A Novel Hybrid Model of CNN-SA-NGU for Silver Closing Price Prediction
Silver is an important industrial raw material, and the price of silver has always been a concern of the financial industry. Silver price data belong to time series data and have high volatility, irregularity, nonlinearity, and long-term correlation. Predicting the silver price for economic developm...
Gespeichert in:
Veröffentlicht in: | Processes 2023-03, Vol.11 (3), p.862 |
---|---|
Hauptverfasser: | , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | 3 |
container_start_page | 862 |
container_title | Processes |
container_volume | 11 |
creator | Wang, Haiyao Dai, Bolin Li, Xiaolei Yu, Naiwen Wang, Jingyang |
description | Silver is an important industrial raw material, and the price of silver has always been a concern of the financial industry. Silver price data belong to time series data and have high volatility, irregularity, nonlinearity, and long-term correlation. Predicting the silver price for economic development is of great practical significance. However, the traditional time series prediction models have shortcomings, such as poor nonlinear fitting ability and low prediction accuracy. Therefore, this paper presents a novel hybrid model of CNN-SA-NGU for silver closing price prediction, which includes conventional neural networks (CNNs), the self-attention mechanism (SA), and the new gated unit (NGU). A CNN extracts the feature of input data. The SA mechanism captures the correlation between different eigenvalues, thus forming new eigenvectors to make weight distribution more reasonable. The NGU is a new deep-learning gated unit proposed in this paper, which is formed by a forgetting gate and an input gate. The NGU’s input data include the cell state of the previous time, the hidden state of the previous time, and the input data of the current time. The NGU learns the previous time’s experience to process the current time’s input data and adds a Tri module behind the input gate to alleviate the gradient disappearance and gradient explosion problems. The NGU optimizes the structure of traditional gates and reduces the computation. To prove the prediction accuracy of the CNN-SA-NGU, this model is compared with the thirteen other time series forecasting models for silver price prediction. Through comparative experiments, the mean absolute error (MAE) value of the CNN-SA-NGU model is 87.898771, the explained variance score (EVS) value is 0.970745, the r-squared (R2) value is 0.970169, and the training time is 332.777 s. The performance of CNN-SA-NGU is better than other models. |
doi_str_mv | 10.3390/pr11030862 |
format | Article |
fullrecord | <record><control><sourceid>gale_proqu</sourceid><recordid>TN_cdi_proquest_journals_2791710438</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A743935447</galeid><sourcerecordid>A743935447</sourcerecordid><originalsourceid>FETCH-LOGICAL-c334t-269f8c8dd1ee6c00cbc601b54eee30a58d0656e261cde32d41f7d8834a33b3083</originalsourceid><addsrcrecordid>eNpNUF1rwjAUDWODifNlvyCwt0Fdvpq0j6VMHbhu4HwubXIjkdq4VAX__SIOtnvhfnHOvdyD0CMlU85z8rIPlBJOMslu0IgxppJcUXX7r75Hk2HYkmg55VkqR2hW4MqfoMOLcxucwe_exMZbXFZVsiqSar7G1ge8ct0JAi47P7h-gz-D0xAjGKcPzvcP6M423QCT3zxG69nrV7lIlh_zt7JYJppzcUiYzG2mM2MogNSE6FZLQttUAAAnTZoZIlMJTFJtgDMjqFUmy7hoOG_jZ3yMnq5798F_H2E41Ft_DH08WTOVU0WJ4BfU9IraNB3Urrf-EBod3cDOad-DdXFeKMFzngqhIuH5StDBD0MAW--D2zXhXFNSX7St_7TlP0n3aGI</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2791710438</pqid></control><display><type>article</type><title>A Novel Hybrid Model of CNN-SA-NGU for Silver Closing Price Prediction</title><source>MDPI - Multidisciplinary Digital Publishing Institute</source><source>EZB-FREE-00999 freely available EZB journals</source><creator>Wang, Haiyao ; Dai, Bolin ; Li, Xiaolei ; Yu, Naiwen ; Wang, Jingyang</creator><creatorcontrib>Wang, Haiyao ; Dai, Bolin ; Li, Xiaolei ; Yu, Naiwen ; Wang, Jingyang</creatorcontrib><description>Silver is an important industrial raw material, and the price of silver has always been a concern of the financial industry. Silver price data belong to time series data and have high volatility, irregularity, nonlinearity, and long-term correlation. Predicting the silver price for economic development is of great practical