[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119126-en":3,"doc-seo-119126-105":30,"detail-sidebar-cat-0-en-105":92},{"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":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},119126,8796095462418,"Noah","https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780",8,"Research & Report","Forecasting Bitcoin volatility using machine learning techniques - Article","This paper studies Bitcoin volatility forecasting performance by comparing traditional econometric models with machine learning methods. It evaluates 1-day to 2-month ahead forecasts using Long Short-Term Memory (LSTM) and a hybrid Convolutional Neural Network-LSTM (CNN-LSTM) approach, against Generalised Autoregressive Conditional Heteroskedasticity (GARCH) and Heterogeneous Autoregressive (HAR) baselines. Neural networks outperform GARCH across all horizons, and LSTM also beats HAR. Adding Markov Transition Field (MTF) to CNN-LSTM improves especially short-term, notably 7-day, forecasting.","Forecasting Bitcoin volatility using machine learning techniques  \nArticle  \nPublished Version  \nCreative Commons: Attribution 4.0 (CC-BY)  \nOpen Access  \nHuang, Z.-C., Sangiorgi, I. ORCID: [https://orcid.org/0000-](https://orcid.org/0000-)[ ](https://orcid.org/0000-)[0002-8344-9983 and Urquhart](0002-8344-9983 and Urquhart) , A. ORCID:  \n[https://orcid.org/0000-0001-8834-4243](https://orcid.org/0000-0001-8834-4243) (2024) Forecasting Bitcoin volatility using machine learning techniques. Journal of International Financial Markets, Institutions and Money, 97.  \n102064. ISSN 1873-0612 doi:  \n[https://doi.org/10.1016/j.intfin.2024.102064 Available at](https://doi.org/10.1016/j.intfin.2024.102064 Available at)  \n[https://centaur. reading.ac. uk/1](https://centaur. reading.ac. uk/1) 18950/  \nIt is advisable to refer to the publisher’s version if you intend to cite from the work. See Guidance on citing.  \nTo link to this article DOI: [http://dx.doi.org/10.1016/j.intfin.2024.102064](http://dx.doi.org/10.1016/j.intfin.2024.102064)  \nPublisher: Elsevier  \nAll outputs in CentAUR are protected by Intellectual Property Rights law, including copyright law. Copyright and IPR is retained by the creators or other copyright holders . Terms and conditions for use of this material are defined in the End User Agreement  .  \n[www. reading.ac. uk/centaur](www. reading.ac. uk/centaur)  \nCentAUR  \nCentral Archive at the University of Reading  \nReading’s research outputs online  \n| Forecasting Bitcoin volatility using machine learning techniques\u003Cbr>Zih-Chun Huang a, Ivan Sangiorgi a, Andrew Urquhart b,∗ a ICMA Centre, Henley Business School, University of Reading, Reading, United Kingdom b Birmingham Business School, University of Birmingham, Birmingham, United Kingdom |  |  |  |\n| --- | --- | --- | --- |\n| A R T I C L E I N F O |  | A B S T R A C T |  |\n| JEL classification:\u003Cbr>C45 C53 G17\u003Cbr>Keywords: Bitcoin\u003Cbr>Volatility forecasting Machine learning |  | This paper studies the Bitcoin volatility forecasting performance between popular traditional econometric models and machine learning techniques. We compare the 1-day to 2-month ahead forecasting performance of the Long Short-Term Memory (LSTM) and a hybrid Convolutional Neural Network-LSTM (CNN-LSTM) model to the traditional models. We find that neural networks outperform Generalised Autoregressive Conditional Heteroskedasticity (GARCH) models for all forecasting horizons. Furthermore, the LSTM model outperforms the Heterogeneous Autoregressive (HAR) model and by integrating the Markov Transition Field (MTF) into the CNN-LSTM model, we achieve superior forecasting results in the short-term, particularly for the 7-day forecasts. |  |\n\n1. Introduction  \nHeterogeneous Autoregressive (HAR) models have been shown to outperform many standard volatility forecasting models when forecasting Bitcoin (Shen et al., 2020; Urquhart, 2017b; Zhang and Tan, 2018). However, with their growth and popularity evergrowing, we examine whether machine learning techniques can beat the HAR model in Bitcoin volatility forecasting. Second, we empirically test whether high-frequency Bitcoin data provide valuable information for Bitcoin volatility estimation. We aim to improve Bitcoin volatility forecasting accuracy by employing a hybrid neural network model along with image transformation.  \nOur primary contributions are threefold. First, we apply machine learning models to forecast Bitcoin volatility using highfrequency data. We use neural network models to extract extra hidden information from the images transformed from the high-frequency Bitcoin volatility data. Instead of incorporating additional factors, such as macroeconomic indicators (Feng et al., 2024) or Google Trends data (Seo and Kim, 2020), we utilise the Markov Transition Field (MTF) technique (Wang et al., 2015), converting ordinary time series into images with transitional probabilities, and demonstrate that MTF can contribute to Bitcoin volatility predictio","cbCaiaYAyQCah5Wy","https://ap.wps.com/l/cbCaiaYAyQCah5Wy","pdf",2518889,1,22,"English","en",105,"# Introduction\n## Research motivation and objective\n## Main contributions\n## Forecasting challenge and data considerations","[{\"question\":\"Which models are compared for Bitcoin volatility forecasting?\",\"answer\":\"The study compares traditional econometric approaches (including GARCH and HAR) with machine learning methods, specifically LSTM and a hybrid CNN-LSTM model.\"},{\"question\":\"How far ahead does the paper forecast Bitcoin volatility?\",\"answer\":\"It evaluates forecasting performance from 1-day to 2-month ahead horizons.\"},{\"question\":\"What key technique improves the CNN-LSTM model’s performance?\",\"answer\":\"Integrating Markov Transition Field (MTF) into CNN-LSTM yields superior short-term results, particularly for 7-day forecasts.\"}]","Forecasting Bitcoin volatility using machine learning techniques - Article | PDF",1785722526,55,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"forecasting-bitcoin-volatility-using-machine-learning-techniques-article","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/forecasting-bitcoin-volatility-using-machine-learning-techniques-article/119126/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04","2026-08-03",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Which models are compared for Bitcoin volatility forecasting?","Question",{"text":76,"@type":77},"The study compares traditional econometric approaches (including GARCH and HAR) with machine learning methods, specifically LSTM and a hybrid CNN-LSTM model.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How far ahead does the paper forecast Bitcoin volatility?",{"text":81,"@type":77},"It evaluates forecasting performance from 1-day to 2-month ahead horizons.",{"name":83,"@type":74,"acceptedAnswer":84},"What key technique improves the CNN-LSTM model’s performance?",{"text":85,"@type":77},"Integrating Markov Transition Field (MTF) into CNN-LSTM yields superior short-term results, particularly for 7-day forecasts.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]