[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128176-en":3,"doc-seo-128176-105":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},128176,549768702563,"Sage","https://ap-avatar.wpscdn.com/avatar/8000c4aa63b76e948b?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786536092046926083",8,"Research & Report","Machine Learning for Sequential Data - Unraveling the Challenges Associated with Feature Encoding, Output Decoding, and Distribution Shifts - Doctoral Dissertation","This doctoral dissertation addresses core difficulties in applying machine learning to sequential data, focusing on three connected stages: feature encoding, output decoding, and the resulting sensitivity to distribution shifts. The work frames these challenges through a structured research background on different sequential data types and modeling pitfalls. Contributions are presented as a set of research papers developing transformer-based and end-to-end learning approaches, robust valuation and forecasting methods, and strategies to detect and mitigate shortcut learning bias under shifting data distributions.","Machine Learning for Sequential Data: Unraveling the Challenges Associated with Feature Encoding, Output Decoding, and Distribution Shifts  \nDer Fakultät für Wirtschaftswissenschaften der  \nUniversität Paderborn  \nzur Erlangung des akademischen Grades  \nDoktor der Wirtschaftswissenschaften  \n- Doctor rerum politicarum   \nvorgelegte Dissertation  \nvon  \nMatthew Caron (M.Sc.)  \ngeboren am 22.03.1986 in St-Hyacinthe  \nRemember that all models are wrong; the practical question is how wrong do they have to be to not be useful.  \n– George Box (1987)  \nAcknowledgements  \nThe last few years have been an incredible journey, and I would like to take a moment to thank the many people who supported me along the way:  \nOliver, for giving me this incredible opportunity, for his generous mentorship, insightful feedback, and constant support. His guidance, critical insights, and ideas have been indispensable throughout this journey.  \nCarina, for her constant support and exceptional organization, ensuring that everything behind the scenes ran smoothly and making our work as easy as possible.  \nJochen and Michael, for the inspiring collaboration, great project ideas, and for opening my eyes to the possibilities at the intersection of data science and sports analytics – an opportunity that has shaped my career path.  \nGuido, for the many insightful discussions, valuable feedback, and thoughtful advice that have helped me grow academically and professionally.  \nDavid and Frederik, for always believing in me and for being incredible friends and confidants – always being there for me, day or night.  \nJohannes, for the great collaboration, engaging discussions, and willingness to always lend a hand. Your contributions and friendship will not be forgotten.  \nLast but not least, Maryna, for always being there for me, for her endless support, patience, and understanding. Knowing that you are proud of me and always by my side means everything.  \nContents  \nList of Figures v  \nList of Tables vii  \nPart A: Synopsis 1  \n1 Introduction 3  \n1. 1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3  \n1.2 Objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3  \n1.3 List of Publications . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4  \n1.4 Thesis Structure . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6  \n2 Research Background 7  \n2. 1 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7  \n2.2 Sequential Data . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7  \n2.2. 1 Definition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7  \n2.2.2 Time Series Data . . . . . . . . . . . . . . . . . . . . . . . . . . 8  \n2.2.3 Panel Data . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9  \n2.2.4 Event Data . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10  \n2.2.5 Spatio-Temporal Data . . . . . . . . . . . . . . . . . . . . . . . 11  \n2.2.6 Textual Data . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11  \n2.3 Challenges of Modeling Sequential Data . . . . . . . . . . . . . . . . . 12  \n2.3. 1 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12  \n2.3.2 Feature Encoding & Output Decoding .............. 13  \n2.3.3 Distribution Shifts in Machine Learning ............. 14  \n3 Research Contributions 17  \n3. 1 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17  \n3.2 Paper 1 – Hardening Soft Information ................... 20  \n3.3 Paper 2 – PIVOT: A Framework for Valuing Actions in Handball ... 22  \n3.4 Paper 3 – To the Moon! Analyzing the Community of “Degenerates” . 24  \n3.5 Paper 4 – Towards Transparent Data-Driven Brand Valuation . . . . . 27  \n3.6 Paper 5 – Shortcut Learning in Financial Text Mining ......... 30  \n3.7 Paper 6 – Integrating Driver Behavior into Last-Mile Delivery Routing 33  \n3.8 Paper 7 – TacticalGPT: LLMs for Tactical Decisions in Football . . . . 3","cbCaicaF4eXGboyy","https://ap.wps.com/l/cbCaicaF4eXGboyy","pdf",5668422,1,86,"English","en",105,"# Contents\n## Part A: Synopsis\n### 1 Introduction\n## 2 Research Background\n## 3 Research Contributions\n## 4 Discussion & Conclusion\n## Part B: Research Papers\n# Bibliography","[{\"question\":\"What main problems does the dissertation target in sequential-data machine learning?\",\"answer\":\"It targets challenges spanning feature encoding, output decoding, and the impact of distribution shifts on model reliability and generalization.\"},{\"question\":\"How are the research contributions organized?\",\"answer\":\"They are grouped into a synopsis part and a separate collection of individual research papers, each addressing a specific methodological problem.\"},{\"question\":\"Why is distribution shift emphasized in the dissertation?\",\"answer\":\"Because performance can degrade and misleading shortcuts can appear when training and evaluation distributions differ, so the thesis develops ways to detect and mitigate such biases.\"}]","Machine Learning for Sequential Data - Unraveling the Challenges Associated with Feature Encoding, Output Decoding, and Distribution Shifts - Doctoral Dissertation | PDF",1785945301,217,{"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},"machine-learning-for-sequential-data-unraveling-the-challenges-associated-with-feature-encoding-output-decoding-and-distribution-shifts-doctoral-dissertation","",{"@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/machine-learning-for-sequential-data-unraveling-the-challenges-associated-with-feature-encoding-output-decoding-and-distribution-shifts-doctoral-dissertation/128176/",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","2026-08-23","2026-08-05",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 main problems does the dissertation target in sequential-data machine learning?","Question",{"text":76,"@type":77},"It targets challenges spanning feature encoding, output decoding, and the impact of distribution shifts on model reliability and generalization.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How are the research contributions organized?",{"text":81,"@type":77},"They are grouped into a synopsis part and a separate collection of individual research papers, each addressing a specific methodological problem.",{"name":83,"@type":74,"acceptedAnswer":84},"Why is distribution shift emphasized in the dissertation?",{"text":85,"@type":77},"Because performance can degrade and misleading shortcuts can appear when training and evaluation distributions differ, so the thesis develops ways to detect and mitigate such biases.","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"]