[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118308-en":3,"doc-seo-118308-105":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},118308,7971461740909,"Levi","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","A Machine Learning Based Approach for the Identification of Fake Bills - Article 1","Fake or counterfeiting currency presents a major economic risk, especially given the global prominence of the US dollar. This work builds an automated identification system using machine learning algorithms trained on a dataset of bill measurements (1500 samples: 1000 real and 500 fake). Models are trained on a training set and assessed on a test set using 5-fold cross-validation to yield a more reliable effectiveness estimate. Initial results show up to 99% accuracy for the best model and highlight key measurements for determining authenticity.","Rose-Hulman Undergraduate Mathematics Journal  \n\n| Volume 25 Issue 2 | Article 1 |\n| --- | --- |\n| A Machine Learning Based Approach for the Identification Bills\u003Cbr>Tianyang Lu\u003Cbr>Shandong University, [lutianyang2002@gmail.com](lutianyang2002@gmail.com)\u003Cbr>Hongyang Pang\u003Cbr>Nankai University, 1774301[1672@163.com](1672@163.com)\u003Cbr>Follow this and additional works at: [https://scholar.rose-hulman.edu/rhumj](https://scholar.rose-hulman.edu/rhumj)\u003Cbr> Part of the Applied Statistics Commons, and the Statistical Models Commons | of Fake |\n\nRecommended Citation  \nLu, Tianyang and Pang, Hongyang (2024) \"A Machine Learning Based Approach for the Identification of Fake Bills,\" Rose-Hulman Undergraduate Mathematics Journal: Vol. 25: Iss. 2, Article 1.  \nAvailable at: [https://scholar.rose-hulman.edu/rhumj/vol25/iss2/1](https://scholar.rose-hulman.edu/rhumj/vol25/iss2/1)  \nA Machine Learning Based Approach for the Identification of Fake Bills  \nCover Page Footnote  \nThis research was conducted during the six-week summer Global Education, Academics, and Research Skills (GEARS) program in 2023 at North Carolina State University. The authors are grateful for the supervision, support, and mentorship in this work from Professor Hien Tran in the department of mathematics at North Carolina State University.  \nThis article is available in Rose-Hulman Undergraduate Mathematics Journal: [https://scholar.rose-hulman.edu/rhumj/](https://scholar.rose-hulman.edu/rhumj/)[ ](https://scholar.rose-hulman.edu/rhumj/)vol25/iss2/1  \nRose-Hulman Undergraduate Mathematics Journal  \nVOLUME 25, ISSUE 2, 2024  \nA Machine Learning Based Approach for the Identification of Fake Bills  \nBy Tianyang Lu, Hongyang Pang, and Hien Tran  \nAbstract. Fake or counterfeiting currency, which has been around as long as money has existed, is a major economic problem. Since the US dollar is the most popular form of currency globally, it is the most popular currency to counterfeit. The United States Department of Treasury estimates that between $70 million and $200 million in fake bills are in circulation. The Federal Reserve Bank uses special banknote processing systems to count each bill deposited by the bank and examine them for the possibility of counterfeits. These machines have sensors designed to detect general quality of the bills, including paper type, quality of ink, and color-shifting ink. In this paper, several machine learning algorithms were used to develop an automated identification system for the detection of fake bills. A fake bills dataset, which contains 1500 bill measurements, was used to train several machine learning models. The dataset is split into training and testing sets. The machine learning models are trained with the training set and the accuracy of the models was evaluated with the test set using a 5-fold cross-validation to provide a more reliable measure of the model’s effectiveness. Our initial results are very promising with an accuracy rate of 99% for the best machine learning model. Furthermore, the machine learning model also identifies which bill measurements are critical for the identification of the bill authenticity. These results can provide useful information to the consumers as well as experts to spot fake bills based on bills measurement.  \n1 Introduction  \nAmong the many responsibilities of the Federal Reserve Bank is to protect the nation’s currency from counterfeits. The United States Department of Treasury estimated that $70 million to $200 million of US currency in circulation are counterfeit [1, 2] . In the U.S., the most common counterfeit bill is the 20 dollar note while the $100 bill is the most fake bill overseas. About 90% of counterfeit money in the U.S. is produced using lithographic technology, which allows for mass production. The U.S. Bureau of Engraving and Printing regularly updates the US currency to deter counterfeiting. A newly redesigned $20 was issued in 2003 followed by $50 bill in 2004 and $100 bill in 2005 . Th","cbCaikcUcv71W8dA","https://ap.wps.com/l/cbCaikcUcv71W8dA","pdf",589348,1,15,"English","en",105,"# Abstract\n# 1 Introduction\n# 2 A Machine Learning Based Approach for the Identification of Fake Bills","[{\"question\":\"What problem does the paper address?\",\"answer\":\"The paper addresses the challenge of detecting counterfeit currency in circulation, focusing on identifying fake US bills automatically.\"},{\"question\":\"What data and features are used to train the models?\",\"answer\":\"The study uses a fake bills dataset containing real and fake bill measurements, including geometric measurements, margins, and total length as predictive features.\"},{\"question\":\"How are the machine learning models evaluated?\",\"answer\":\"Models are trained and evaluated using train/test splitting with 5-fold cross-validation, providing a more reliable measure of model performance.\"}]","A Machine Learning Based Approach for the Identification of Fake Bills - Article 1 | PDF",1785682960,38,{"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},"a-machine-learning-based-approach-for-the-identification-of-fake-bills-article-1","",{"@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/a-machine-learning-based-approach-for-the-identification-of-fake-bills-article-1/118308/",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","2026-08-02",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?","Question",{"text":75,"@type":76},"The paper addresses the challenge of detecting counterfeit currency in circulation, focusing on identifying fake US bills automatically.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What data and features are used to train the models?",{"text":80,"@type":76},"The study uses a fake bills dataset containing real and fake bill measurements, including geometric measurements, margins, and total length as predictive features.",{"name":82,"@type":73,"acceptedAnswer":83},"How are the machine learning models evaluated?",{"text":84,"@type":76},"Models are trained and evaluated using train/test splitting with 5-fold cross-validation, providing a more reliable measure of model 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"]