[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121341-en":3,"doc-seo-121341-105":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},121341,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Machine Learning the Cross-Section of Corporate Bond Excess Returns - Master Thesis","This thesis uses machine learning to predict the cross-section of corporate bond excess returns, both through direct modeling and via rank-transformations. Evidence indicates that non-linearities improve prediction quality for corporate bond excess returns, yet untransformed features yield the best out-of-sample results for non-linear models. Model performance is shown to be fragile regarding outlier handling and feature transformations, requiring careful implementation. The study also finds that higher OOS-R2 does not necessarily translate into stronger portfolio performance.","WISEflow Europe/Oslo(CEST)  \n30 Jun 2024  \nHandelshøyskolen BIGRA 1 9 7 0 3 Master  \nT hes is  \nF i n a l T h e s i s M a s t e r o f S c i e  c 1 0 0 %  \nP r e d e f i n e r t i n f o r m a s j o n  \nStartdato: 08-01-2024 09:00 CET  \nSluttdato: 01-07-2024 12:00 CEST  \nEksamensform: T  \nTermin: 202410  \nVurderingsform: Norsk 6-trinns skala (A-F)  \nFlowkode: 202410||11436||IN00||W||T  \nExternal assessor: External assessor 1  \nInternal assessor: Internal assessor 1  \nName:  \n\n| Steffen Larsen, Sondre | Skår |\n| --- | --- |\n\n\n| I n f o r m a s j o n f r a d e l t a k e r\u003Cbr>Tittel *: Machine Learning the Cross-Section of Corporate Bond Excess Returns Navn på veileder *: Paolo Giordani |  |  |  |\n| --- | --- | --- | --- |\n| Inneholder besvarelsenkonfidensielt materiale?: | Nei | Kan besvarelsenoffentliggjøres?: | Ja |\n\nG r u p p e  \nGruppenavn: (Anonymisert)  \nGruppenummer: 279  \nAndre medlemmer igruppen:  \nMachine Learning the Cross-Section of Corporate Bond Excess Returns  \nMaster Thesis  \nby  \nSondre Sk˚ar and Steffen Larsen  \nMSc in Quantitative Finance  \nSupervisor:  \nPaolo Giordani  \nOslo, June 30, 2024  \nABSTRACT  \nWe use machine learning, to predict the cross-section of corporate bond excess returns, both directly and via rank-transformations.  \nWe find some evidence that non-linearities matter for corporate bond excess return predictions and that using untransformed features produces the best out-of-sample results for the non-linear models. However, the fragility of the models in terms of the handling of outliers and transformation of features is something that needs careful consideration when trying to predict corporate bond excess returns. We also find that a forecast’s OOS-R2 is not necessarily a good indication of portfolio performance.  \nThis thesis is a part of the MSc programme at BI Norwegian Business School. The school takes no responsibility for the methods used, results found,  \nor conclusions drawn.  \nAcknowledgements  \nThe authors of this thesis would like to express their gratitude to our supervisor, Paolo Giordani, at the Department of Finance at BI Norwegian Business School. We deeply appreciate his guidance, support, and willingness to share his extensive knowledge of machine learning as applied to financial topics.  \nWe also want to thank Alexander Dickerson, at the School of Banking & Finance at the University of New South Wales (UNSW) in Sydney, Australia, for taking the time to have a call with us and give us guidance and tips on the use of the corporate bond data published on his website.  \nDisclaimer  \nNo text in this thesis has been generated or suggested using AI. We have used ChatGPT to improve the text and Grammarly to suggest grammatical or spelling corrections and used our discretion to accept or reject any of the suggestions. We have used ChatGPT to suggest or improve part or all of the code in the computer programs used in the conduct of the research reported in this thesis.  \nContents  \nList of Tables IV  \nList of Figures IV  \n1 Introduction and motivation 1  \n2 Literature review 4  \n2.1 Corporate bond data: No CRSP ..................... 4  \n2.2 Corporate bond (and equity) factors .................. 8  \n2.3 Bond Risk Premiums with Machine Learning .............. 9  \n3 Data 12  \n3.1 Overview .................................. 12  \n3.2 The target variable ............................ 13  \n3.3 The features ................................ 14  \n4 Hypothesis and Methodology 16  \n4.1 Hypothesis ................................. 16  \n4.2 Methods-Machine Learning ....................... 17  \n4.2.1 Cross Validation ......................... 18  \n4.2.2 Benchmark regression ....................... 19  \n4.2.3 Gradient Boosted trees: XGBoost ................ 19  \n5 Results and analysis 21  \n5.1 Predicting with Ridge regression ..................... 21  \n5.2 Predicting with XGBoost ......................... 23  \n5.3 Comparing forecasting performance ................... 26  \n5.4 Portfolios ...............","cbCaiclGsUp1DE0B","https://ap.wps.com/l/cbCaiclGsUp1DE0B","pdf",1165379,1,75,"English","en",105,"# Contents\n## Introduction and motivation\n## Literature review\n## Data\n## Hypothesis and Methodology\n## Results and analysis\n## Conclusion\n## Appendix\n## List of Abbreviations\n## List of Tables\n## List of Figures","[{\"question\":\"What prediction task does the thesis address?\",\"answer\":\"The thesis predicts the cross-section of corporate bond excess returns using machine learning, both directly and via rank-transformations.\"},{\"question\":\"What do the results suggest about non-linear models and feature handling?\",\"answer\":\"Non-linearities appear to matter for predictions, and for non-linear models the best out-of-sample results come from using untransformed features. The models also prove fragile when handling outliers and when transforming features.\"},{\"question\":\"Does OOS-R2 reliably indicate portfolio performance?\",\"answer\":\"No. The thesis finds that a forecast’s OOS-R2 is not necessarily a good indication of portfolio performance.\"}]","Machine Learning the Cross-Section of Corporate Bond Excess Returns - Master Thesis | PDF",1785735150,189,{"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},"machine-learning-the-cross-section-of-corporate-bond-excess-returns-master-thesis","",{"@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/machine-learning-the-cross-section-of-corporate-bond-excess-returns-master-thesis/121341/",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","2026-08-03",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 prediction task does the thesis address?","Question",{"text":75,"@type":76},"The thesis predicts the cross-section of corporate bond excess returns using machine learning, both directly and via rank-transformations.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What do the results suggest about non-linear models and feature handling?",{"text":80,"@type":76},"Non-linearities appear to matter for predictions, and for non-linear models the best out-of-sample results come from using untransformed features. The models also prove fragile when handling outliers and when transforming features.",{"name":82,"@type":73,"acceptedAnswer":83},"Does OOS-R2 reliably indicate portfolio performance?",{"text":84,"@type":76},"No. The thesis finds that a forecast’s OOS-R2 is not necessarily a good indication of portfolio performance.","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"]