[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123104-en":3,"doc-seo-123104-105":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},123104,687197207639,"Asher","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Designing for Effective Human-Guided Machine Learning Feasibility Analysis - Completed Research Paper","Machine learning offers substantial potential for enterprise data use cases, yet a shortage of skilled data scientists limits adoption. Automated ML can support business users, but it often underperforms when domain knowledge shapes model choice and problem framing, leaving the effectiveness of human-guided ML unclear. A design science research project develops design principles through interviews with seven business users, realizing them in a prototype (MLFeasi). Evaluations indicate that data scientists cannot be fully replaced, and that feasibility analysis should be performed collaboratively for feasible ML use cases.","Association for Information Systems  \nAIS Electronic Library (AISeL)  \n\n| ICIS 2024 Proceedings | International Conference on Information Systems (ICIS) |\n| --- | --- |\n| December 2024\u003Cbr>Designing for Effective Human-Guided Machine Learning Feasibility Analysis\u003Cbr>Jonas Gunklach\u003Cbr>Karlsruhe Institute of Technology, [jonas.gunklach@kit.edu](jonas.gunklach@kit.edu)\u003Cbr>Mario Nadj\u003Cbr>University of Duisburg-Essen, [mario.nadj@ris.uni-due.de](mario.nadj@ris.uni-due.de)\u003Cbr>Merlin Knaeble\u003Cbr>Karlsruhe Institute of Technology (KIT), [merlin.knaeble@kit.edu](merlin.knaeble@kit.edu)\u003Cbr>Isabela Bragaglia\u003Cbr>Aioneers AG, [isabela.bragaglia@aioneers.com](isabela.bragaglia@aioneers.com)\u003Cbr>Alexander Mädche\u003Cbr>Karlsruhe Institute of Technology (KIT), [alexander.maedche@kit.edu](alexander.maedche@kit.edu)\u003Cbr>Follow this and additional works at: [https://aisel.aisnet.org/icis2024](https://aisel.aisnet.org/icis2024) |  |\n\nRecommended Citation  \nGunklach, Jonas; Nadj, Mario; Knaeble, Merlin; Bragaglia, Isabela; and Mädche, Alexander, \"Designing for Effective Human-Guided Machine Learning Feasibility Analysis\" (2024) . ICIS 2024 Proceedings. 1.  \n[https://aisel.aisnet.org/icis2024/humtechinter/humtechinter/1](https://aisel.aisnet.org/icis2024/humtechinter/humtechinter/1)  \nThis material is brought to you by the International Conference on Information Systems (ICIS) at AIS Electronic Library (AISeL) . It has been accepted for inclusion in ICIS 2024 Proceedings by an authorized administrator of AIS Electronic Library (AISeL) . For more information, please [contact elibrary@aisnet.org](contact elibrary@aisnet.org).  \nEffective Human-Guided Machine Learning Feasibility Analysis  \nDesigning for Effective Human-Guided Machine Learning Feasibility Analysis  \nCompleted Research Paper  \nJonas Gunklach  \nKarlsruhe Institute of Technology [jonas.gunklach@kit.edu](jonas.gunklach@kit.edu)  \nMerlin Knaeble  \nKarlsruhe Institute of Technology [merlin.knaeble@kit.edu](merlin.knaeble@kit.edu)  \nMarioNadj  \nUniversity of Duisburg-Essen [mario.nadj@ris.uni-due.de](mario.nadj@ris.uni-due.de)  \nIsabela Bragaglia  \naioneers Technologies GmbH [isabela.bragaglia@aioneers.com](isabela.bragaglia@aioneers.com)  \nAlexander Maedche  \nKarlsruhe Institute of Technology  \n[alexander.maedche@kit.edu](alexander.maedche@kit.edu)  \nAbstract  \nMachine learning (ML) holds immense potential for enterprise data use cases, but a lack of skilled data scientists hinders its utilization. Automated ML (AutoML) aims to empower business users but often falls short, especially when domain knowledge influences model selection. It remains unclear how humanguided ML (HGML) systems can effectively empower business users. To address this, we establish a design science research project. Drawing on the theory of effective use and interviews with seven business users, we present three design principles that we instantiated in our prototype, MLFeasi. Our formative evaluation with business users and data scientists revealed the impracticality of completely replacing data scientists.  \nInstead, a collaborative approach involving data scientists is advocated when ML use cases are deemed feasible-a process we refer to as HGML feasibility analysis. The summative evaluation, including a small-scale experiment and real-world use cases, demonstrates MLFeasi’s effectiveness in improving HGML feasibility analysis.  \nKeywords: Machine Learning, Guidance, Feasibility Analysis, Theory of Effective Use, Business Users, Design Science Research  \nIntroduction  \nMachine Learning (ML) has emerged as a transformative technology that holds the potential to revolutionize business and decision-making processes thus offering the potential to solve a wide range of business challenges (Abbasi et al. 2016) . However, despite the growing demand for ML applications, there exists a significant hurdle that impedes progress – a critical shortage of skilled data scientists. Gartner (2016) estimates revealed that a staggering 85 perc","cbCaig3udYUfJSP2","https://ap.wps.com/l/cbCaig3udYUfJSP2","pdf",1059411,1,18,"English","en",105,"# Introduction\n## Context: ML demand and data scientist shortages\n## Role of business users and domain knowledge\n## Limits of AutoML and the need for guidance\n## Target concept: HGML feasibility analysis","[{\"question\":\"Why are business users central to human-guided machine learning feasibility analysis?\",\"answer\":\"Business users have domain-specific knowledge that helps translate business challenges into ML use cases. This enables them to assess feasibility and frame problems more effectively even without deep ML expertise.\"},{\"question\":\"What problem motivates the proposed HGML feasibility analysis approach?\",\"answer\":\"AutoML systems often fall short when model selection depends on domain knowledge, and implementing ML use cases can require iterative handovers between business users and data scientists. The paper addresses how to empower business users effectively.\"},{\"question\":\"Does MLFeasi replace data scientists in practice?\",\"answer\":\"No. The formative evaluation shows it is impractical to completely replace data scientists, and the paper advocates a collaborative process that involves data scientists when ML use cases are deemed feasible.\"}]","Designing for Effective Human-Guided Machine Learning Feasibility Analysis - Completed Research Paper | PDF",1785814660,45,{"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},"designing-for-effective-human-guided-machine-learning-feasibility-analysis-completed-research-paper","",{"@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/designing-for-effective-human-guided-machine-learning-feasibility-analysis-completed-research-paper/123104/",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},"Why are business users central to human-guided machine learning feasibility analysis?","Question",{"text":75,"@type":76},"Business users have domain-specific knowledge that helps translate business challenges into ML use cases. This enables them to assess feasibility and frame problems more effectively even without deep ML expertise.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What problem motivates the proposed HGML feasibility analysis approach?",{"text":80,"@type":76},"AutoML systems often fall short when model selection depends on domain knowledge, and implementing ML use cases can require iterative handovers between business users and data scientists. The paper addresses how to empower business users effectively.",{"name":82,"@type":73,"acceptedAnswer":83},"Does MLFeasi replace data scientists in practice?",{"text":84,"@type":76},"No. The formative evaluation shows it is impractical to completely replace data scientists, and the paper advocates a collaborative process that involves data scientists when ML use cases are deemed feasible.","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"]