[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128341-en":3,"doc-seo-128341-105":31,"detail-sidebar-cat-0-en-105":93},{"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},128341,962085564549,"Genevieve","https://ap-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Public procurement cartels: A large-sample testing of screens using machine learning","Measuring public procurement cartels is essential due to their high budgetary costs and harmful welfare impacts. Prior research offers cartel screens tailored to selected cartel types and high-quality datasets, yet it does not yield generalizable knowledge for policy and law enforcement using typical real-world data. This study simultaneously measures multiple cartel behaviours across 73 cartels from seven European countries, spanning 2004–2021, and applies machine learning to predict confirmed cartels.","Journal Pre-proof  \nPublic procurement cartels: A large-sample testing of screens using machine learning  \nMihly Fazekas , Bence Tth , Johannes Wachs , Aly Abdou  \nPII: S0167-7187(25)00094-3  \nDOI: [https://doi.org/10.1016/j.ijindorg.2025.103228](https://doi.org/10.1016/j.ijindorg.2025.103228)  \nReference: INDOR 103228  \nTo appear in: International Journal of Industrial Organization  \nReceived date: 17 May 2024  \nRevised date: 17 November 2025  \nAccepted date: 21 November 2025  \nPlease cite this article as: Mihly Fazekas , Bence Tth , Johannes Wachs , Aly Abdou , Public procurement cartels: A large-sample testing of screens using machine learning, International Journal of  \nIndustrial Organization (2025), doi: [https://doi.org/10.1016/j.ijindorg.2025.103228](https://doi.org/10.1016/j.ijindorg.2025.103228)  \nThis is a PDF of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability. This version will undergo additional copyediting, typesetting and review before it is published in its final form. As such, this version is no longer the Accepted Manuscript, but it is not yet the definitive Version of Record; we are providing this early version to give early visibility of the article. Please note that Elsevier's sharing policy for the Published Journal Article applies to this version, see: [https://www.elsevier.com/about/](https://www.elsevier.com/about/)[ ](https://www.elsevier.com/about/)[policies-and-standards/sharing\\#4-published-journal-article](policies-and-standards/sharing#4-published-journal-article. Please also note that)[. Please also note that](policies-and-standards/sharing#4-published-journal-article. Please also note that) , [during the produc](during the produc)tion process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.  \n© 2025 Published by Elsevier B.V.  \nPublic procurement cartels: A large-sample testing of screens using machine learning  \nAuthor Names  \nMihály Fazekas1,6 Bence Tóth2,6 , Johannes Wachs3,4,5, Aly Abdou6  \nAffiliations  \n¹Central European University, Vienna, Austria ² University College London, London, United Kingdom 3Corvinus University of Budapest  \n4 HUN-REN Centre for Economics and Regional Studies , Budapest, Hungary  \n5 Complexity Science Hub, Vienna, Austria 6Government Transparency Institute, Budapest, Hungary  \nCorresponding Author  \nName: Mihály Fazekas  \nAffiliation: Central European University, Vienna, Austria & Government Transparency Institute, Budapest, Hungary  \nPhone Number: 0043 660 7506365  \n[Email: mfazekas@govtransparency.eu](Email: mfazekas@govtransparency.eu)  \nAddress: Quellenstrasse 51, Vienna 1100, Austria  \nAbstract  \nDue to the high budgetary costs of public procurement cartels, it is crucial to measure and understand them. The literature developed screens that work well for selected cartel types and with high quality data, but it didn’t produce generalisable knowledge supporting policy and law enforcement on typically available datasets. We simultaneously measure multiple cartel behaviours on publicly available data of 73 cartels from 7 European countries covering 2004-2021. We apply machine learning methods, using diverse cartel screens characterising pricing and bidding behaviours in a predictive model. Combining many indicators in a random forest algorithm achieves 70-84% prediction accuracy, distinguishing behavioural traces of confirmed cartels from non-cartels across different cartel types and countries (accuracy is 97% when trained and tested on a single cartel case, typical of the literature) . Most screens contribute to prediction in line with theory. These results could improve cartel detection and investigations and support pro-competition policies.  \nJEL codes: C21; C45; C52; D22; D40; K42; L41  \nKeywords: Cartel screening, bid-rigging, public procurement, Europe, machine learning  \n1 Introduction  \nPublic","cbCainrNbX68rY7s","https://ap.wps.com/l/cbCainrNbX68rY7s","pdf",1821714,5,1,35,"English","en",105,"# Introduction\n## Motivation and problem setting\n## Data availability and limitations in prior screens\n## Study approach and contribution","[{\"question\":\"Why is it crucial to measure public procurement cartels?\",\"answer\":\"Public procurement cartel activity generates high budgetary costs and welfare losses. Due to frequent government purchasing, these markets allow collusion to arise and operate for longer periods.\"},{\"question\":\"What limitation does the paper identify in existing cartel screening research?\",\"answer\":\"Most screens rely on data variables that are not commonly available in e-procurement systems, and many studies focus on a single cartel behaviour or few cartel cases, reducing generalizability.\"},{\"question\":\"How does the study evaluate cartel screens using machine learning?\",\"answer\":\"It measures multiple cartel behaviours using public data on 73 cartels from seven European countries (2004–2021). A predictive model built with diverse screens characterizing pricing and bidding behaviours is tested, with random forest combining many indicators to achieve higher accuracy.\"}]","Public procurement cartels: A large-sample testing of screens using machine learning | PDF",1785946944,88,{"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":88,"head_meta":90,"extra_data":92,"updated_unix":29},"public-procurement-cartels-a-large-sample-testing-of-screens-using-machine-learning","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/public-procurement-cartels-a-large-sample-testing-of-screens-using-machine-learning/128341/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-30","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"Why is it crucial to measure public procurement cartels?","Question",{"text":77,"@type":78},"Public procurement cartel activity generates high budgetary costs and welfare losses. Due to frequent government purchasing, these markets allow collusion to arise and operate for longer periods.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"What limitation does the paper identify in existing cartel screening research?",{"text":82,"@type":78},"Most screens rely on data variables that are not commonly available in e-procurement systems, and many studies focus on a single cartel behaviour or few cartel cases, reducing generalizability.",{"name":84,"@type":75,"acceptedAnswer":85},"How does the study evaluate cartel screens using machine learning?",{"text":86,"@type":78},"It measures multiple cartel behaviours using public data on 73 cartels from seven European countries (2004–2021). A predictive model built with diverse screens characterizing pricing and bidding behaviours is tested, with random forest combining many indicators to achieve higher accuracy.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},"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":20,"slug":139},19,"General","general"]