[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122781-en":3,"doc-seo-122781-105":30,"detail-sidebar-cat-0-en-105":91},{"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":4,"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},122781,1649267921044,"Ava Thompson","https://us-avatar.wpscdn.com/avatar/1800007509477c92dfb?_k=1782875107921204101",8,"Research & Report","Forecasting mid-price movement of Bitcoin futures using machine learning","The paper addresses challenges investors face in understanding price dynamics across assets in the wake of the global financial crisis and the ongoing COVID-19 pandemic. It evaluates the forecasting performance of multiple machine learning algorithms for predicting the mid-price movement of Bitcoin futures. Using high-frequency intraday data, the study compares results across time frequencies from 5 to 60 minutes. Findings show that five of six models achieve average classification accuracy consistently above 50%, outperforming benchmark approaches such as ARIMA and random walk during COVID-19 market turmoil.","Zurich Open Repository and Archive  \nUniversity of Zurich  \nUniversity Library Strickhofstrasse 39  \nCH-8057 Zurich [www.zora.uzh.ch](www.zora.uzh.ch)  \nYear: 2021  \nForecasting mid-price movement of Bitcoin futures using machine learning  \nAkyildirim, Erdinc ; Cepni, Oguzhan ; Corbet, Shaen ; Uddin, Gazi Salah  \nAbstract: In the aftermath of the global financial crisis and ongoing COVID-19 pandemic, investors face challenges in understanding price dynamics across assets. This paper explores the performance of the various typeof machine learning algorithms (MLAs) to predict mid-price movement for Bitcoin futures prices. We use highfrequency intraday data to evaluate the relative forecasting performances across various time frequencies, ranging between 5 and 60-min. Our findings show that the average classification accuracy for five out of the six MLAs is consistently above the 50% threshold, indicating that MLAs outperform benchmark models such as ARIMA and random walk in forecasting Bitcoin futures prices. This highlights the importance and relevance of MLAs to produce accurate forecasts for bitcoin futures prices during the COVID-19 turmoil.  \nDOI: [https://doi.org/10.1007/s10479-021-04205-x](https://doi.org/10.1007/s10479-021-04205-x)  \nPosted at the Zurich Open Repository and Archive, University of Zurich ZORA URL: [https://doi.org/10.5167/uzh-235842](https://doi.org/10.5167/uzh-235842)  \nJournal Article Published Version  \nThe following work is licensed under a Creative Commons: Attribution 4.0 International (CC BY 4.0) License.  \nOriginally published at:  \nAkyildirim, Erdinc; Cepni, Oguzhan; Corbet, Shaen; Uddin, Gazi Salah (2021) . Forecasting mid-price movement of Bitcoin futures using machine learning. Annals of Operations Research:Epub ahead of print.  \nDOI: [https://doi.org/10.1007/s10479-021-04205-x](https://doi.org/10.1007/s10479-021-04205-x)  \nAnnals of Operations Research  \n[https://doi.org/10.1007/s10479-021-04205-x](https://doi.org/10.1007/s10479-021-04205-x)  \nORIGINAL RESEARCH  \nForecasting mid-price movement of Bitcoin futures using machine learning  \nErdinc Akyildirim1,2 · Oguzhan Cepni3,4 · Shaen Corbet5,6 · Gazi Salah Uddin7  \nAccepted: 30 June 2021  \n© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2021  \nAbstract  \nIn the aftermath of the global financial crisis and ongoing COVID-19 pandemic, investors face challenges in understanding price dynamics across assets. This paper explores the performance of the various type of machine learning algorithms (MLAs) to predict mid-price movement for Bitcoin futures prices. We use high-frequency intraday data to evaluate the relative forecasting performances across various time frequencies, ranging between 5 and 60-min. Our findings show that the average classification accuracy for five out of the six MLAs is consistently above the 50% threshold, indicating that MLAs outperform benchmark models such as ARIMA and random walk in forecasting Bitcoin futures prices. This highlights the importance and relevance of MLAs to produce accurate forecasts for bitcoin futures prices during the COVID-19 turmoil.  \nKeywords Cryptocurrency · Bitcoin futures · Machine learning · Covid-19 · k-Nearest neighbours · Logistic regression · Naive Bayes · Random forest · Support vector machine · Extreme gradient boosting  \n1 Introduction  \nIn this research, we use high-frequency Bitcoin pricing data together with machine learning algorithms to predict mid-price movement for bitcoin futures price series across a variety of time frequencies, ranging between 5 and 60-min. The novelty of our research surrounds the  \nB Erdinc Akyildirim [erdinc.akyildirim@bf.uzh.ch](erdinc.akyildirim@bf.uzh.ch)  \n1 Department of Banking and Finance, Burdur Mehmet Akif Ersoy University, Burdur, Turkey  \n2 Department of Banking and Finance, University of Zurich, Zurich, Switzerland  \n3 Department of Economics, Copenhagen Business School, Porcelænshaven 16A, 2","cbCaitmQBZ0qgHYl","https://ap.wps.com/l/cbCaitmQBZ0qgHYl","pdf",338675,1,33,"English","en",105,"# Abstract\n# Introduction\n## Data and trading context\n## Forecasting approach and evaluation","[{\"question\":\"What does the paper forecast for Bitcoin futures?\",\"answer\":\"It forecasts the mid-price movement of Bitcoin futures using machine learning classifiers.\"},{\"question\":\"What data and time horizons are used in the study?\",\"answer\":\"The research uses high-frequency intraday Bitcoin pricing data and evaluates multiple time frequencies ranging from 5 to 60 minutes.\"},{\"question\":\"How do machine learning models perform compared with benchmark methods?\",\"answer\":\"Five out of six machine learning algorithms achieve average classification accuracy above 50%, outperforming benchmarks such as ARIMA and random walk.\"}]","Forecasting mid-price movement of Bitcoin futures using machine learning | PDF",1785812861,83,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"forecasting-mid-price-movement-of-bitcoin-futures-using-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@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-mid-price-movement-of-bitcoin-futures-using-machine-learning/122781/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What does the paper forecast for Bitcoin futures?","Question",{"text":75,"@type":76},"It forecasts the mid-price movement of Bitcoin futures using machine learning classifiers.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What data and time horizons are used in the study?",{"text":80,"@type":76},"The research uses high-frequency intraday Bitcoin pricing data and evaluates multiple time frequencies ranging from 5 to 60 minutes.",{"name":82,"@type":73,"acceptedAnswer":83},"How do machine learning models perform compared with benchmark methods?",{"text":84,"@type":76},"Five out of six machine learning algorithms achieve average classification accuracy above 50%, outperforming benchmarks such as ARIMA and random walk.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]