[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123377-en":3,"doc-seo-123377-105":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},123377,962075114101,"Seraphina","https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165",8,"Research & Report","Process Mining Influence on Requirement Elicitation for Machine Learning","Machine Learning (ML) increasingly supports decision-making, yet high dimensionality and feature complexity make selecting effective features difficult and threaten model accuracy. Meeting this challenge requires better quantitative and qualitative requirements for the features that drive higher-performing ML models. Process Mining (PM) leverages event logs to discover processes and derive knowledge in dynamic settings, especially in healthcare. This study presents an integrated methodology that elicits feature requirements for ML, validated via colorectal cancer (CRC) treatment planning.","2024 International Conference on Frontiers of Information Technology (FIT) ©2024 IEEE DOI: 10.1109/FIT63703.2024.10838404| 979-8-3315-1050-3/24/$31.00 |   \nProcess Mining Influence on Requirement Elicitation for Machine Learning  \nLin Chin-Ying  \nFaculty of EEMCS University of Twente The Netherlands [c.lin-1@student.utwente.nl](c.lin-1@student.utwente.nl)  \nJeewanie Jayasinghe Arachchige  \nDepartment of Computer Science Vrije University The Netherlands [j.jayasinghearachchige@vu.nl](j.jayasinghearachchige@vu.nl)  \nFaiza A.Bukhsh  \nFaculty of EEMCS University of Twente The Netherlands [f.a.bukhsh@utwente.nl](f.a.bukhsh@utwente.nl)  \nAbstract—Machine Learning (ML) is becoming a prominent approach in decision-making across many domains. However, the complexity of data and the high number of features are severe challenges when selecting the most effective features in ML models. This situation demands better quantity and quality requirements of the features that are the essential ingredients to ML models for higher accuracy. On the other hand, Process Mining is a young discipline which is successfully shown it’s growth in process discovery using event logs. This study explores the influence of Process Mining by revealing quantitative and qualitative requirements for features to enhance the ML approaches. The proposed methodology was validated with a case of Colorectal Cancer (CRC) treatment planning.  \nIndex Terms—machine learning, requirements, features elicitation, process mining, colorectal cancer  \nI. INTRODUCTION  \nMachine Learning (ML) techniques are becoming prominent in many domains including healthcare for better decisionmaking, in this complex data world. According to [1], the high processing power, availability of large amounts of data, and easy-to-use software frameworks made ML popular. However, the increasing trend of complexity of data and high dimensionality exhibits a severe challenge in the feature selection process in ML. Authors of the [2], argue that even though feature engineering is an inherent part of ML models, significant effort should be paid into feature engineering to ensure the explainability of ML models. Therefore, we believe that better requirements elicitation for features plays a vital role in ML.  \nWhen exploring featuring elicitation methods in the literature [2] one way is domain-specific feature elicitation. The paper [3] stated that prior knowledge is required in feature elicitation and it is often tacit and only available from domain experts. They proposed user models for feature elicitation.  \nOn the other hand Process Mining(PM) is a considerably young discipline which used to identify frequent processes, critical paths, and bottlenecks using event logs that are formed with data. PM has effectively demonstrated its ability to obtain knowledge in the dynamic nature of healthcare processes [4],[5] and [6] .  \n979-8-3315-1050-3/24/$31.00 ©2024 IEEE  \nTherefore, this paper introduces a methodology that integrates Process Mining and Machine Learning. The former elicits the feature requirements of the latter. More specifically, this paper focuses on the research question of how PM can influence in requirement elicitation in terms of quantitative and qualitative aspects of features for ML models. We employed the proposed methodology in a colorectal cancer (CRC) treatment planning case study.  \nThe process of treatment planning in CRC, characterized by its complexity and the multitude of options available, demands careful consideration and often leads to significant stress and uncertainty for those affected. Navigating through many options and uncertainties, choosing a course of action becomes a formidable task. This challenge is particularly pronounced in CRC treatment, where choices range from invasive surgeries to targeted therapies [7] . Physicians often require many years of extensive experience to make informed judgments. Thus, this underscores a significant gap in current treatment planning","cbCaimd7ZmxpiIEO","https://ap.wps.com/l/cbCaimd7ZmxpiIEO","pdf",1368242,1,6,"English","en",105,"# Introduction\n## Feature elicitation challenges in ML\n## Domain-specific feature elicitation and user models\n## Process mining for healthcare event logs\n# Methodology and research focus\n## Integrating Process Mining with Machine Learning\n## Case study: colorectal cancer treatment planning\n# CRC treatment planning motivation\n## Uncertainty, complexity, and need for data-driven decisions\n## Process mining–based feature requirement elicitation\n# Design science methodology (Engineering Cycle)\n## Problem investigation to implementation evaluation","[{\"question\":\"What problem does the paper address in machine learning feature development?\",\"answer\":\"The paper addresses how data complexity and high dimensionality create difficulties in selecting effective features, impacting ML accuracy and explainability.\"},{\"question\":\"How does process mining contribute to feature requirements elicitation?\",\"answer\":\"Process mining analyzes event logs to discover processes and extract quantitative and qualitative feature requirements, providing guidance for downstream ML model development.\"},{\"question\":\"How was the proposed methodology validated?\",\"answer\":\"The methodology was validated using a colorectal cancer (CRC) treatment planning case, where event log–driven feature requirement elicitation supports more tailored decision-making.\"}]","Process Mining Influence on Requirement Elicitation for Machine Learning | PDF",1785816189,15,{"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},"process-mining-influence-on-requirement-elicitation-for-machine-learning","",{"@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/process-mining-influence-on-requirement-elicitation-for-machine-learning/123377/",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},"What problem does the paper address in machine learning feature development?","Question",{"text":75,"@type":76},"The paper addresses how data complexity and high dimensionality create difficulties in selecting effective features, impacting ML accuracy and explainability.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does process mining contribute to feature requirements elicitation?",{"text":80,"@type":76},"Process mining analyzes event logs to discover processes and extract quantitative and qualitative feature requirements, providing guidance for downstream ML model development.",{"name":82,"@type":73,"acceptedAnswer":83},"How was the proposed methodology validated?",{"text":84,"@type":76},"The methodology was validated using a colorectal cancer (CRC) treatment planning case, where event log–driven feature requirement elicitation supports more tailored decision-making.","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},[93,97,101,105,110,114,119,122,127,130,134],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]