Time series forecasting by using a neural arima model based on wavelet decomposition
Autor(a) principal: | |
---|---|
Data de Publicação: | 2016 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Independent Journal of Management & Production |
Texto Completo: | http://www.ijmp.jor.br/index.php/ijmp/article/view/400 |
Resumo: | In the prediction of (stochastic) time series, it has been common to suppose that an individual predictive method – for instance, an Auto-Regressive Integrated Moving Average (ARIMA) model – produces residuals like a white noise process. However, mainly due to the structures of auto-dependence not mapped by a given individual predictive method, this assumption may easily be violated, in practice, as pointed out in Firmino et al. (2015). In order to correct it (and accordingly to produce more forecasts with more accuracy power), this paper puts forward a Wavelet Hybrid Forecaster (WHF) that integrates the following numerical techniques: wavelet decomposition; ARIMA models; Artificial Neural Networks (ANNs); and linear combination of forecasts. Basically, the proposed WHF can map simultaneously linear – by means of a linear combination of ARIMA forecasts – and non-linear – through a linear combination of ANN forecasts – auto-dependence structures exhibited by a given time series. Differently of other hybrid methodologies existing in literature, the WHF forecasts are produced carrying into account implicitly the information from the frequency presenting in the underlying time series by means of the Wavelet Components (WCs) obtained by the wavelet decomposition approach. All numerical results show that WHF method has achieved remarkable accuracy gains, when comparing with other competitive forecasting methods already published in specialized literature, in the prediction of a well-known annual time series of sunspot. |
id |
IJMP_32dbba1891bb03cd689ba4547d4877eb |
---|---|
oai_identifier_str |
oai:www.ijmp.jor.br:article/400 |
network_acronym_str |
IJMP |
network_name_str |
Independent Journal of Management & Production |
repository_id_str |
|
spelling |
Time series forecasting by using a neural arima model based on wavelet decompositionWavelet decompositionARIMA modelArtificial neural networksLinear combination of forecastsIn the prediction of (stochastic) time series, it has been common to suppose that an individual predictive method – for instance, an Auto-Regressive Integrated Moving Average (ARIMA) model – produces residuals like a white noise process. However, mainly due to the structures of auto-dependence not mapped by a given individual predictive method, this assumption may easily be violated, in practice, as pointed out in Firmino et al. (2015). In order to correct it (and accordingly to produce more forecasts with more accuracy power), this paper puts forward a Wavelet Hybrid Forecaster (WHF) that integrates the following numerical techniques: wavelet decomposition; ARIMA models; Artificial Neural Networks (ANNs); and linear combination of forecasts. Basically, the proposed WHF can map simultaneously linear – by means of a linear combination of ARIMA forecasts – and non-linear – through a linear combination of ANN forecasts – auto-dependence structures exhibited by a given time series. Differently of other hybrid methodologies existing in literature, the WHF forecasts are produced carrying into account implicitly the information from the frequency presenting in the underlying time series by means of the Wavelet Components (WCs) obtained by the wavelet decomposition approach. All numerical results show that WHF method has achieved remarkable accuracy gains, when comparing with other competitive forecasting methods already published in specialized literature, in the prediction of a well-known annual time series of sunspot.Independent2016-03-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdftext/htmlhttp://www.ijmp.jor.br/index.php/ijmp/article/view/40010.14807/ijmp.v7i1.400Independent Journal of Management & Production; Vol. 7 No. 1 (2016): Independent Journal of Management & Production; 252-2702236-269X2236-269Xreponame:Independent Journal of Management & Productioninstname:Instituto Federal de Educação, Ciência e Tecnologia de São Paulo (IFSP)instacron:IJM&Penghttp://www.ijmp.jor.br/index.php/ijmp/article/view/400/287http://www.ijmp.jor.br/index.php/ijmp/article/view/400/505Copyright (c) 2016 Eliete Nascimento Pereira, Cassius Tadeu Scarpin, Luíz Albino Teixeira Júniorinfo:eu-repo/semantics/openAccessPereira, Eliete NascimentoScarpin, Cassius TadeuTeixeira Júnior, Luíz Albino2018-09-04T13:12:15Zoai:www.ijmp.jor.br:article/400Revistahttp://www.ijmp.jor.br/PUBhttp://www.ijmp.jor.br/index.php/ijmp/oaiijmp@ijmp.jor.br||paulo@paulorodrigues.pro.br||2236-269X2236-269Xopendoar:2018-09-04T13:12:15Independent Journal of Management & Production - Instituto Federal de Educação, Ciência e Tecnologia de São Paulo (IFSP)false |
