Forecasting and trading currency volatility: an application of recurrent neural regression and model combination

In this paper, we examine the use of non‐parametric Neural Network Regression (NNR) and Recurrent Neural Network (RNN) regression models for forecasting and trading currency volatility, with an application to the GBP/USD and USD/JPY exchange rates. Both the results of the NNR and RNN models are benc...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of forecasting 2002-08, Vol.21 (5), p.317-354
Hauptverfasser: Dunis, Christian L., Huang, Xuehuan
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 354
container_issue 5
container_start_page 317
container_title Journal of forecasting
container_volume 21
creator Dunis, Christian L.
Huang, Xuehuan
description In this paper, we examine the use of non‐parametric Neural Network Regression (NNR) and Recurrent Neural Network (RNN) regression models for forecasting and trading currency volatility, with an application to the GBP/USD and USD/JPY exchange rates. Both the results of the NNR and RNN models are benchmarked against the simpler GARCH alternative and implied volatility. Two simple model combinations are also analysed. The intuitively appealing idea of developing a nonlinear nonparametric approach to forecast FX volatility, identify mispriced options and subsequently develop a trading strategy based upon this process is implemented for the first time on a comprehensive basis. Using daily data from December 1993 through April 1999, we develop alternative FX volatility forecasting models. These models are then tested out‐of‐sample over the period April 1999–May 2000, not only in terms of forecasting accuracy, but also in terms of trading efficiency: in order to do so, we apply a realistic volatility trading strategy using FX option straddles once mispriced options have been identified. Allowing for transaction costs, most trading strategies retained produce positive returns. RNN models appear as the best single modelling approach yet, somewhat surprisingly, model combination which has the best overall performance in terms of forecasting accuracy, fails to improve the RNN‐based volatility trading results. Another conclusion from our results is that, for the period and currencies considered, the currency option market was inefficient and/or the pricing formulae applied by market participants were inadequate. Copyright © 2002 John Wiley & Sons, Ltd.
doi_str_mv 10.1002/for.833
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_39132108</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>179867831</sourcerecordid><originalsourceid>FETCH-LOGICAL-c4173-9d8d142420e8aab5a56a6782b87d6f4f478fdb78148c7f5947457a68cf7d57423</originalsourceid><addsrcrecordid>eNp10MtO4zAUBmALgUS5iFeIWMACBXxL7MyOIsoMKhQhLqPZWK5jI4MbBzsZpm-PS0YskFjZOv7O0fEPwB6CxwhCfGJ8OOaErIERglWVI4J-r4MRxIzlZVmRTbAV4zOEkHGER6Cd-KCVjJ1tnjLZ1FkXZL26qz4E3ahl9tc72Vlnu-WPBDLZts6qVPFN5k2Wmj9glzW6D9KlwlPQMa6eV-MWvtYuU34xt81H0w7YMNJFvfv_3Ab3k_O7s5_5dHbx6-x0miuKGMmrmteIYoqh5lLOC1mUsmQczzmrS0MNZdzU8_QHyhUzRUUZLZgsuTKsLhjFZBscDHPb4F97HTuxsFFp52SjfR8FqRDBCPIE97_AZ9-HJu0mMKowZCVCCR0OSAUfY9BGtMEuZFgKBMUqdpFiFyn2JI8G-WadXn7HxGR2O-h80DZ2-t-nluFFlIywQjxeX4gr9nB5M_4zFoS8A1XSk8g</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>219207611</pqid></control><display><type>article</type><title>Forecasting and trading currency volatility: an application of recurrent neural regression and model combination</title><source>EBSCOhost Business Source Complete</source><source>Access via Wiley Online Library</source><creator>Dunis, Christian L. ; Huang, Xuehuan</creator><creatorcontrib>Dunis, Christian L. ; Huang, Xuehuan</creatorcontrib><description>In this paper, we examine the use of non‐parametric Neural Network Regression (NNR) and Recurrent Neural Network (RNN) regression models for forecasting and trading currency volatility, with an application to the GBP/USD and USD/JPY exchange rates. Both the results of the NNR and RNN models are benchmarked against the simpler GARCH alternative and implied volatility. Two simple model combinations are also analysed. The intuitively appealing idea of developing a nonlinear nonparametric approach to forecast FX volatility, identify mispriced options and subsequently develop a trading strategy based upon this process is implemented for the first time on a comprehensive basis. Using daily data from December 1993 through April 1999, we develop