[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120412-en":3,"doc-seo-120412-105":29,"detail-sidebar-cat-0-en-105":89},{"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":11},120412,1374391974468,"Eden","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","UPI Fraud Detection Using Machine Learning","Digital payments have expanded rapidly due to convenience and accessibility, but the same momentum has increased online payment fraud. Reserve Bank of India data shows digital payment volumes and values rising by 216% and 10% from March 2019 to March 2022. Widespread UPI adoption has also enabled fraudsters to exploit system and user vulnerabilities and siphon funds. Since transactions are traceable, this study builds a machine learning model to detect fraudulent transactions by analyzing transaction patterns in a dataset, improving online payment security.","UPI Fraud Detection Using Machine Learning  \nNilam Prakash Khopade1*, Shubhangi M. Vitalkar2  \n1Student, Department of MCA, Trinity Academy of Engineering, Pune, India  \n2Professor, Department of MCA, Trinity Academy of Engineering, Pune, India  \nAbstract—In recent years, digital transactions have surged, driven by convenience and accessibility, but this growth has also led to a rise in online payment fraud. According to the Reserve Bank of India, digital payment volumes and values increased by 216% and 10%, respectively, from March 2019 to March 2022. While consumers increasingly embrace digital payments, security concerns and a lack of awareness about safe online practices persist. Just a few years ago, online payments were rare, but today, UPI QR codes are commonplace, even at doorsteps. This widespread adoption has attracted fraudsters who exploit vulnerabilities to deceive users and siphon funds. Fortunately, digital transactions are trackable, enabling analysis with advanced tools. This study aims to develop a machine learning model to detect fraudulent transactions by analysing patterns in a transaction dataset, enhancing the security of online payments.  \nIndex Terms—E-banking, Cyber fraud, Banking security, Voice recognition, Blockchain, Data encryption.  \n1. Introduction  \nThe rise of mobile payments as a dominant payment method has fuelled a surge in transactions on online trading platforms, transforming the digital economy. However, this popularity has also attracted cybercriminals who exploit the intricate network environment to perpetrate fraud, causing financial harm to consumers and hindering the sustainable development of ecommerce. Effective fraud detection mechanisms are thus critical to countering network transaction fraud. Traditional detection methods, which rely on statistical and multidimensional analysis, often fail to uncover hidden patterns in transaction data, limiting their efficacy. In contrast, big data technologies and machine learning algorithms provide powerful tools for identifying fraudulent activities. By leveraging large datasets, machine learning can extract critical features that conventional statistical approaches overlook, enabling the development of robust models for fraud detection. In 2018, Zhaohui Zhang introduced a convolutional neural network-based model tailored for transaction fraud detection, which offered enhanced stability and classification performance compared to other neural network models. Nevertheless, challenges such as imbalanced sample labels continue to affect detection accuracy. To address this, this study proposes two advanced fraud detection algorithms: one based on a Fully Connected Neural Network that combines two models with distinct cross-entropy loss functions for efficient design, and another that optimizes an Boost classifier using  \nHyperope to achieve superior performance through optimal parameter selection. These algorithms cater to diverse application scenarios, offering promising solutions to mitigate transaction fraud and its associated losses.  \nThe financial transaction landscape in India has been revolutionized by the emergence of digital payment systems, with the Unified Payments Interface (UPI), developed by the National Payments Corporation of India (NPCI), leading the charge. UPI has transformed financial inclusion by offering a seamless, interoperable, and real-time platform for transferring funds between individuals, businesses, and institutions. The proliferation of financial institutions and the rise of web-based e-commerce have driven a significant surge in transaction volumes. However, this growth has been accompanied by an alarming increase in fraudulent transactions, posing a persistent challenge for online banking security. As UPI evolves, so do the tactics of fraudsters, who continuously adapt to exploit vulnerabilities in fraud detection systems, making detection increasingly complex. Fraudsters often capitalize on weaknesses in sec","cbCaiba3r39nMOhh","https://ap.wps.com/l/cbCaiba3r39nMOhh","pdf",259171,1,3,"English","en",105,"# Introduction\n## Problem background and impact\n## Limitations of traditional detection\n## Machine learning approaches and prior work\n## Proposed fraud detection algorithms","[{\"question\":\"Why has UPI fraud become a growing concern?\",\"answer\":\"UPI adoption has increased transaction volumes and lowered barriers for both legitimate use and attacks. Fraudsters exploit vulnerabilities in security, control, and monitoring systems, making detection harder over time.\"},{\"question\":\"How does the study frame fraud detection?\",\"answer\":\"Fraud detection in banking is treated as a binary classification problem that distinguishes legitimate transactions from fraudulent ones.\"},{\"question\":\"What is the goal of the proposed approach?\",\"answer\":\"To develop machine learning models that analyze patterns in transaction data and more effectively identify fraudulent transactions, addressing limitations of traditional statistical methods.\"}]","UPI Fraud Detection Using Machine Learning | PDF",1785729919,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":84,"head_meta":86,"extra_data":88,"updated_unix":28},"upi-fraud-detection-using-machine-learning","",{"@graph":35,"@context":83},[36,52,66],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,49],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":21},"https://docshare.wps.com/document/research-report/",{"item":50,"name":13,"@type":42,"position":51},"https://docshare.wps.com/document/upi-fraud-detection-using-machine-learning/120412/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":23,"description":14,"dateModified":60,"datePublished":60,"encodingFormat":59,"isAccessibleForFree":61,"interactionStatistic":62},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":40,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":63,"interactionType":64,"userInteractionCount":4},"InteractionCounter",{"@type":65},"ViewAction",{"@type":67,"mainEntity":68},"FAQPage",[69,75,79],{"name":70,"@type":71,"acceptedAnswer":72},"Why has UPI fraud become a growing concern?","Question",{"text":73,"@type":74},"UPI adoption has increased transaction volumes and lowered barriers for both legitimate use and attacks. Fraudsters exploit vulnerabilities in security, control, and monitoring systems, making detection harder over time.","Answer",{"name":76,"@type":71,"acceptedAnswer":77},"How does the study frame fraud detection?",{"text":78,"@type":74},"Fraud detection in banking is treated as a binary classification problem that distinguishes legitimate transactions from fraudulent ones.",{"name":80,"@type":71,"acceptedAnswer":81},"What is the goal of the proposed approach?",{"text":82,"@type":74},"To develop machine learning models that analyze patterns in transaction data and more effectively identify fraudulent transactions, addressing limitations of traditional statistical methods.","https://schema.org",{"og:url":50,"og:type":85,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":87,"canonical":50},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":90},[91,95,99,103,108,113,118,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":92,"show_sort_weight":93,"slug":94},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":96,"show_sort_weight":97,"slug":98},"Literature",80,"literature",{"id":51,"doc_module":4,"doc_module_name":45,"category_name":100,"show_sort_weight":101,"slug":102},"Exam",70,"exam",{"id":104,"doc_module":4,"doc_module_name":45,"category_name":105,"show_sort_weight":106,"slug":107},5,"Comic",60,"comic",{"id":109,"doc_module":4,"doc_module_name":45,"category_name":110,"show_sort_weight":111,"slug":112},6,"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":45,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":104,"slug":136},19,"General","general"]