[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124042-en":3,"doc-seo-124042-105":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},124042,8796095461610,"Oliver","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Topics in Bayesian machine learning for finance","This thesis presents novel Bayesian machine learning-based approaches to selected problems in finance. It models perceived market inefficiencies using curated financial data sets, and evaluates market trading and investment strategies to deliver three contributions. The work includes a deep learning prediction framework for intraday limit order book data with short-term forecasts and aleatoric uncertainty, plus pseudo-Bayesian estimation of epistemic uncertainty. It also reframes Black-Litterman with view uncertainty and data fusion, and develops a Bayes-based conditional factor state space model for multivariate equity trading with transaction costs over 29 years.","Topics in Bayesian machine learning for finance  \nTrent Spears  \nKellogg College  \nA thesis submitted for the degree of Doctor of Philosophy  \nSupervised by  \nAssoc. Prof. Stefan Zohren and Prof. Stephen Roberts  \nDepartment of Engineering Science University of Oxford  \nHilary Term, 2024  \nTo Hadley andRorik  \nDeclaration  \nI declare that this thesis is entirely my own work and, except where stated, describes my own research.  \nTrent Spears Kellogg College  \nThis document was created using the LATEX typesetting system. The underlying LATEX file structure for this thesis was adapted from the open-source Github template provided in  \nAcknowledgements  \nThank you to my supervisors. I would like to extend my deepest gratitude to Prof Stephen Roberts. I appreciate you sharing your energy, unbounded positivity, and immense intellect for the duration of my study period. I am also grateful for the supervision of Dr Stefan Zohren, and the guidance, lively discussion, trust, and encouragement that came with it.  \nThank you, Anthony Ledford and the team at the Oxford-Man Institute (OMI), who steward such a wonderful hub for student research. The department provided a supportive and inspiring environment to pursue quantitative finance research. The financial support provided by the OMI is also gratefully acknowledged.  \nI would like to acknowledge members of the OMI including academics Dr Jan-Peter Calliess, Prof Nir Vulkan and Dr Jeremy Large. Your advice and support had a direct and meaningful impact on my development as a junior researcher. Thank you also to the students within the OMI, especially those in my intake from neighbouring pods including Daniel Poh, Sam Kessler, Max Ahrens and Yin-Cong Zhi, who each contributed to making the research environment so pleasant.  \nAt home, I have been fortunate to have the ultimate companions and support, and I gratefully acknowledge Ingrid, Hadley and, more recently, Rorik. I am also thankful for my other immediate family Jacqueline, Carol, Scott, Brooke, and the late Graham, for many years of love, direction, and belief in my choices.  \nFinally, thank you to my teachers and mentors from the last 20 years. I have been so incredibly lucky to have you. Your efforts were critical in shaping my education and desire to understand the world. I look forward to paying it on.  \nAbstract  \nThis thesis presents novel Bayesian machine learning-based approaches to selected problems in finance. We investigate and model perceived market inefficiencies with respect to curated financial data sets, then assess market trading and investment strategies, yielding the following three contributions.  \nFirstly, we consider a modern deep learning prediction model given intraday limit order book data constituting of a subset of Eurodollar futures contracts, the popular and liquidly traded set of interest rate derivatives. The data is spatio-temporal in nature, such that the model utilises convolutional neural networks for automated feature extraction andrecurrent neural networks for time series prediction. We show how to train the network to yield short-term forecasts paired with aleatoric uncertainty estimates by specifying a suitable loss function. Further, we estimate an approximation to epistemic uncertainty via a pseudo-Bayesian deep learning method. This work demonstrates the utility of the model output for deciding the relative allocation of risk capital across trades. That is, investment sizes are scaled between trade opportunities in a principled and data-driven way. We calculate the trading benefit and demonstrate model outperformance relative to strategies that either do not take uncertainty into account, or that utilize an alternative-yet-common market-based statistic as a proxy for uncertainty.  \nThe Black-Litterman model extends the framework of the Markowitz Modern Portfolio Theory to incorporate investor views. In our second work, we recognise this extension as a Bayesian formulation, and relate view unc","cbCaio13yRbGU7kx","https://ap.wps.com/l/cbCaio13yRbGU7kx","pdf",5714168,1,154,"English","en",105,"# Abstract\n## Bayesian deep learning for intraday prediction and uncertainty\n## Black-Litterman as a Bayesian view model with data fusion\n## Bayes-based conditional factor model for statistical arbitrage","[{\"question\":\"What are the three main contributions of the thesis?\",\"answer\":\"The thesis contributes (1) a Bayesian deep learning prediction approach using intraday limit order book data with uncertainty estimates, (2) a Bayesian interpretation of Black-Litterman with view uncertainty and consistency-based data fusion, and (3) a Bayes-based conditional factor state space model for statistical arbitrage trading in US equities.\"},{\"question\":\"How does the thesis estimate different types of uncertainty in the prediction model?\",\"answer\":\"It produces aleatoric uncertainty directly via a suitable loss function, and estimates epistemic uncertainty through a pseudo-Bayesian deep learning method.\"},{\"question\":\"How is the Black-Litterman extension linked to data fusion in this work?\",\"answer\":\"The thesis treats view uncertainty in a Bayesian formulation and considers multiple estimates for the same asset subset at a point in time, using data fusion techniques to synthesize fused view and uncertainty pairs that guide portfolio allocation.\"}]","Topics in Bayesian machine learning for finance | PDF",1785820061,388,{"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},"topics-in-bayesian-machine-learning-for-finance","",{"@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/topics-in-bayesian-machine-learning-for-finance/124042/",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","2026-08-05","2026-08-04",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},"What are the three main contributions of the thesis?","Question",{"text":76,"@type":77},"The thesis contributes (1) a Bayesian deep learning prediction approach using intraday limit order book data with uncertainty estimates, (2) a Bayesian interpretation of Black-Litterman with view uncertainty and consistency-based data fusion, and (3) a Bayes-based conditional factor state space model for statistical arbitrage trading in US equities.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the thesis estimate different types of uncertainty in the prediction model?",{"text":81,"@type":77},"It produces aleatoric uncertainty directly via a suitable loss function, and estimates epistemic uncertainty through a pseudo-Bayesian deep learning method.",{"name":83,"@type":74,"acceptedAnswer":84},"How is the Black-Litterman extension linked to data fusion in this work?",{"text":85,"@type":77},"The thesis treats view uncertainty in a Bayesian formulation and considers multiple estimates for the same asset subset at a point in time, using data fusion techniques to synthesize fused view and uncertainty pairs that guide portfolio allocation.","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"]