alternative FX volatility forecasting models. These models are then tested out‐of‐sample over the period April 1999–May 2000, not only in terms of forecasting accuracy, but also in terms of trading efficiency: in order to do so, we apply a realistic volatility trading strategy using FX option straddles once mispriced options have been identified. Allowing for transaction costs, most trading strategies retained produce positive returns. RNN models appear as the best single modelling approach yet, somewhat surprisingly, model combination which has the best overall performance in terms of forecasting accuracy, fails to improve the RNN‐based volatility trading results. Another conclusion from our results is that, for the period and currencies considered, the currency option market was inefficient and/or the pricing formulae applied by market participants were inadequate. Copyright © 2002 John Wiley &amp; Sons, Ltd.</description><identifier>ISSN: 0277-6693</identifier><identifier>EISSN: 1099-131X</identifier><identifier>DOI: 10.1002/for.833</identifier><identifier>CODEN: JOFODV</identifier><language>eng</language><publisher>Chichester, UK: John Wiley &amp; Sons, Ltd</publisher><subject>Accuracy ; Currencies ; Currency ; Currency options ; Economic forecasting ; Economic models ; Economics ; Efficiency ; Forecasting ; forecasting accuracy ; Forecasts ; Foreign exchange markets ; Foreign exchange rates ; Investigations ; model combination ; Modelling ; Networks ; Neural networks ; recurrent neural networks ; Regression analysis ; Securities markets ; Stochastic models ; Studies ; Time series ; trading efficiency ; Volatility ; volatility modelling</subject><ispartof>Journal of forecasting, 2002-08, Vol.21 (5), p.317-354</ispartof><rights>Copyright © 2002 John Wiley &amp; Sons, Ltd.</rights><rights>Copyright Wiley Periodicals Inc. Aug 2002</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c4173-9d8d142420e8aab5a56a6782b87d6f4f478fdb78148c7f5947457a68cf7d57423</citedby><cites>FETCH-LOGICAL-c4173-9d8d142420e8aab5a56a6782b87d6f4f478fdb78148c7f5947457a68cf7d57423</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://onlinelibrary.wiley.com/doi/pdf/10.1002%2Ffor.833$$EPDF$$P50$$Gwiley$$H</linktopdf><linktohtml>$$Uhttps://onlinelibrary.wiley.com/doi/full/10.1002%2Ffor.833$$EHTML$$P50$$Gwiley$$H</linktohtml><link.rule.ids>314,780,784,1417,27924,27925,45574,45575</link.rule.ids></links><search><creatorcontrib>Dunis, Christian L.</creatorcontrib><creatorcontrib>Huang, Xuehuan</creatorcontrib><title>Forecasting and trading currency volatility: an application of recurrent neural regression and model combination</title><title>Journal of forecasting</title><addtitle>J. Forecast</addtitle><description>In this paper, we examine the use of non‐parametric Neural Network Regression (NNR) and Recurrent Neural Network (RNN) regression models for forecasting and trading currency volatility, with an application to the GBP/USD and USD/JPY exchange rates. Both the results of the NNR and RNN models are benchmarked against the simpler GARCH alternative and implied volatility. Two simple model combinations are also analysed. The intuitively appealing idea of developing a nonlinear nonparametric approach to forecast FX volatility, identify mispriced options and subsequently develop a trading strategy based upon this process is implemented for the first time on a comprehensive basis. Using daily data from December 1993 through April 1999, we develop alternative FX volatility forecasting models. These models are then tested out‐of‐sample over the period April 1999–May 2000, not only in terms of forecasting accuracy, but also in terms of trading efficiency: in order to do so, we apply a realistic volatility trading strategy using FX option straddles once mispriced options have been identified. Allowing for transaction costs, most trading strategies retained produce positive returns. RNN models appear as the best single modelling approach yet, somewhat surprisingly, model combination which has the best overall performance in terms of forecasting accuracy, fails to improve the RNN‐based volatility trading results. Another conclusion from our results is that, for the period and currencies considered, the currency option market was inefficient and/or the pricing formulae applied by market participants were inadequate. Copyright © 2002 John Wiley &amp; Sons, Ltd.