significance. However, the traditional time series prediction models have shortcomings, such as poor nonlinear fitting ability and low prediction accuracy. Therefore, this paper presents a novel hybrid model of CNN-SA-NGU for silver closing price prediction, which includes conventional neural networks (CNNs), the self-attention mechanism (SA), and the new gated unit (NGU). A CNN extracts the feature of input data. The SA mechanism captures the correlation between different eigenvalues, thus forming new eigenvectors to make weight distribution more reasonable. The NGU is a new deep-learning gated unit proposed in this paper, which is formed by a forgetting gate and an input gate. The NGU’s input data include the cell state of the previous time, the hidden state of the previous time, and the input data of the current time. The NGU learns the previous time’s experience to process the current time’s input data and adds a Tri module behind the input gate to alleviate the gradient disappearance and gradient explosion problems. The NGU optimizes the structure of traditional gates and reduces the computation. To prove the prediction accuracy of the CNN-SA-NGU, this model is compared with the thirteen other time series forecasting models for silver price prediction. Through comparative experiments, the mean absolute error (MAE) value of the CNN-SA-NGU model is 87.898771, the explained variance score (EVS) value is 0.970745, the r-squared (R2) value is 0.970169, and the training time is 332.777 s. The performance of CNN-SA-NGU is better than other models.</description><identifier>ISSN: 2227-9717</identifier><identifier>EISSN: 2227-9717</identifier><identifier>DOI: 10.3390/pr11030862</identifier><language>eng</language><publisher>Basel: MDPI AG</publisher><subject>Accuracy ; Artificial neural networks ; Datasets ; Deep learning ; Economic development ; Eigenvalues ; Eigenvectors ; Financial markets ; Forecasts and trends ; Genetic algorithms ; Gold ; Machine learning ; Neural networks ; Nonlinear systems ; Nonlinearity ; Prediction models ; Raw materials ; Silver ; Silver industry ; Support vector machines ; Time series</subject><ispartof>Processes, 2023-03, Vol.11 (3), p.862</ispartof><rights>COPYRIGHT 2023 MDPI AG</rights><rights>2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c334t-269f8c8dd1ee6c00cbc601b54eee30a58d0656e261cde32d41f7d8834a33b3083</citedby><cites>FETCH-LOGICAL-c334t-269f8c8dd1ee6c00cbc601b54eee30a58d0656e261cde32d41f7d8834a33b3083</cites><orcidid>0000-0003-4275-4225 ; 0000-0003-3829-6540</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Wang, Haiyao</creatorcontrib><creatorcontrib>Dai, Bolin</creatorcontrib><creatorcontrib>Li, Xiaolei</creatorcontrib><creatorcontrib>Yu, Naiwen</creatorcontrib><creatorcontrib>Wang, Jingyang</creatorcontrib><title>A Novel Hybrid Model of CNN-SA-NGU for Silver Closing Price Prediction</title><title>Processes</title><description>Silver is an important industrial raw material, and the price of silver has always been a concern of the financial industry. Silver price data belong to time series data and have high volatility, irregularity, nonlinearity, and long-term correlation. Predicting the silver price for economic development is of great practical significance. However, the traditional time series prediction models have shortcomings, such as poor nonlinear fitting ability and low prediction accuracy. Therefore, this paper presents a novel hybrid model of CNN-SA-NGU for silver closing price prediction, which includes conventional neural networks (CNNs), the self-attention mechanism (SA), and the new gated unit (NGU). A CNN extracts the feature of input data. The SA mechanism captures the correlation between different eigenvalues, thus forming new eigenvectors to make weight distribution more reasonable. The NGU is a new deep-learning gated unit proposed in this paper, which is formed by a forgetting gate and an input gate. The NGU’s input data include the cell state of the previous time, the hidden state of the previous time, and the input data of the current time. The NGU learns the previous time’s experience to process the current time’s input data and adds a Tri module behind the input gate to alleviate the gradient disappearance and gradient explosion problems. The NGU optimizes the structure of traditional gates and reduces the computation. To prove the prediction accuracy of the CNN-SA-NGU, this model is compared with the thirteen other time series forecasting models for silver price prediction. Through comparative experiments, the mean absolute error (MAE) value of the CNN-SA-NGU model is 87.898771, the explained variance score (EVS) value is 0.970745, the r-squared (R2) value is 0.970169, and the training time is 332.777 s. The performance of CNN-SA-NGU is better than other models.