THE EFFECT OF DECOMPOSITION METHOD AS DATA PREPROCESSING ON NEURAL NETWORKS MODEL FOR FORECASTING TREND AND SEASONAL TIME SERIES
Recently, one of the central topics for the neural networks (NN) community is the issue of data preprocessing on the use of NN. In this paper, we will investigate this topic particularly on the effect of Decomposition method as data processing and the use of NN for modeling effectively time series w...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Petra Christian University
2006-01-01
|
Series: | Jurnal Teknik Industri |
Subjects: | |
Online Access: | http://puslit2.petra.ac.id/ejournal/index.php/ind/article/view/16556 |
id |
doaj-0b3914dce0314596bcfc506598ad1aaa |
---|---|
record_format |
Article |
spelling |
doaj-0b3914dce0314596bcfc506598ad1aaa2020-11-25T01:19:19ZengPetra Christian UniversityJurnal Teknik Industri1411-24852006-01-0182156164THE EFFECT OF DECOMPOSITION METHOD AS DATA PREPROCESSING ON NEURAL NETWORKS MODEL FOR FORECASTING TREND AND SEASONAL TIME SERIESSubanar SubanarSuhartono SuhartonoRecently, one of the central topics for the neural networks (NN) community is the issue of data preprocessing on the use of NN. In this paper, we will investigate this topic particularly on the effect of Decomposition method as data processing and the use of NN for modeling effectively time series with both trend and seasonal patterns. Limited empirical studies on seasonal time series forecasting with neural networks show that some find neural networks are able to model seasonality directly and prior deseasonalization is not necessary, and others conclude just the opposite. In this research, we study particularly on the effectiveness of data preprocessing, including detrending and deseasonalization by applying Decomposition method on NN modeling and forecasting performance. We use two kinds of data, simulation and real data. Simulation data are examined on multiplicative of trend and seasonality patterns. The results are compared to those obtained from the classical time series model. Our result shows that a combination of detrending and deseasonalization by applying Decomposition method is the effective data preprocessing on the use of NN for forecasting trend and seasonal time series. http://puslit2.petra.ac.id/ejournal/index.php/ind/article/view/16556decompositiondata preprocessingneural networkstrendseasonalitytime seriesforecasting. |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Subanar Subanar Suhartono Suhartono |
spellingShingle |
Subanar Subanar Suhartono Suhartono THE EFFECT OF DECOMPOSITION METHOD AS DATA PREPROCESSING ON NEURAL NETWORKS MODEL FOR FORECASTING TREND AND SEASONAL TIME SERIES Jurnal Teknik Industri decomposition data preprocessing neural networks trend seasonality time series forecasting. |
author_facet |
Subanar Subanar Suhartono Suhartono |
author_sort |
Subanar Subanar |
title |
THE EFFECT OF DECOMPOSITION METHOD AS DATA PREPROCESSING ON NEURAL NETWORKS MODEL FOR FORECASTING TREND AND SEASONAL TIME SERIES |
title_short |
THE EFFECT OF DECOMPOSITION METHOD AS DATA PREPROCESSING ON NEURAL NETWORKS MODEL FOR FORECASTING TREND AND SEASONAL TIME SERIES |
title_full |
THE EFFECT OF DECOMPOSITION METHOD AS DATA PREPROCESSING ON NEURAL NETWORKS MODEL FOR FORECASTING TREND AND SEASONAL TIME SERIES |
title_fullStr |
THE EFFECT OF DECOMPOSITION METHOD AS DATA PREPROCESSING ON NEURAL NETWORKS MODEL FOR FORECASTING TREND AND SEASONAL TIME SERIES |
title_full_unstemmed |
THE EFFECT OF DECOMPOSITION METHOD AS DATA PREPROCESSING ON NEURAL NETWORKS MODEL FOR FORECASTING TREND AND SEASONAL TIME SERIES |
title_sort |
effect of decomposition method as data preprocessing on neural networks model for forecasting trend and seasonal time series |
publisher |
Petra Christian University |
series |
Jurnal Teknik Industri |
issn |
1411-2485 |
publishDate |
2006-01-01 |
description |
Recently, one of the central topics for the neural networks (NN) community is the issue of data preprocessing on the use of NN. In this paper, we will investigate this topic particularly on the effect of Decomposition method as data processing and the use of NN for modeling effectively time series with both trend and seasonal patterns. Limited empirical studies on seasonal time series forecasting with neural networks show that some find neural networks are able to model seasonality directly and prior deseasonalization is not necessary, and others conclude just the opposite. In this research, we study particularly on the effectiveness of data preprocessing, including detrending and deseasonalization by applying Decomposition method on NN modeling and forecasting performance. We use two kinds of data, simulation and real data. Simulation data are examined on multiplicative of trend and seasonality patterns. The results are compared to those obtained from the classical time series model. Our result shows that a combination of detrending and deseasonalization by applying Decomposition method is the effective data preprocessing on the use of NN for forecasting trend and seasonal time series. |
topic |
decomposition data preprocessing neural networks trend seasonality time series forecasting. |
url |
http://puslit2.petra.ac.id/ejournal/index.php/ind/article/view/16556 |
work_keys_str_mv |
AT subanarsubanar theeffectofdecompositionmethodasdatapreprocessingonneuralnetworksmodelforforecastingtrendandseasonaltimeseries AT suhartonosuhartono theeffectofdecompositionmethodasdatapreprocessingonneuralnetworksmodelforforecastingtrendandseasonaltimeseries AT subanarsubanar effectofdecompositionmethodasdatapreprocessingonneuralnetworksmodelforforecastingtrendandseasonaltimeseries AT suhartonosuhartono effectofdecompositionmethodasdatapreprocessingonneuralnetworksmodelforforecastingtrendandseasonaltimeseries |
_version_ |
1725138977026998272 |