[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-291003-en":3,"doc-seo-291003-105":31,"detail-sidebar-cat-0-en-105":98},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30,"preview_page_count":4},291003,13056703019662,"Evangeline","https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188",8,"Research & Report","Crypto Volatility Forecasting - Mounting a HAR, Sentiment, and Machine Learning Horserace","The relationship between investor sentiment and cryptocurrency market volatility remains a key theme in empirical finance. This study introduces an AI-generated sentiment dataset sourced from cryptocurrency news and applies a horserace comparison of a Heterogeneous Autoregressive (HAR) model against five machine learning methods. Machine learning improves forecast accuracy versus the HAR benchmark, while adding sentiment does not enhance HAR performance. Sentiment effects are captured nonlinearly only by ML models, with LightGBM, XGBoost, and LSTM outperforming in 54.17% of cases.","University of Dundee  \nCrypto Volatility Forecasting: Mounting a HAR, Sentiment, and Machine Learning Horserace  \nBrauneis, Alexander; Sahiner, Mehmet  \nDOI:  \n10.1007/s10690-024-09510-6  \nPublication date:  \n2024  \nLicence: CC BY  \nDocument Version  \nPublisher's PDF, also known as Version of record  \nLink to publication in Discovery Research Portal  \nCitation for published version (APA):  \nBrauneis, A. , & Sahiner, M. (2024) . Crypto Volatility Forecasting: Mounting a HAR, Sentiment, and Machine Learning Horserace. Asia-Pacific Financial Markets. Advance online publication. [https://doi.org/10.1007/s10690-](https://doi.org/10.1007/s10690-)[ ](https://doi.org/10.1007/s10690-)[024-09510-6](024-09510-6)  \nGeneral rights  \nCopyright and moral rights for the publications made accessible in Discovery Research Portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights.  \nTake down policy  \nIf you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim.  \nDownload date: 13. Feb. 2025  \nAsia-Pacific Financial Markets  \n[https://doi.org/10.1007/s10690-024-09510-6](https://doi.org/10.1007/s10690-024-09510-6)  \nORIGINAL RESEARCH  \nCrypto Volatility Forecasting: Mounting a HAR, Sentiment, and Machine Learning Horserace  \nAlexander Brauneis1 · Mehmet Sahiner2  \nAccepted: 23 November 2024 © The Author(s) 2024  \nAbstract  \nThe relationship between investor sentiment and cryptocurrency market volatility remains an area of growing interest in empirical finance. In this study, we present an innovative forecasting approach by utilizing a unique dataset of AI-generated sentiment from a comprehensive database of crypto market news. In a horserace fashion, we first evaluate the Heterogeneous Autoregressive (HAR) model and then compare its forecasting performance to five advanced machine learning (ML) methods. ML performs reasonably well and improves the accuracy of the benchmark HAR model. Interestingly, including sentiment does not improve the forecasting accuracy of the HAR model. However, our findings highlight that investor sentiment seems to influence crypto market volatility in a nonlinear fashion that can (only) be captured by ML methods. In other words, LightGBM, XGBoost, and LSTM models show enhanced predictive accuracy when sentiment data is incorporated, improving nosentiment forecasts in 54.17% of the cases studied. Overall, our results emphasize the significant potential of integrating machine learning and sentiment analysis as a promising avenue for improved forecasting, offering potential benefits for risk management strategies and provide valuable insights for researchers and practitioners.  \nKeywords Cryptocurrencies · Sentiment · Machine learning · Volatility forecasting  \nJEL Classification G10 · G14 · G17  \n* Alexander Brauneis  \n[alexander.brauneis@ntu.ac.uk](alexander.brauneis@ntu.ac.uk)  \n[https://www.ntu.ac.uk/staff-profiles/business/alexander-brauneis](https://www.ntu.ac.uk/staff-profiles/business/alexander-brauneis)  \nMehmet Sahiner  \n[msahiner001@dundee.ac.uk](msahiner001@dundee.ac.uk)  \n[https://www.dundee.ac.uk/people/mehmet-sahiner](https://www.dundee.ac.uk/people/mehmet-sahiner)  \n1 Finance and Accounting, Nottingham Trent University Business School, 50 Shakespeare Street, Nottingham NG1 4FQ, UK  \n2 Economics, School of Business, University of Dundee, Nethergate, Dundee DD1 4HN, Scotland, UK  \n1 Introduction  \nCryptocurrencies have received immense interest from investors and policymakers due to their decentralized and traceable features (Fry and Cheah (2016)), while at the same time their distinctly volatile nature has prompted researchers to focus on predicting price movements by applying various techniques Köchlinget al. (2020); Ftiti et al. (2021); Catania and Grassi (2022a)","cbCaithuR397UFUu","https://ap.wps.com/l/cbCaithuR397UFUu","pdf",1604804,11,1,34,"English","en",105,"# Introduction\n## Research gap and study aim\n# Forecasting approach\n## Dataset and model comparison","[{\"question\":\"What forecasting models are compared in the study?