Data preprocessing techniques and neural networks for trended time series forecasting

Research on time series forecasting continues to attract significant attention, particularly in the use of Artificial Neural Networks (ANN) due to their ability to model nonlinear behaviors. However, forecasting economic time series with steep upward trends presents challenges, often leading to poor...

ver descrição completa

Detalhes bibliográficos
Autores: Lazcano, Ana, Jaramillo-Morán, Miguel A.
Formato: artículo
Fecha de publicación:2025
País:España
Recursos:Universidad Francisco de Vitoria
Repositorio:DDFV. Repositorio Institucional de la Universidad Francisco de Vitoria
Idioma:inglés
OAI Identifier:oai:ddfv.ufv.es:10641/6884
Acesso em linha:https://hdl.handle.net/10641/6884
Access Level:acceso abierto
Palavra-chave:Differentiation
Forecasting
LSTM
MLP
Preprocessing
Software
Yes
yes
id ES_3fec7ad80ec3bf59831a68b4ff5565bc
oai_identifier_str oai:ddfv.ufv.es:10641/6884
network_acronym_str ES
network_name_str España
repository_id_str
spelling Data preprocessing techniques and neural networks for trended time series forecastingLazcano, AnaLazcano, AnaJaramillo-Morán, Miguel A.DifferentiationForecastingLSTMMLPPreprocessingSoftwareYesyesResearch on time series forecasting continues to attract significant attention, particularly in the use of Artificial Neural Networks (ANN) due to their ability to model nonlinear behaviors. However, forecasting economic time series with steep upward trends presents challenges, often leading to poorly fitting predictions. This study addresses the issue by applying differentiation as a preprocessing step. Three real-world time series exhibiting this behavior were analyzed and forecasted using two neural network models—Long Short-Term Memory (LSTM) and Multilayer Perceptron (MLP)—with and without preprocessing. The differentiated series were further processed using techniques such as Empirical Mode Decomposition (EMD) and trend-fluctuation decomposition via Moving Average of Wavelet Transform. The results demonstrate that differentiation significantly enhances forecasting accuracy across all tested models, reducing errors by up to 30 % compared to models without preprocessing. This approach effectively mitigates trend-related distortions, leading to more reliable predictions in complex economic time series.Facultad de Derecho, Empresa y Gobierno20252025-04-0120252025-04-01journal articlehttp://purl.org/coar/resource_type/c_6501info:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/10641/6884reponame:DDFV. Repositorio Institucional de la Universidad Francisco de Vitoriainstname:Universidad Francisco de VitoriaInglésengopen accesshttp://purl.org/coar/access_right/c_abf2http://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:ddfv.ufv.es:10641/68842026-06-11T12:44:57Z
dc.title.none.fl_str_mv Data preprocessing techniques and neural networks for trended time series forecasting
title Data preprocessing techniques and neural networks for trended time series forecasting
spellingShingle Data preprocessing techniques and neural networks for trended time series forecasting
Lazcano, Ana
Differentiation
Forecasting
LSTM
MLP
Preprocessing
Software
Yes
yes
title_short Data preprocessing techniques and neural networks for trended time series forecasting
title_full Data preprocessing techniques and neural networks for trended time series forecasting
title_fullStr Data preprocessing techniques and neural networks for trended time series forecasting
title_full_unstemmed Data preprocessing techniques and neural networks for trended time series forecasting
title_sort Data preprocessing techniques and neural networks for trended time series forecasting
dc.creator.none.fl_str_mv Lazcano, Ana
Lazcano, Ana
Jaramillo-Morán, Miguel A.
author Lazcano, Ana
author_facet Lazcano, Ana
Jaramillo-Morán, Miguel A.
author_role author
author2 Jaramillo-Morán, Miguel A.
author2_role author
dc.contributor.none.fl_str_mv Facultad de Derecho, Empresa y Gobierno
dc.subject.none.fl_str_mv Differentiation
Forecasting
LSTM
MLP
Preprocessing
Software
Yes
yes
topic Differentiation
Forecasting
LSTM
MLP
Preprocessing
Software
Yes
yes
description Research on time series forecasting continues to attract significant attention, particularly in the use of Artificial Neural Networks (ANN) due to their ability to model nonlinear behaviors. However, forecasting economic time series with steep upward trends presents challenges, often leading to poorly fitting predictions. This study addresses the issue by applying differentiation as a preprocessing step. Three real-world time series exhibiting this behavior were analyzed and forecasted using two neural network models—Long Short-Term Memory (LSTM) and Multilayer Perceptron (MLP)—with and without preprocessing. The differentiated series were further processed using techniques such as Empirical Mode Decomposition (EMD) and trend-fluctuation decomposition via Moving Average of Wavelet Transform. The results demonstrate that differentiation significantly enhances forecasting accuracy across all tested models, reducing errors by up to 30 % compared to models without preprocessing. This approach effectively mitigates trend-related distortions, leading to more reliable predictions in complex economic time series.
publishDate 2025
dc.date.none.fl_str_mv 2025
2025-04-01
2025
2025-04-01
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/10641/6884
url https://hdl.handle.net/10641/6884
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2

http://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2

http://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:DDFV. Repositorio Institucional de la Universidad Francisco de Vitoria
instname:Universidad Francisco de Vitoria
instname_str Universidad Francisco de Vitoria
reponame_str DDFV. Repositorio Institucional de la Universidad Francisco de Vitoria
collection DDFV. Repositorio Institucional de la Universidad Francisco de Vitoria
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869406700488884224
score 15.812429

Registos relacionados