[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125279-en":3,"doc-seo-125279-105":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},125279,2336464648746,"Skyler","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Machine Learning for Probabilistic and Attribute-Aware Process Mining - Doctoral Dissertation","In a setting of pervasive digitalisation, processes can be recorded and analysed to gain insights, make predictions, support better decisions, and enable optimisation. Real-world process variability must be modelled alongside process attributes, which drive different variants under specific conditions, while stochasticity adds an additional, unavoidable source of variation. This thesis studies machine learning methods to address variability in process mining, focusing first on neural-network uncertainty for next-activity prediction, then on explicit process-model approaches for trace clustering, decision discovery, and stochastic model composition using attributes and prior executed activities.","Machine Learning for Probabilistic and Attribute-Aware Process Mining  \nDoctoral Dissertation of:  \nPietro Portolani  \nAdvisor: Prof. Matteo Matteucci  \nTutor: Prof. Davide Martinenghi Year 2025-XXXVI Cycle  \ni  \nAbstract  \nIn the context of pervasive digitalisation, every process around us could be recorded and investigated for insights, predictions, better decision making and optimisation possibilities. Variability is always present in real-world processes and it is crucial to take it into consideration during the analysis and the development of solutions. Process attributes could explain part of the process variability, steering the process towards specific variants in presence of determined characteristics; it is therefore crucial to insert them into the process investigation. At the same time, a certain degree of stochasticity will always permeate a process being a source of variability.  \nProcess mining is a recently rising field that provides tools to extract knowledge about the process from data recorded by information systems. Process mining techniques are able to create process models, predict process behaviour as well as establishing the adherence of a model to specific data. Machine learning is another scientific field that has revolutionised many areas of our lives in recent times. It can automatically learn complex patterns linking an input to an output of a given system or detect similarities and relations inside data.  \nIn this thesis we investigate the use of machine learning techniques to deal with the process variability, taking into consideration process attributes and stochasticity inside the process mining analysis. Specifically, in the first part we study the uncertainty hidden in the forecast of neural networks in the next activity prediction task. Due to the hard explainability of neural networks, in the second part the thesis focuses on methods related to explicit process models. In particular, it proposes a novel approach to trace clustering and to decision discovery in a given model. The thesis also developed an extension toa state-of-the-art method to compose a stochastic process model that considers process attributes and activities previously executed during an instance execution. The developed approaches are then applied to an industrial case study to predict the most probable activities needed to produce a specific item in a highly flexible manufacturing process.  \nKeywords: Process Mining, Machine Learning, Probabilistic Attributes-Aware Models  \niii  \nAbstract in lingua italiana  \nNel contesto della digitalizzazione pervasiva in cui viviamo, ogni processo che ci circondapuò essere registrato e analizzato per ottenere approfondimenti, effettuare previsioni, migliorare il processo decisionale e individuare possibilità di ottimizzazione. La variabilitàè sempre presente nei processi del mondo reale ed è fondamentale tenerne conto durantel’analisi e lo sviluppo di soluzioni. Le caratteristiche di un processo possono spiegare partedella sua variabilità, indirizzandolo verso specifiche varianti in presenza di determinati attributi; è quindi essenziale includerli nell’analisi del processo stesso. Allo stesso tempo, sarà sempre presente un certo grado di stocasticità che costituisce una seconda fonte divariabilità .  \nIl Process Mining è un campo emergente che fornisce strumenti per indagare e conoscerei processi a partire dai dati registrati dai sistemi informativi durante la loro esecuzione. Le tecniche di Process Mining consentono di creare modelli di processo, prevederne il comportamento e valutare l’aderenza di un modello a specifici dati. Il Machine Learning è un altro ambito scientifico che recentemente ha rivoluzionato molte aree della nostra vita. Questa disciplina permette di apprendere automaticamente schemi complessi che collegano un input ad un output di un determinato sistema o di individuare somiglianzee relazioni all’interno dei dati.  \nIn questa tesi, si indaga l’uso di tecniche di Ma","cbCaiemmeIpUmaML","https://ap.wps.com/l/cbCaiemmeIpUmaML","pdf",14579400,1,186,"English","en",105,"# 1 Introduction\n## 1.1 The Pervasiveness of Digitalisation\n## 1.2 Extracting Value from Data: Machine Learning and Process Mining\n## 1.3 Motivations\n## 1.4 Contributions & Outline\n# 2 Background\n## 2.1 Process Mining\n## 2.2 Decision Mining","[{\"question\":\"How does the thesis handle variability in real-world processes during process mining analysis?\",\"answer\":\"It incorporates both process attributes, which steer variants under determined characteristics, and stochasticity, which remains present in processes as an additional variability source.\"},{\"question\":\"What is the focus of the first part of the thesis?\",\"answer\":\"The first part studies uncertainty hidden in neural networks when predicting the next activity in a process trace.\"},{\"question\":\"What new methods does the thesis propose in relation to explicit process models?\",\"answer\":\"It proposes an approach for trace clustering and decision discovery, and also develops an extension for composing stochastic process models that consider process attributes and previously executed activities.\"}]","Machine Learning for Probabilistic and Attribute-Aware Process Mining - Doctoral Dissertation | PDF",1785897931,469,{"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-for-probabilistic-and-attribute-aware-process-mining-doctoral-dissertation","",{"@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-for-probabilistic-and-attribute-aware-process-mining-doctoral-dissertation/125279/",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","2026-08-05",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},"How does the thesis handle variability in real-world processes during process mining analysis?","Question",{"text":75,"@type":76},"It incorporates both process attributes, which steer variants under determined characteristics, and stochasticity, which remains present in processes as an additional variability source.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the focus of the first part of the thesis?",{"text":80,"@type":76},"The first part studies uncertainty hidden in neural networks when predicting the next activity in a process trace.",{"name":82,"@type":73,"acceptedAnswer":83},"What new methods does the thesis propose in relation to explicit process models?",{"text":84,"@type":76},"It proposes an approach for trace clustering and decision discovery, and also develops an extension for composing stochastic process models that consider process attributes and previously executed activities.","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"]