[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-152912-105":59,"doc-detail-152912-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","realized-volatility-forecasting-with-neural-networks","Realized Volatility Forecasting with Neural Networks","","Realized volatility forecasting can be improved by using artificial neural networks as flexible models for time series with long-memory and nonlinear dependencies. This work compares feed-forward and recurrent neural networks, with emphasis on LSTM and NARX architectures, against traditional econometric approaches for predicting conditional volatility. The study finds that recurrent neural networks outperform conventional methods, and that incorporating long-range dependence via LSTM and NARX increases forecasting accuracy even during highly volatile periods.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/realized-volatility-forecasting-with-neural-networks/152912/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/realized-volatility-forecasting-with-neural-networks/152912.png","ImageObject",300,407,{"name":92,"@type":93},"Levi","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-29","2026-08-27",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",14,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"Why use neural networks for realized volatility forecasting?","Question",{"text":113,"@type":114},"Neural networks can approximate complex linear and nonlinear behaviors without requiring knowledge of the data-generating process, making them suitable for long-memory, nonlinear volatility dynamics.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"Which neural network models are compared in the study?",{"text":118,"@type":114},"The comparison includes feed-forward and recurrent neural networks, focusing on LSTM and NARX architectures, and contrasts them with traditional econometric methods.",{"name":120,"@type":111,"acceptedAnswer":121},"Do neural networks improve forecasting accuracy during volatile periods?",{"text":122,"@type":114},"Yes. The results indicate that capturing long-range dependence through LSTM and NARX improves forecasting accuracy even in highly volatile periods.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},152912,1787868255,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":41,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":130,"read_time":144,"preview_page_count":4},7971461740909,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","Journal of Financial Econometrics, 2020, 1–30 doi: 10.1093/jjfinec/nbaa008 Article  \nRealized Volatility Forecasting with Neural Networks  \nAndrea Bucci 1,2  \n1Universita` Politecnica delle Marche and 2Universita` degli Studi G. d’Annunzio Chieti e Pescara Address correspondence to Andrea Bucci, Universit degli Studi “G. d’Annunzio” Chieti-Pescara, Viale Pindaro 42, Pescara, Italy, or e-mail: [andrea.bucci@unich.it](andrea.bucci@unich.it).  \nReceived September 2, 2019; revised September 2, 2019; editorial decision April 14, 2020; accepted April 14, 2020  \nAbstract  \nIn the last few decades, a broad strand of literature in finance has implemented artificial neural networks as a forecasting method. The major advantage of this approach is the possibility to approximate any linear and nonlinear behaviors without knowing the structure of the data generating process. This makes it suitable for forecasting time series which exhibit long-memory and nonlinear dependencies, like conditional volatility. In this article, the predictive performance of feed-forward andrecurrent neural networks (RNNs) was compared, particularly focusing on the recently developed long short-term memory (LSTM) network and nonlinear autoregressive model process with eXogenous input (NARX) network, with traditional econometric approaches. The results show that RNNs are able to outperform all the traditional econometric methods. Additionally, capturing long-range dependence through LSTM and NARX models seems to improve the forecasting accuracy also ina highly volatile period.  \nKey words: neural network, machine learning, stock market volatility, realized volatility  \nJEL classification: C22, C24, C58, G17  \nMeasuring and predicting stock market volatility has received growing attention from both academics and practitioners over the last years. It is well known that stock return volatility varies over time (Engle, 1982; Bollerslev, 1986) and asymmetrically responds to unexpected news (Black, 1976; Nelson, 1990), which may cause distortions in the estimation of volatility and in the definition of its underlying process. For these reasons, some authors suggested to estimate stock market volatility through a smooth transition or a threshold model (De Pooter, Martens, and Van Dijk, 2008; McAleer and Medeiros, 2008) . The nonlinearity makes the estimation of these models difficult, since the sample log-likelihood can exhibit local maxima and may be generally hard to solve with confidence. Furthermore, this class of models is in general greedy in requiring a substantial amount of data to identify the states  \nVC The Author(s) 2020 . Published by Oxford University Press. All rights reserved.  \nFor permissions, please email: [journals.permissions@oup.com](journals.permissions@oup.com)  \nDownloaded from [https://academic.oup.com/jfec/advance-article-abstract/doi/10.1093/jjfinec/nbaa008/5856840 by Uppsala Universitetsbibliotek user on](https://academic.oup.com/jfec/advance-article-abstract/doi/10.1093/jjfinec/nbaa008/5856840 by Uppsala Universitetsbibliotek user on) 13 June 2020  \n2 Journal of Financial Econometrics  \nand presents poor out-of-sample forecasting performance (Clements and Krolzig, 1998; Pavlidis, Paya, and Peel, 2012) .  \nIn this framework, this article aims to capture the nonlinear relationships between aggregate stock market volatility, measured by realized volatility, and a set of financial and macroeconomic variables through artificial neural networks (ANNs) . Realized volatility has been shown to be subject to structural breaks and regime-switching, hence the need to use a nonlinear adaptive modeling approach such neural networks. This method allows approximating arbitrarily well a wide class of linear and nonlinear functions without knowing the data generating process. Furthermore, ANNs are found to be particularly useful to forecast volatile financial variables exhibiting nonlinear dependence, such as stock prices, exchange rates, and realized volatility","cbCaiqXjhlGjnsU8","https://ap.wps.com/l/cbCaiqXjhlGjnsU8","pdf",950505,"English","# Abstract\n## Forecasting approach and motivation\n## Neural network models compared\n## Empirical findings and implications","[{\"question\":\"Why use neural networks for realized volatility forecasting?\",\"answer\":\"Neural networks can approximate complex linear and nonlinear behaviors without requiring knowledge of the data-generating process, making them suitable for long-memory, nonlinear volatility dynamics.\"},{\"question\":\"Which neural network models are compared in the study?\",\"answer\":\"The comparison includes feed-forward and recurrent neural networks, focusing on LSTM and NARX architectures, and contrasts them with traditional econometric methods.\"},{\"question\":\"Do neural networks improve forecasting accuracy during volatile periods?\",\"answer\":\"Yes. The results indicate that capturing long-range dependence through LSTM and NARX improves forecasting accuracy even in highly volatile periods.\"}]","Realized Volatility Forecasting with Neural Networks | PDF",76]