-noised Artificial Neural Network (WDANN) for Exchange Rate Predication. [Dissertation (University of Nottingham only)] (Unpublished)
spellingShingle Hu, Qiongjie
Wavelet De-noised Artificial Neural Network (WDANN) for Exchange Rate Predication
title Wavelet De-noised Artificial Neural Network (WDANN) for Exchange Rate Predication
title_full Wavelet De-noised Artificial Neural Network (WDANN) for Exchange Rate Predication
title_fullStr Wavelet De-noised Artificial Neural Network (WDANN) for Exchange Rate Predication
title_full_unstemmed Wavelet De-noised Artificial Neural Network (WDANN) for Exchange Rate Predication
title_short Wavelet De-noised Artificial Neural Network (WDANN) for Exchange Rate Predication
title_sort wavelet de-noised artificial neural network (wdann) for exchange rate predication
url https://eprints.nottingham.ac.uk/23530/