dc.title.none.fl_str_mv |
Time series forecasting by using a neural arima model based on wavelet decomposition |
title |
Time series forecasting by using a neural arima model based on wavelet decomposition |
spellingShingle |
Time series forecasting by using a neural arima model based on wavelet decomposition Pereira, Eliete Nascimento Wavelet decomposition ARIMA model Artificial neural networks Linear combination of forecasts |
title_short |
Time series forecasting by using a neural arima model based on wavelet decomposition |
title_full |
Time series forecasting by using a neural arima model based on wavelet decomposition |
title_fullStr |
Time series forecasting by using a neural arima model based on wavelet decomposition |
title_full_unstemmed |
Time series forecasting by using a neural arima model based on wavelet decomposition |
title_sort |
Time series forecasting by using a neural arima model based on wavelet decomposition |
author |
Pereira, Eliete Nascimento |
author_facet |
Pereira, Eliete Nascimento Scarpin, Cassius Tadeu Teixeira Júnior, Luíz Albino |
author_role |
author |
author2 |
Scarpin, Cassius Tadeu Teixeira Júnior, Luíz Albino |
author2_role |
author author |
dc.contributor.author.fl_str_mv |
Pereira, Eliete Nascimento Scarpin, Cassius Tadeu Teixeira Júnior, Luíz Albino |
dc.subject.por.fl_str_mv |
Wavelet decomposition ARIMA model Artificial neural networks Linear combination of forecasts |
topic |
Wavelet decomposition ARIMA model Artificial neural networks Linear combination of forecasts |
description |
In the prediction of (stochastic) time series, it has been common to suppose that an individual predictive method – for instance, an Auto-Regressive Integrated Moving Average (ARIMA) model – produces residuals like a white noise process. However, mainly due to the structures of auto-dependence not mapped by a given individual predictive method, this assumption may easily be violated, in practice, as pointed out in Firmino et al. (2015). In order to correct it (and accordingly to produce more forecasts with more accuracy power), this paper puts forward a Wavelet Hybrid Forecaster (WHF) that integrates the following numerical techniques: wavelet decomposition; ARIMA models; Artificial Neural Networks (ANNs); and linear combination of forecasts. Basically, the proposed WHF can map simultaneously linear – by means of a linear combination of ARIMA forecasts – and non-linear – through a linear combination of ANN forecasts – auto-dependence structures exhibited by a given time series. Differently of other hybrid methodologies existing in literature, the WHF forecasts are produced carrying into account implicitly the information from the frequency presenting in the underlying time series by means of the Wavelet Components (WCs) obtained by the wavelet decomposition approach. All numerical results show that WHF method has achieved remarkable accuracy gains, when comparing with other competitive forecasting methods already published in specialized literature, in the prediction of a well-known annual time series of sunspot. |
publishDate |
2016 |
dc.date.none.fl_str_mv |
2016-03-01 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://www.ijmp.jor.br/index.php/ijmp/article/view/400 10.14807/ijmp.v7i1.400 |
url |
http://www.ijmp.jor.br/index.php/ijmp/article/view/400 |
identifier_str_mv |
10.14807/ijmp.v7i1.400 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
http://www.ijmp.jor.br/index.php/ijmp/article/view/400/287 http://www.ijmp.jor.br/index.php/ijmp/article/view/400/505 |
dc.rights.driver.fl_str_mv |
Copyright (c) 2016 Eliete Nascimento Pereira, Cassius Tadeu Scarpin, Luíz Albino Teixeira Júnior info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
Copyright (c) 2016 Eliete Nascimento Pereira, Cassius Tadeu Scarpin, Luíz Albino Teixeira Júnior |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf text/html |
dc.publisher.none.fl_str_mv |
Independent |
publisher.none.fl_str_mv |
Independent |
dc.source.none.fl_str_mv |
Independent Journal of Management & Production; Vol. 7 No. 1 (2016): Independent Journal of Management & Production; 252-270 2236-269X 2236-269X reponame:Independent Journal of Management & Production instname:Instituto Federal de Educação, Ciência e Tecnologia de São Paulo (IFSP) instacron:IJM&P |
instname_str |
Instituto Federal de Educação, Ciência e Tecnologia de São Paulo (IFSP) |
instacron_str |
IJM&P |
institution |
IJM&P |
reponame_str |
Independent Journal of Management & Production |
collection |
Independent Journal of Management & Production |
repository.name.fl_str_mv |
Independent Journal of Management & Production - Instituto Federal de Educação, Ciência e Tecnologia de São Paulo (IFSP) |
repository.mail.fl_str_mv |
ijmp@ijmp.jor.br||paulo@paulorodrigues.pro.br|| |
_version_ |
1797220490553589760 |