</description><subject>Accuracy</subject><subject>Artificial neural networks</subject><subject>Datasets</subject><subject>Deep learning</subject><subject>Economic development</subject><subject>Eigenvalues</subject><subject>Eigenvectors</subject><subject>Financial markets</subject><subject>Forecasts and trends</subject><subject>Genetic algorithms</subject><subject>Gold</subject><subject>Machine learning</subject><subject>Neural networks</subject><subject>Nonlinear systems</subject><subject>Nonlinearity</subject><subject>Prediction models</subject><subject>Raw materials</subject><subject>Silver</subject><subject>Silver industry</subject><subject>Support vector machines</subject><subject>Time series</subject><issn>2227-9717</issn><issn>2227-9717</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GNUQQ</sourceid><recordid>eNpNUF1rwjAUDWODifNlvyCwt0Fdvpq0j6VMHbhu4HwubXIjkdq4VAX__SIOtnvhfnHOvdyD0CMlU85z8rIPlBJOMslu0IgxppJcUXX7r75Hk2HYkmg55VkqR2hW4MqfoMOLcxucwe_exMZbXFZVsiqSar7G1ge8ct0JAi47P7h-gz-D0xAjGKcPzvcP6M423QCT3zxG69nrV7lIlh_zt7JYJppzcUiYzG2mM2MogNSE6FZLQttUAAAnTZoZIlMJTFJtgDMjqFUmy7hoOG_jZ3yMnq5798F_H2E41Ft_DH08WTOVU0WJ4BfU9IraNB3Urrf-EBod3cDOad-DdXFeKMFzngqhIuH5StDBD0MAW--D2zXhXFNSX7St_7TlP0n3aGI</recordid><startdate>20230301</startdate><enddate>20230301</enddate><creator>Wang, Haiyao</creator><creator>Dai, Bolin</creator><creator>Li, Xiaolei</creator><creator>Yu, Naiwen</creator><creator>Wang, Jingyang</creator><general>MDPI AG</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SR</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>8FH</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BBNVY</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>BHPHI</scope><scope>CCPQU</scope><scope>D1I</scope><scope>DWQXO</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>JG9</scope><scope>KB.</scope><scope>LK8</scope><scope>M7P</scope><scope>PDBOC</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><orcidid>https://orcid.org/0000-0003-4275-4225</orcidid><orcidid>https://orcid.org/0000-0003-3829-6540</orcidid></search><sort><creationdate>20230301</creationdate><title>A Novel Hybrid Model of CNN-SA-NGU for Silver Closing Price Prediction</title><author>Wang, Haiyao ; Dai, Bolin ; Li, Xiaolei ; Yu, Naiwen ; Wang, Jingyang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c334t-269f8c8dd1ee6c00cbc601b54eee30a58d0656e261cde32d41f7d8834a33b3083</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Accuracy</topic><topic>Artificial neural networks</topic><topic>Datasets</topic><topic>Deep learning</topic><topic>Economic development</topic><topic>Eigenvalues</topic><topic>Eigenvectors</topic><topic>Financial markets</topic><topic>Forecasts and trends</topic><topic>Genetic algorithms</topic><topic>Gold</topic><topic>Machine learning</topic><topic>Neural networks</topic><topic>Nonlinear systems</topic><topic>Nonlinearity</topic><topic>Prediction models</topic><topic>Raw materials</topic><topic>Silver</topic><topic>Silver industry</topic><topic>Support vector machines</topic><topic>Time series</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Wang, Haiyao</creatorcontrib><creatorcontrib>Dai, Bolin</creatorcontrib><creatorcontrib>Li, Xiaolei</creatorcontrib><creatorcontrib>Yu, Naiwen</creatorcontrib><creatorcontrib>Wang, Jingyang</creatorcontrib><collection>CrossRef</collection><collection>Engineered Materials Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Natural Science Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>Biological Science Collection</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>Natural Science Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Materials Science Collection</collection><collection>ProQuest Central