[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126557-en":3,"doc-seo-126557-105":31,"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},126557,13056712833777,"Logic","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Quantifying and Explaining Machine Learning Uncertainty in Predictive Process Monitoring - An Operations Research Perspective","This paper introduces a comprehensive multi-stage machine learning methodology that combines information systems and artificial intelligence to improve decision-making in operations research. The framework addresses key shortcomings in prior work, including missing data-driven estimation for important production parameters, reliance on point forecasts without model uncertainty, and limited explanations of uncertainty origins. Quantile Regression Forests generate interval predictions, while local and global SHapley Additive Explanations support interpretable uncertainty insights. A production planning case study demonstrates practical value and highlights the role of prescriptive analytics.","arXiv :2304 .06412v1 [ cs .LG] 13 Apr 2023  \nQuantifying and Explaining Machine Learning Uncertainty in Predictive Process Monitoring: An Operations Research Perspective  \nNijat Mehdiyev 1,2*, Maxim Majlatow 1,2 and Peter Fettke 1,2  \n1 German Research Center for Arti􀀌cial Intelligence (DFKI), Campus D 3.2, Saarbr􀁿ucken, 66123, Saarland, Germany.  \n2 Saarland University, Campus D 3 .2, Saarbr􀁿ucken, 66123, Saarland, Germany.  \n*Corresponding author. E-mail: [nijat.mehdiyev@dfki.de](nijat.mehdiyev@dfki.de) ; Contributing [authors:](authors: maxim.majlatow@dfki.de)[ maxim.majlatow@dfki.de](authors: maxim.majlatow@dfki.de);  \n[peter.fettke@dfki.de](peter.fettke@dfki.de) ;  \nAbstract  \nThis paper introduces a comprehensive, multi-stage machine learning methodology that e􀀋ectively integrates information systems and arti􀀌 -cial intelligence to enhance decision-making processes within the domain of operations research. The proposed framework adeptly addresses common limitations of existing solutions, such as the neglect of data-driven estimation for vital production parameters, exclusive generation of point forecasts without considering model uncertainty, and lacking explanations regarding the sources of such uncertainty. Our approach employs Quantile Regression Forests for generating interval predictions, alongside both local and global variants of SHapley Additive Explanations for the examined predictive process monitoring problem. The practical applicability of the proposed methodology is substantiated through a real-world production planning case study, emphasizing the potential of prescriptive analytics in re􀀌ning decision-making procedures. This paper accentuates the imperative of addressing these challenges to fully harness the extensive and rich data resources accessible for well-informed decision-making.  \nKeywords: Explainable Arti􀀌cial Intelligence (XAI), Uncertainty  \nQuanti􀀌cation (UQ), Predictive Process Monitoring, Information Systems (IS)  \n2  \n1 Introduction  \nIn today's highly competitive and complex business environment, organizations are under constant pressure to optimize their performance and decision-making processes. According to Herbert Simon, enhancing organizational performance relies on e􀀋ectively channeling 􀀌nite human attention towards critical data for decision-making, necessitating the integration of information systems (IS), arti􀀌cial intelligence (AI) and operations research (OR) insights [1] . Recent OR research provides evidence in support of this proposition, as the discipline has witnessed a transformation due to the abundant availability of rich and voluminous data from various sources coupled with advances in machine learning [2] . As of late, heightened academic attention has been devoted to prescriptive analytics, a discipline that suggests combining the results of predictive analytics with optimization techniques in a probabilistic framework to generate responsive, automated, restricted, time-sensitive, and ideal decisions [3] .  \nThe con􀀍uence of AI and OR is evident due to their interdependent and complementary nature, as both disciplines strive to augment decision-making processes through computational and mathematical methodologies [4] . Various integration scenarios exist for combining these disciplines in order to address real-world problems. A prevalent method is the \"predict-then-optimize approach\", where machine learning is used to predict essential parameters of an optimization model before or simultaneously as the optimization models are solved [5] . In this context, data-driven analytics techniques have proven e􀀋ective in addressing a diverse range of operations research (OR) problems, encompassing areas such as capacity planning [6], production planning and scheduling [7], distribution planning [8], inventory management [9], transportation [10], sales and operations planning [11], dynamic pricing and revenue management [12] . Employing data-driven decision-making within these bu","cbCailkVPAMuPj3F","https://ap.wps.com/l/cbCailkVPAMuPj3F","pdf",2056946,2,1,43,"English","en",105,"# Introduction\n## AI and OR integration scenarios\n## Predict-then-optimize in operations research\n## Key gaps: data-driven parameter estimation and uncertainty handling\n## Key gaps: point forecasts and missing uncertainty explanations","[{\"question\":\"What limitations in existing predictive process monitoring are targeted by the paper?\",\"answer\":\"The approach addresses the neglect of data-driven estimation for critical production parameters, the exclusive use of point forecasts without uncertainty, and the lack of explanations about where uncertainty originates.\"},{\"question\":\"How does the proposed method quantify predictive uncertainty?\",\"answer\":\"It uses Quantile Regression Forests to produce interval predictions rather than only point forecasts.\"},{\"question\":\"How does the paper explain uncertainty in the context of predictive process monitoring?\",\"answer\":\"It applies local and global SHapley Additive Explanations (SHAP variants) to explain sources of uncertainty for the predictive monitoring problem.\"}]","Quantifying and Explaining Machine Learning Uncertainty in Predictive Process Monitoring - An Operations Research Perspective | PDF",1785933311,108,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"quantifying-and-explaining-machine-learning-uncertainty-in-predictive-process-monitoring-an-operations-research-perspective","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/quantifying-and-explaining-machine-learning-uncertainty-in-predictive-process-monitoring-an-operations-research-perspective/126557/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-27","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 limitations in existing predictive process monitoring are targeted by the paper?","Question",{"text":76,"@type":77},"The approach addresses the neglect of data-driven estimation for critical production parameters, the exclusive use of point forecasts without uncertainty, and the lack of explanations about where uncertainty originates.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the proposed method quantify predictive uncertainty?",{"text":81,"@type":77},"It uses Quantile Regression Forests to produce interval predictions rather than only point forecasts.",{"name":83,"@type":74,"acceptedAnswer":84},"How does the paper explain uncertainty in the context of predictive process monitoring?",{"text":85,"@type":77},"It applies local and global SHapley Additive Explanations (SHAP variants) to explain sources of uncertainty for the predictive monitoring problem.","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":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]