\",\"answer\":\"The study evaluates a Heterogeneous Autoregressive (HAR) model and compares its forecasting performance with five machine learning methods, including LightGBM, XGBoost, and LSTM.\"},{\"question\":\"Does adding sentiment improve the HAR model’s forecasting accuracy?\",\"answer\":\"No. Including sentiment does not improve the forecasting accuracy of the HAR model in the study’s results.\"},{\"question\":\"How does sentiment affect volatility forecasts according to the findings?\",\"answer\":\"Investor sentiment influences cryptocurrency market volatility in a nonlinear way, and this effect is only captured by machine learning methods, improving sentiment-based forecasts in 54.17% of cases studied.\"}]","Crypto Volatility Forecasting - Mounting a HAR, Sentiment, and Machine Learning Horserace | PDF",1789643167,86,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":93,"head_meta":95,"extra_data":97,"updated_unix":29},"crypto-volatility-forecasting-mounting-a-har-sentiment-and-machine-learning-horserace","",{"@graph":37,"@context":92},[38,55,75],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/crypto-volatility-forecasting-mounting-a-har-sentiment-and-machine-learning-horserace/291003/",4,{"url":53,"name":13,"@type":56,"image":57,"author":62,"headline":13,"publisher":64,"fileFormat":67,"inLanguage":24,"description":14,"dateModified":68,"datePublished":69,"encodingFormat":67,"isAccessibleForFree":70,"interactionStatistic":71},"DigitalDocument",{"url":58,"@type":59,"width":60,"height":61},"https://docshare.wps.com/thumbnails/crypto-volatility-forecasting-mounting-a-har-sentiment-and-machine-learning-horserace/291003.png","ImageObject",300,407,{"name":9,"@type":63},"Person",{"url":42,"name":65,"@type":66},"DocShare","Organization","application/pdf","2026-10-29","2026-09-17",true,{"@type":72,"interactionType":73,"userInteractionCount":20},"InteractionCounter",{"@type":74},"ViewAction",{"@type":76,"mainEntity":77},"FAQPage",[78,84,88],{"name":79,"@type":80,"acceptedAnswer":81},"What forecasting models are compared in the study?","Question",{"text":82,"@type":83},"The study evaluates a Heterogeneous Autoregressive (HAR) model and compares its forecasting performance with five machine learning methods, including LightGBM, XGBoost, and LSTM.","Answer",{"name":85,"@type":80,"acceptedAnswer":86},"Does adding sentiment improve the HAR model’s forecasting accuracy?",{"text":87,"@type":83},"No. Including sentiment does not improve the forecasting accuracy of the HAR model in the study’s results.",{"name":89,"@type":80,"acceptedAnswer":90},"How does sentiment affect volatility forecasts according to the findings?",{"text":91,"@type":83},"Investor sentiment influences cryptocurrency market volatility in a nonlinear way, and this effect is only captured by machine learning methods, improving sentiment-based forecasts in 54.17% of cases studied.","https://schema.org",{"og:url":53,"og:type":94,"og:title":13,"og:site_name":65,"og:description":14},"article",{"robots":96,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":99},[100,104,108,112,117,122,127,130,135,138,142],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":101,"show_sort_weight":102,"slug":103},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":105,"show_sort_weight":106,"slug":107},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":110,"slug":111},"Exam",70,"exam",{"id":113,"doc_module":4,"doc_module_name":47,"category_name":114,"show_sort_weight":115,"slug":116},5,"Comic",60,"comic",{"id":118,"doc_module":4,"doc_module_name":47,"category_name":119,"show_sort_weight":120,"slug":121},6,"Technology",50,"technology",{"id":123,"doc_module":4,"doc_module_name":47,"category_name":124,"show_sort_weight":125,"slug":126},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":128,"slug":129},30,"research-report",{"id":131,"doc_module":4,"doc_module_name":47,"category_name":132,"show_sort_weight":133,"slug":134},9,"Religion & Spirituality",20,"religion-spirituality",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":136,"show_sort_weight":133,"slug":137},"World Cup","world-cup",{"id":139,"doc_module":4,"doc_module_name":47,"category_name":140,"show_sort_weight":139,"slug":141},10,"Lifestyle","lifestyle",{"id":143,"doc_module":4,"doc_module_name":47,"category_name":144,"show_sort_weight":113,"slug":145},19,"General","general"]