</description><subject>Accuracy</subject><subject>Currencies</subject><subject>Currency</subject><subject>Currency options</subject><subject>Economic forecasting</subject><subject>Economic models</subject><subject>Economics</subject><subject>Efficiency</subject><subject>Forecasting</subject><subject>forecasting accuracy</subject><subject>Forecasts</subject><subject>Foreign exchange markets</subject><subject>Foreign exchange rates</subject><subject>Investigations</subject><subject>model combination</subject><subject>Modelling</subject><subject>Networks</subject><subject>Neural networks</subject><subject>recurrent neural networks</subject><subject>Regression analysis</subject><subject>Securities markets</subject><subject>Stochastic models</subject><subject>Studies</subject><subject>Time series</subject><subject>trading efficiency</subject><subject>Volatility</subject><subject>volatility modelling</subject><issn>0277-6693</issn><issn>1099-131X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2002</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNp10MtO4zAUBmALgUS5iFeIWMACBXxL7MyOIsoMKhQhLqPZWK5jI4MbBzsZpm-PS0YskFjZOv7O0fEPwB6CxwhCfGJ8OOaErIERglWVI4J-r4MRxIzlZVmRTbAV4zOEkHGER6Cd-KCVjJ1tnjLZ1FkXZL26qz4E3ahl9tc72Vlnu-WPBDLZts6qVPFN5k2Wmj9glzW6D9KlwlPQMa6eV-MWvtYuU34xt81H0w7YMNJFvfv_3Ab3k_O7s5_5dHbx6-x0miuKGMmrmteIYoqh5lLOC1mUsmQczzmrS0MNZdzU8_QHyhUzRUUZLZgsuTKsLhjFZBscDHPb4F97HTuxsFFp52SjfR8FqRDBCPIE97_AZ9-HJu0mMKowZCVCCR0OSAUfY9BGtMEuZFgKBMUqdpFiFyn2JI8G-WadXn7HxGR2O-h80DZ2-t-nluFFlIywQjxeX4gr9nB5M_4zFoS8A1XSk8g</recordid><startdate>200208</startdate><enddate>200208</enddate><creator>Dunis, Christian L.</creator><creator>Huang, Xuehuan</creator><general>John Wiley &amp; Sons, Ltd</general><general>Wiley Periodicals Inc</general><scope>BSCLL</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>0U~</scope><scope>1-H</scope><scope>3V.</scope><scope>7WY</scope><scope>7WZ</scope><scope>7XB</scope><scope>87Z</scope><scope>8BJ</scope><scope>8FK</scope><scope>8FL</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>BENPR</scope><scope>BEZIV</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FQK</scope><scope>FRNLG</scope><scope>F~G</scope><scope>JBE</scope><scope>K60</scope><scope>K6~</scope><scope>L.-</scope><scope>L.0</scope><scope>M0C</scope><scope>PQBIZ</scope><scope>PQBZA</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>Q9U</scope></search><sort><creationdate>200208</creationdate><title>Forecasting and trading currency volatility: an application of recurrent neural regression and model combination</title><author>Dunis, Christian L. ; Huang, Xuehuan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c4173-9d8d142420e8aab5a56a6782b87d6f4f478fdb78148c7f5947457a68cf7d57423</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2002</creationdate><topic>Accuracy</topic><topic>Currencies</topic><topic>Currency</topic><topic>Currency options</topic><topic>Economic forecasting</topic><topic>Economic models</topic><topic>Economics</topic><topic>Efficiency</topic><topic>Forecasting</topic><topic>forecasting accuracy</topic><topic>Forecasts</topic><topic>Foreign exchange markets</topic><topic>Foreign exchange rates</topic><topic>Investigations</topic><topic>model combination</topic><topic>Modelling</topic><topic>Networks</topic><topic>Neural networks</topic><topic>recurrent neural networks</topic><topic>Regression analysis</topic><topic>Securities markets</topic><topic>Stochastic models</topic><topic>Studies</topic><topic>Time series</topic><topic>trading efficiency</topic><topic>Volatility</topic><topic>volatility modelling</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Dunis, Christian L.</creatorcontrib><creatorcontrib>Huang, Xuehuan</creatorcontrib><collection>Istex</collection><collection>CrossRef</collection><collection>Global News &amp; ABI/Inform Professional</collection><collection>Trade PRO</collection><collection>ProQuest Central (Corporate)</collection><collection>Access via ABI/INFORM (ProQuest)</collection><collection>ABI/INFORM Global (PDF only)</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>ABI/INFORM Global (Alumni Edition)</collection><collection>International Bibliography of the Social Sciences (IBSS)</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ABI/INFORM Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central</collection><collection>Business Premium Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>International Bibliography of the Social Sciences</collection><collection>Business