[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125038-en":3,"doc-seo-125038-105":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},125038,8796095461610,"Oliver","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Automated Detection of Front Companies - Exploring Machine Learning Potentials and Limitations","This project examines the potential and limitations of modern machine learning for automatically detecting front companies. Predictive classification models are used to analyze a firm’s transaction history to identify the most effective approach for the classification task. The work is conducted in collaboration with B4 Investigate, leveraging a dataset provided by the company and analyzed using Python-based tools. Findings highlight the importance of creating appropriate variable representations and suggest tree-based algorithms are well suited for learning indicative patterns, supporting further research.","EuropeW/O0Jf(ClwT23) 􀂔  \nHandelsh0ysllolen Bl GRA 19703 Master Thesis  \nThesis Master of Science 100% - W  \nPredefinert informasjon  \nStartdato:  \nSluttdato:  \nEllsamensform:  \nFlowkode:  \nIntern sensor:  \nDelta􀂕er  \nNavn:  \n09-01-2023 09:00 CET  \n03-07-2023 12:00 CESTT 202310ll11184IIINOOIIWIIT (Anonymisert)  \nLiam Alexander Høgtun  \nTermin:  \nVurderingsform:  \n202310  \nNorsk 6-trinns sllala (A-F)  \nlnformasjon fra delta􀂕er  \nTittel •: Automated Detection of Front Companies: Exploring Machine Leaming Potentials and Limitations  \nNaun pli ueileder •: Emil Aas Stoltenberg  \nlnneholder besuarelsen Nei konfidensielt  \nmateriale7:  \nKan besuarelsenoffentliggj•res?:  \nJa  \nGruppe  \nljruppenaun: (Anonymisert)  \nljruppenummer: 349  \nAndre medlemmer i Deltakeren har innleuert i en enlleltmannsgruppe gruppen:  \nAutomated Detection of Front Companies: Exploring Machine Learning Potentials and Limitations  \nHand-in date:  \n03.07.2023  \nCampus:  \nBI Oslo  \nExamination code and name:  \nGRA1974-Master Thesis  \nProgramme:  \nMSc in Business Analytics  \nAcknowledgements  \nFirst, we would like to express our gratitude to our supervisor, Assistant Professor Emil Aas Stoltenberg, of the Department of Data Science at BI Norwegian Business School. His superb guidance and feedback have proven invaluable throughout our project's development.  \nEqually, we are grateful to Nigel Krishna Iyer, CEO and Founder of B4 Investigate AB, for his enlightening insights on front companies, fraud, and global beneficial ownership transparency. His willingness to collaborate and allow us to use some of B4 Investigate's data has significantly contributed to our work. We would also like to acknowledge Christian Kalbakk-Bohler of B4 Investigate for his exemplary work in creating datasets grounded in big data and real cases. Finally, our sincere thanks go to Dalia Breskuvien for sharing her expert knowledge in dealing with machine learning problems with high cardinality nominal variables in imbalanced datasets.  \nAbstract  \nThis project is aimed at understanding the potential and limitations of modern machine learning algorithms in automatically detecting front companies. We employed predictive classification models to analyse a company's transaction history, with the goal of developing the most effective approach to solve the classification task.  \nThe research was conducted in collaboration with B4 Investigate, a young company specializing in developing software for fraud detection and financial damage mitigation. The dataset used for analysis and model development was provided by B4 Investigate and was analysed using various Python libraries and intrinsic tools.  \nFront companies have a pervasive presence worldwide. While there might be valid justifications for utilizing a front, in most cases, they are often employed to conceal engagement in illegal or dubious activities. One significant hurdle is the arduous task of identifying such entities, as inadvertent association with a front company can lead to substantial financial or reputational harm.  \nThrough our analysis, several important insights emerged. We discovered the significance of creating suitable representations of relevant variables, such as the country of registration for each company in the dataset as well as conveying the context of a company's regular business activities when employing the predictive solution. The implementation of these measures significantly improved the performance of the prediction task. Additionally, tree-based algorithms appear tobe the most suitable for learning the correct indicative patterns in this specific prediction task. The findings suggest that modern machine learning algorithms indeed have the potential to serve as effective tools for automated detection of front companies, underscoring the value of further exploration in this field through future research. This approach holds promise and can provide tangible value to companies and non-profit organizations by accurately","cbCaiplPAd711rMS","https://ap.wps.com/l/cbCaiplPAd711rMS","pdf",1297416,1,61,"English","en",105,"# CHAPTER 1, INTRODUCTION\n## 1.1: THE AIM OF THIS PROJECT\n## 1.2: WHAT DO WE MEAN BY FRONT COMPANIES\n## 1.3: ESTABLISHING THE PREMISES FOR THE DATA USED IN THIS PROJECT\n# CHAPTER 2, LITERATURE REVIEW\n## 2.1: FRONT COMPANY AND MONEY LAUNDERING LITERATURE\n## 2.2: ANALYTICS LITERATURE\n# CHAPTER 3, DATA STRUCTURE\n# CHAPTER 4, TESTING AND DEVELOPMENT\n## 4.1: PERFORMANCE METRIC IN FOCUS (F1-SCORE)\n## 4.2: CHRONOLOGICAL DEVELOPMENT STRUCTURE (STEP 1-3)\n## 4.3: DEVELOPMENT DESCRIPTIONS AND RESULTS","[{\"question\":\"What is the main goal of the project?\",\"answer\":\"To understand how well modern machine learning can automatically detect front companies and to evaluate its potential and limitations in this classification task.\"},{\"question\":\"How is the classification task approached in the study?\",\"answer\":\"The project uses predictive classification models that analyze a company’s transaction history to learn patterns indicative of front companies.\"},{\"question\":\"What insights improve model performance according to the findings?\",\"answer\":\"Creating suitable representations for relevant variables—such as registration country and contextual information about regular business activities—significantly improves prediction performance.\"}]","Automated Detection of Front Companies - Exploring Machine Learning Potentials and Limitations | PDF",1785896298,154,{"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},"automated-detection-of-front-companies-exploring-machine-learning-potentials-and-limitations","",{"@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/automated-detection-of-front-companies-exploring-machine-learning-potentials-and-limitations/125038/",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},"What is the main goal of the project?","Question",{"text":75,"@type":76},"To understand how well modern machine learning can automatically detect front companies and to evaluate its potential and limitations in this classification task.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the classification task approached in the study?",{"text":80,"@type":76},"The project uses predictive classification models that analyze a company’s transaction history to learn patterns indicative of front companies.",{"name":82,"@type":73,"acceptedAnswer":83},"What insights improve model performance according to the findings?",{"text":84,"@type":76},"Creating suitable representations for relevant variables—such as registration country and contextual information about regular business activities—significantly improves prediction performance.","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"]