[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118969-en":3,"doc-seo-118969-105":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},118969,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Fraud Guard - A Comprehensive Comparative Analysis of Machine Learning Approaches to Enhance Credit Card Fraud Detection - Optimal Resampling and Classifier Results","The COVID-19 pandemic accelerated the shift toward online purchasing, increasing exposure to credit card fraud and driving demand for robust detection methods. This study evaluates machine learning models for distinguishing legitimate and fraudulent transactions by leveraging data-driven algorithms. Four resampling techniques (CNN, AllKNN, SMOTE, and SVMSM) and three classifiers (XGBoost, CatBoost, and RF) are applied to unbalanced credit card fraud datasets. Results show AllKNN undersampling combined with CatBoost achieves the strongest performance, with accuracy 99.9%, precision 95.9%, recall 80%, and f1-score 87.4%.","Fraud Guard: A Comprehensive Comparative Analysis of Machine Learning Approaches to Enhance Credit Card Fraud  \nDetection  \nOmar Gheni Abdulateef  \nCollege Of Literature, University Of Samarra, Iraq  \nE-mail of the corresponding author: [omar.ghani@uosamarra.edu.iq](omar.ghani@uosamarra.edu.iq)  \nAbstract  \nThe COVID-19 pandemic has constrained people's mobility, prompting a surge in reliance on online services due to challenges in offline purchasing. Machine learning (ML) methods have played a crucial role in advancing classification and prediction techniques across various domains. In the realm of Credit Card Fraud Detection, the significance of ML is particularly pronounced. These methods harness the power of data-driven algorithms to distinguish between legitimate and fraudulent transactions, contributing significantly to the enhancement of security measures in financial transactions. The dynamic and adaptive nature of ML allows for the continuous evolution of fraud detection systems, ensuring a proactive approach to safeguarding against emerging threats in the credit card landscape. With this shift, credit card fraud has become a significant concern within the domain of internet-based transactions. Hence, there is a pressing demand to devise an optimal machine learning method for preventing fraudulent credit card transactions. The study employed four resampling techniques (CNN, AllKNN, SMOTE, and SVMSM ) and three machine learning approaches (XGBoost , CatBoost, and RF) for analysing credit card fraud datasets with the aim of detection. These findings demonstrated that integrating AllKNN as an undersampling technique and CatBoost as a classifier are achieving superior results across the evaluated methods. The accuracy, precision, recall, and f1-score were 99.9%, 95.9%, 80%, and 87.4%, respectively.  \nKeywords: Unbalanced data, machine learning techniques, fraud detection, and credit card fraud.  \nDOI: 10.7176/JIEA/14-2-02  \nPublication date:March 31st 2024  \n1. Introduction.  \nThe increasing trend of cashless society is causing a greater dependence on internet transactions. Contemporary fraud has evolved beyond the need for physical presence at crime scenes, allowing malevolent actors to operate discreetly from the confines of their homes. Various tactics for concealing identities further complicate the tracking process, encompassing methods like employing a VPN, directing victim traffic through the Tor network, and employing other sophisticated techniques. Tracing these perpetrators proves to be a formidable challenge.  \nThe ramifications of online financial losses are profound and should not be underestimated. Once offenders gain access to card details, they have the option to exploit the cards directly or sell the pilfered information to others. In India, for instance, approximately 70 million individuals have fallen victim to this trend, with their card details circulating on the dark web [1] . The UK witnessed a particularly severe credit card fraud case, resulting ina staggering total about GBP 17 million in lost revenue. This incident unfolded when an international group of fraudsters collaborated to illicitly obtain detailed information from over 32,000 credit cards in the mid-2000s [2] . Regarded as the largest card fraud in history, it underscores the substantial financial repercussions arising from inadequate security measures [3]. Both cardholders, trusting in the integrity of their transactions, and card issuers, responsible for processing these transactions, often find themselves misled. Despite assurances of transactional security, fraudsters remain dedicated to duping financial institutions and cardholders, presenting a significant challenge to the prevailing belief in the benign nature of all transactions.  \nFurthermore, an ongoing concern involves surreptitious fraudulent transactions conducted for financial gain, evading detection by both card issuers and cardholders. The obscure nature of these unautho","cbCaibNjBo8vaN0T","https://ap.wps.com/l/cbCaibNjBo8vaN0T","pdf",813319,1,9,"English","en",105,"# Introduction\n## Online transactions and evolving fraud threats\n## Impact of credit card fraud losses\n## Existing fraud detection approaches and machine learning role\n## Evaluation criteria and resampling for imbalanced data","[{\"question\":\"Why is machine learning important for credit card fraud detection?\",\"answer\":\"Machine learning enables data-driven classification and prediction to distinguish legitimate and fraudulent transactions. Its adaptive nature supports continuous improvement against emerging fraud patterns.\"},{\"question\":\"Which resampling and classifier combination performed best in this study?\",\"answer\":\"AllKNN as an undersampling technique combined with CatBoost as the classifier produced the best results among the evaluated methods.\"},{\"question\":\"What metrics were used to evaluate model performance?\",\"answer\":\"Accuracy, precision, recall, and F1-score were used. The top configuration reported accuracy 99.9%, precision 95.9%, recall 80%, and F1-score 87.4%.\"}]","Fraud Guard - A Comprehensive Comparative Analysis of Machine Learning Approaches to Enhance Credit Card Fraud Detection - Optimal Resampling and Classifier Results | PDF",1785721259,23,{"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},"fraud-guard-a-comprehensive-comparative-analysis-of-machine-learning-approaches-to-enhance-credit-card-fraud-detection-optimal-resampling-and-classifier-results","",{"@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/fraud-guard-a-comprehensive-comparative-analysis-of-machine-learning-approaches-to-enhance-credit-card-fraud-detection-optimal-resampling-and-classifier-results/118969/",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},"Why is machine learning important for credit card fraud detection?","Question",{"text":75,"@type":76},"Machine learning enables data-driven classification and prediction to distinguish legitimate and fraudulent transactions. Its adaptive nature supports continuous improvement against emerging fraud patterns.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which resampling and classifier combination performed best in this study?",{"text":80,"@type":76},"AllKNN as an undersampling technique combined with CatBoost as the classifier produced the best results among the evaluated methods.",{"name":82,"@type":73,"acceptedAnswer":83},"What metrics were used to evaluate model performance?",{"text":84,"@type":76},"Accuracy, precision, recall, and F1-score were used. The top configuration reported accuracy 99.9%, precision 95.9%, recall 80%, and F1-score 87.4%.","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},[93,97,101,105,110,115,120,123,127,130,134],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]