[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121012-en":3,"doc-seo-121012-105":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},121012,5909877438554,"Maeve","https://ap-avatar.wpscdn.com/avatar/5600025385ad2bf12a7?_k=1778553567797529272",8,"Research & Report","Screen for Collusive Behavior - A Machine Learning Approach","The paper develops a machine-learning-based screen for identifying potentially collusive behavior and supports follow-up investigations. It argues that screening tools can complement leniency programs by raising the risk of detection and by surfacing markets or firms showing suspicious patterns. The approach is applied to the German retail gasoline market, where it detects anomalies in the price-setting process of filling stations. Detected anomalies are interpreted for their implications for market competitiveness, while emphasizing that the screen provides indications rather than direct evidence.","Hohenheim Discussion Papers in Business, Economics and Social Sciences  \nScreen for Collusive Behavior – A Machine Learning Approach  \nMelissa Bantle  \nUniversity of Hohenheim  \nInstitute of Economics  \n01-2024  \n[wiso.uni-hohenheim.de](wiso.uni-hohenheim.de)  \nDiscussion Paper 01-2024  \nScreen for Collusive Behavior – A Machine Learning  \nApproach  \nMelissa Bantle  \nDownload this Discussion Paper from our homepage: [https://wiso.uni-hohenheim.de/papers](https://wiso.uni-hohenheim.de/papers)  \nISSN 2364-2084  \nDie Hohenheim Discussion Papers in Business, Economics and Social Sciences dienen der schnellen Verbreitung von Forschungsarbeiten der Fakultät Wirtschafts-und Sozialwissenschaften. Die Beiträge liegen in alleiniger Verantwortung der Autoren und stellen nicht notwendigerweise die Meinung der Fakultät Wirtschafts-und Sozialwissenschaften dar.  \nHohenheim Discussion Papers in Business, Economics and Social Sciences are intended to make results of the Faculty of Business, Economics and Social Sciences research available to the public in order to encourage scientific discussion and suggestions for revisions. The authors are solely responsible for the contents which do not necessarily represent the opinion of the Faculty of Business,  \nEconomics and Social Sciences.  \nScreen for Collusive Behavior – A Machine Learning  \nApproach  \nMelissa Bantle ∗  \nFebruary 29, 2024  \nAbstract  \nThe paper uses a machine learning technique to build up a screen for collusive behavior. Such tools can be applied by competition authorities but also by companies to screen the behavior of their suppliers. The method is applied to the German retail gasoline market to detect anomalous behavior in the price setting of the filling stations. Therefore, the algorithm identifies anomalies in the data-generating process. The results show that various anomalies can be detected with this method. These anomalies in the price setting behavior are then discussed with respect to their implications for the competitiveness of the market.  \nKeywords: Machine Learning, Cartel Screens, Fuel Retail Market  \nJEL-Codes: C53, K21, L44  \n∗ University of Hohenheim, Department of Economics, Chair of Microeconomics (520C), 70593 Stuttgart, Germany, [melissaulrika.bantle@uni-hohenheim.de](melissaulrika.bantle@uni-hohenheim.de)  \n1 Introduction  \nDespite cartel enforcement and actions like the leniency program, companies still make collusive agreements. The question therefore arises as to whether punishments are not severe enough or whether the risk of detection is too low. In recent years, moreover, leniency applications have declined substantially. It might thus be time for pro-active methods to detect cartels. These include screening methods where market data is examined for evidence of collusion. These cartel screens can be used complementary to leniency programs as they can give an incentive to apply for leniency due to the higher risk of detection through such a screen.  \nScreening is meant to be the basis for an investigation as it does not deliver direct evidence for a cartel but identifies potential collusion. These screens could be used by competition authorities as a first screen to identify markets or firms that should be investigated further. Or to monitor suspicious firms or industries that are already under investigation to identify changes in their behavior. Competition authorities can check for suspicious behavior with a screen in order to start an investigation or prioritise cases.  \nBesides competition authorities, also companies should be aware of screening programs. Such screens could be used to detect anomalous behavior in the price setting of their suppliers. Firms are predestined for screening methods as they have sufficient data from their suppliers and the market knowledge to implement a screen efficiently. Screening tools can, for example, be included in antitrust compliance programs. If an anomaly is detected, the firm could renegotiate prices with ","cbCaieeCHmZn9fa4","https://ap.wps.com/l/cbCaieeCHmZn9fa4","pdf",743636,1,42,"English","en",105,"# Abstract\n# Introduction\n## Motivation for proactive cartel detection\n## Screening as a basis for investigation\n## Applications for authorities and companies\n# Overview of Screening Methods\n## Structural screening\n## Behavioral screening","[{\"question\":\"What is the main goal of the paper?\",\"answer\":\"To build a machine-learning-based screen that identifies potentially collusive behavior so it can support investigations rather than provide direct proof.\"},{\"question\":\"How is the method intended to be used by competition authorities and companies?\",\"answer\":\"Authorities can use it as a first screen to prioritize cases or monitor suspicious firms, while companies can apply it to detect anomalies in their suppliers’ price setting and incorporate it into compliance programs.\"},{\"question\":\"What market data application is used to evaluate the approach?\",\"answer\":\"The method is applied to German retail gasoline prices to detect anomalous behavior in the filling stations’ price-setting process.\"}]","Screen for Collusive Behavior - A Machine Learning Approach | PDF",1785733301,106,{"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},"screen-for-collusive-behavior-a-machine-learning-approach","",{"@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/screen-for-collusive-behavior-a-machine-learning-approach/121012/",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","2026-08-03",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 is the main goal of the paper?","Question",{"text":75,"@type":76},"To build a machine-learning-based screen that identifies potentially collusive behavior so it can support investigations rather than provide direct proof.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the method intended to be used by competition authorities and companies?",{"text":80,"@type":76},"Authorities can use it as a first screen to prioritize cases or monitor suspicious firms, while companies can apply it to detect anomalies in their suppliers’ price setting and incorporate it into compliance programs.",{"name":82,"@type":73,"acceptedAnswer":83},"What market data application is used to evaluate the approach?",{"text":84,"@type":76},"The method is applied to German retail gasoline prices to detect anomalous behavior in the filling stations’ price-setting process.","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"]