[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127621-en":3,"doc-seo-127621-105":30,"detail-sidebar-cat-0-en-105":96},{"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},127621,549768064778,"Finn","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Predicting Multiple Domain Queue Waiting Time via Machine Learning","Implementation of the CRISP-DM methodology supports human queue waiting time prediction using machine learning in a multiple-domain ticket management setting. Work with a Portuguese software development company leverages a database containing millions of ticket records from multiple stores and domains across defined time periods for modeling and deployment simulation. Data preparation includes cleaning, feature engineering, and scaling, followed by comparisons of five regression algorithms under multiple input attribute scenarios and validation schemes. AutoML with newly engineered features yields small prediction error (about 5–7 minutes) with reasonable computation, and an applied XAI method extracts domain-relevant explanations.","Predicting Multiple Domain Queue Waiting Time via Machine Learning  \nCarolina Loureiro 1 , Pedro Jos´e Pereira 1 ,2 , Paulo Cortez2 , Pedro Guimar˜aes 1 ,2 , Carlos Moreira3 , and Andr´e Pinho3  \n1 EPMQ-IT Engineering Maturity and Quality Lab, CCG ZGDV Institute,  \nGuimar˜aes, Portugal  \n{carolina.loureiro,[pedro.pereira](pedro.pereira}@ccg.pt)[}](pedro.pereira}@ccg.pt)[@ccg.pt](pedro.pereira}@ccg.pt)  \n2 ALGORITMI Centre/LASI, Dep. Information Systems, University of Minho,  \nGuimar˜aes, Portugal  \n[pcortez@dsi.uminho.pt](pcortez@dsi.uminho.pt)  \n3 Qevo – Queue Evolution Lda. , Lisboa, Portugal {carlos.aj.moreira, [andremsp95](andremsp95}@gmail.com)[}](andremsp95}@gmail.com)[@gmail.com](andremsp95}@gmail.com)  \nAbstract. This paper describes an implementation of the Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology for a demonstrative case of human queue waiting time prediction. We collaborated with a multiple domain (e.g., bank, pharmacies) ticket management service software development company, aiming to study a Machine Learning (ML) approach to estimate queue waiting time. A large multiple domain database was analyzed, which included millions of records related with two time periods (one year, for the modeling experiments; and two year, for a deployment simulation) . The data was first preprocessed (including data cleaning and feature engineering tasks) and then modeled by exploring five state-of-the-art ML regression algorithms and four input attribute selections (including newly engineered features) . Furthermore, the ML approaches were compared with the estimation method currently adopted by the analyzed company. The computational experiments assumed two main validation procedures, a standard cross-validation anda Rolling Window scheme. Overall, competitive and quality results were obtained by an Automated ML (AutoML) algorithm fed with newly engineered features. Indeed, the proposed AutoML model produces a small error (from 5 to 7 minutes), while requiring a reasonable computational effort. Finally, an eXplainable Artificial Intelligence (XAI) approach was applied to a trained AutoML model, demonstrating the extraction of useful explanatory knowledge for this domain.  \nKeywords: CRISP-DM · Automated Machine Learning · Regression.  \n1 Introduction  \nNowadays, human queues are still required in several service sectors (e.g. , health, banks) . Waiting in these queues is often stressful and exhausting, leading to unsatisfied and frustrated citizens. Therefore, providing a beforehand accurate  \n2 C. Loureiro et al.  \nestimation of citizens waiting time in queues would reduce such frustration, since it allows them to optimize their schedule, avoiding spending an excessive time waiting. Furthermore, this estimation enhances a better resource management by the responsible entities, allowing to avoid excessively long queues. However, an imprecise estimation could produce the opposite effect. If the queue waiting time is overestimated, citizens could loose their turn in the queue, while an underestimation would still force them to wait in the physical queue.  \nThis paper addresses a multiple domain queue waiting time estimation task by adopting a Machine Learning (ML) approach. This research work was developed in collaboration with a Portuguese software development company that operates in the ticket management sector and has several customer companies from multiple domains (e.g., banking) . Over the past years, the company collected and stored a large amount of data that holds valuable knowledge related with human queues. Hence, there is a potential in using Data Mining (DM) and ML [21] to extract valuable predictive knowledge that improves the queue waiting time estimation task. Currently, the analyzed company addresses this estimation by using a rather rigid formula that was based on their business expertise. In this work, adopted the popular Cross-Industry Standard Process for Data Mining (CRISP-DM) metho","cbCaiurxwJZ8GB6W","https://ap.wps.com/l/cbCaiurxwJZ8GB6W","pdf",661746,1,18,"English","en",105,"# Abstract\n# Introduction\n## Problem motivation and impact\n## Proposed approach and CRISP-DM usage","[{\"question\":\"What is the main goal of the study on queue waiting times?\",\"answer\":\"Accurately predict human queue waiting time for tickets using a machine learning supervised regression approach, reducing citizen frustration and improving resource management.\"},{\"question\":\"How was the data prepared before modeling?\",\"answer\":\"The approach analyzes an initial one-year dataset and applies data cleaning such as outlier removal, feature engineering including newly engineered features, and data scaling.\"},{\"question\":\"Which machine learning methods were compared in the experiments?\",\"answer\":\"Five regression algorithms were tested and compared: Decision Trees, Random Forest, Gradient Boosted Trees, deep Artificial Neural Networks, and an Automated Machine Learning method.\"},{\"question\":\"How does the paper make the ML results interpretable?\",\"answer\":\"After training an AutoML model, an eXplainable Artificial Intelligence (XAI) approach is applied to extract useful explanatory knowledge for the queue waiting time domain.\"}]","Predicting Multiple Domain Queue Waiting Time via Machine Learning | PDF",1785940318,45,{"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":91,"head_meta":93,"extra_data":95,"updated_unix":28},"predicting-multiple-domain-queue-waiting-time-via-machine-learning","",{"@graph":36,"@context":90},[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/predicting-multiple-domain-queue-waiting-time-via-machine-learning/127621/",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","2026-08-22","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82,86],{"name":73,"@type":74,"acceptedAnswer":75},"What is the main goal of the study on queue waiting times?","Question",{"text":76,"@type":77},"Accurately predict human queue waiting time for tickets using a machine learning supervised regression approach, reducing citizen frustration and improving resource management.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How was the data prepared before modeling?",{"text":81,"@type":77},"The approach analyzes an initial one-year dataset and applies data cleaning such as outlier removal, feature engineering including newly engineered features, and data scaling.",{"name":83,"@type":74,"acceptedAnswer":84},"Which machine learning methods were compared in the experiments?",{"text":85,"@type":77},"Five regression algorithms were tested and compared: Decision Trees, Random Forest, Gradient Boosted Trees, deep Artificial Neural Networks, and an Automated Machine Learning method.",{"name":87,"@type":74,"acceptedAnswer":88},"How does the paper make the ML results interpretable?",{"text":89,"@type":77},"After training an AutoML model, an eXplainable Artificial Intelligence (XAI) approach is applied to extract useful explanatory knowledge for the queue waiting time domain.","https://schema.org",{"og:url":52,"og:type":92,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":94,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":97},[98,102,106,110,115,120,125,128,133,136,140],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},"Exam",70,"exam",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},5,"Comic",60,"comic",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},6,"Technology",50,"technology",{"id":121,"doc_module":4,"doc_module_name":46,"category_name":122,"show_sort_weight":123,"slug":124},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":126,"slug":127},30,"research-report",{"id":129,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":131,"slug":132},9,"Religion & Spirituality",20,"religion-spirituality",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":131,"slug":135},"World Cup","world-cup",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":137,"slug":139},10,"Lifestyle","lifestyle",{"id":141,"doc_module":4,"doc_module_name":46,"category_name":142,"show_sort_weight":111,"slug":143},19,"General","general"]