Premium Collection (Alumni)</collection><collection>ABI/INFORM Global (Corporate)</collection><collection>International Bibliography of the Social Sciences</collection><collection>ProQuest Business Collection (Alumni Edition)</collection><collection>ProQuest Business Collection</collection><collection>ABI/INFORM Professional Advanced</collection><collection>ABI/INFORM Professional Standard</collection><collection>ABI/INFORM Global</collection><collection>ProQuest One Business</collection><collection>ProQuest One Business (Alumni)</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 Basic</collection><jtitle>Journal of forecasting</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Dunis, Christian L.</au><au>Huang, Xuehuan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Forecasting and trading currency volatility: an application of recurrent neural regression and model combination</atitle><jtitle>Journal of forecasting</jtitle><addtitle>J. Forecast</addtitle><date>2002-08</date><risdate>2002</risdate><volume>21</volume><issue>5</issue><spage>317</spage><epage>354</epage><pages>317-354</pages><issn>0277-6693</issn><eissn>1099-131X</eissn><coden>JOFODV</coden><abstract>In this paper, we examine the use of non‐parametric Neural Network Regression (NNR) and Recurrent Neural Network (RNN) regression models for forecasting and trading currency volatility, with an application to the GBP/USD and USD/JPY exchange rates. Both the results of the NNR and RNN models are benchmarked against the simpler GARCH alternative and implied volatility. Two simple model combinations are also analysed. The intuitively appealing idea of developing a nonlinear nonparametric approach to forecast FX volatility, identify mispriced options and subsequently develop a trading strategy based upon this process is implemented for the first time on a comprehensive basis. Using daily data from December 1993 through April 1999, we develop alternative FX volatility forecasting models. These models are then tested out‐of‐sample over the period April 1999–May 2000, not only in terms of forecasting accuracy, but also in terms of trading efficiency: in order to do so, we apply a realistic volatility trading strategy using FX option straddles once mispriced options have been identified. Allowing for transaction costs, most trading strategies retained produce positive returns. RNN models appear as the best single modelling approach yet, somewhat surprisingly, model combination which has the best overall performance in terms of forecasting accuracy, fails to improve the RNN‐based volatility trading results. Another conclusion from our results is that, for the period and currencies considered, the currency option market was inefficient and/or the pricing formulae applied by market participants were inadequate. Copyright © 2002 John Wiley &amp; Sons, Ltd.</abstract><cop>Chichester, UK</cop><pub>John Wiley &amp; Sons, Ltd</pub><doi>10.1002/for.833</doi><tpages>38</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0277-6693
ispartof Journal of forecasting, 2002-08, Vol.21 (5), p.317-354
issn 0277-6693
1099-131X
language eng
recordid cdi_proquest_miscellaneous_39132108
source EBSCOhost Business Source Complete; Access via Wiley Online Library
subjects Accuracy
Currencies
Currency
Currency options
Economic forecasting
Economic models
Economics
Efficiency
Forecasting
forecasting accuracy
Forecasts
Foreign exchange markets
Foreign exchange rates
Investigations
model combination
Modelling
Networks
Neural networks
recurrent neural networks
Regression analysis
Securities markets
Stochastic models
Studies
Time series
trading efficiency
Volatility
volatility modelling
title Forecasting and trading currency volatility: an application of recurrent neural regression and model combination
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T04%3A54%3A17IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Forecasting%20and%20trading%20currency%20volatility:%20an%20application%20of%20recurrent%20neural%20regression%20and%20model%20combination&rft.jtitle=Journal%20of%20forecasting&rft.au=Dunis,%20Christian%20L.&rft.date=2002-08&rft.volume=21&rft.issue=5&rft.spage=317&rft.epage=354&rft.pages=317-354&rft.issn=0277-6693&rft.eissn=1099-131X&rft.coden=JOFODV&rft_id=info:doi/10.1002/for.833&rft_dat=%3Cproquest_cross%3E179867831%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=219207611&rft_id=info:pmid/&rfr_iscdi=true