Korea</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>Materials Research Database</collection><collection>Materials Science Database</collection><collection>ProQuest Biological Science Collection</collection><collection>Biological Science Database</collection><collection>Materials Science Collection</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><jtitle>Processes</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Wang, Haiyao</au><au>Dai, Bolin</au><au>Li, Xiaolei</au><au>Yu, Naiwen</au><au>Wang, Jingyang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Novel Hybrid Model of CNN-SA-NGU for Silver Closing Price Prediction</atitle><jtitle>Processes</jtitle><date>2023-03-01</date><risdate>2023</risdate><volume>11</volume><issue>3</issue><spage>862</spage><pages>862-</pages><issn>2227-9717</issn><eissn>2227-9717</eissn><abstract>Silver is an important industrial raw material, and the price of silver has always been a concern of the financial industry. Silver price data belong to time series data and have high volatility, irregularity, nonlinearity, and long-term correlation. Predicting the silver price for economic development is of great practical significance. However, the traditional time series prediction models have shortcomings, such as poor nonlinear fitting ability and low prediction accuracy. Therefore, this paper presents a novel hybrid model of CNN-SA-NGU for silver closing price prediction, which includes conventional neural networks (CNNs), the self-attention mechanism (SA), and the new gated unit (NGU). A CNN extracts the feature of input data. The SA mechanism captures the correlation between different eigenvalues, thus forming new eigenvectors to make weight distribution more reasonable. The NGU is a new deep-learning gated unit proposed in this paper, which is formed by a forgetting gate and an input gate. The NGU’s input data include the cell state of the previous time, the hidden state of the previous time, and the input data of the current time. The NGU learns the previous time’s experience to process the current time’s input data and adds a Tri module behind the input gate to alleviate the gradient disappearance and gradient explosion problems. The NGU optimizes the structure of traditional gates and reduces the computation. To prove the prediction accuracy of the CNN-SA-NGU, this model is compared with the thirteen other time series forecasting models for silver price prediction. Through comparative experiments, the mean absolute error (MAE) value of the CNN-SA-NGU model is 87.898771, the explained variance score (EVS) value is 0.970745, the r-squared (R2) value is 0.970169, and the training time is 332.777 s. The performance of CNN-SA-NGU is better than other models.</abstract><cop>Basel</cop><pub>MDPI AG</pub><doi>10.3390/pr11030862</doi><orcidid>https://orcid.org/0000-0003-4275-4225</orcidid><orcidid>https://orcid.org/0000-0003-3829-6540</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 2227-9717 |
ispartof | Processes, 2023-03, Vol.11 (3), p.862 |
issn | 2227-9717 2227-9717 |
language | eng |
recordid | cdi_proquest_journals_2791710438 |
source | MDPI - Multidisciplinary Digital Publishing Institute; EZB-FREE-00999 freely available EZB journals |
subjects | Accuracy Artificial neural networks Datasets Deep learning Economic development Eigenvalues Eigenvectors Financial markets Forecasts and trends Genetic algorithms Gold Machine learning Neural networks Nonlinear systems Nonlinearity Prediction models Raw materials Silver Silver industry Support vector machines Time series |
title | A Novel Hybrid Model of CNN-SA-NGU for Silver Closing Price Prediction |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-26T06%3A55%3A59IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_proqu&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Novel%20Hybrid%20Model%20of%20CNN-SA-NGU%20for%20Silver%20Closing%20Price%20Prediction&rft.jtitle=Processes&rft.au=Wang,%20Haiyao&rft.date=2023-03-01&rft.volume=11&rft.issue=3&rft.spage=862&rft.pages=862-&rft.issn=2227-9717&rft.eissn=2227-9717&rft_id=info:doi/10.3390/pr11030862&rft_dat=%3Cgale_proqu%3EA743935447%3C/gale_proqu%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2791710438&rft_id=info:pmid/&rft_galeid=A743935447&rfr_iscdi=true |