[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120392-en":3,"doc-seo-120392-105":29,"detail-sidebar-cat-0-en-105":90},{"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":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},120392,2336464648746,"Skyler","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Elevating Fraud Detection - Machine Learning Models with Computational Intelligence Optimization","E-commerce fraud is escalating as online transactions expand, demanding faster and more accurate payment-fraud identification. This study compares metaheuristic optimization methods as hyperparameter tuning approaches, focusing on particle swarm optimization (PSO) and genetic algorithm (GA). The optimizers tune the ROC AUC of XGBoost, random forest, and light gradient boosting models using unbalanced data. Results show random forest achieves the highest ROC AUC (88.69%) after PSO-based tuning, while PSO performs consistently across scenarios.","Elevating fraud detection: machine learning models with computational intelligence optimization  \nCheryl Angelica, Charleen, Antoni Wibowo  \nDepartment of Computer Science, Master of Computer Science, Bina Nusantara University, Jakarta, Indonesia  \nArticle history:  \nReceived Jan 4, 2024 Revised Mar 26, 2024 Accepted Apr 12, 2024  \nKeywords:  \nE-commerce Fraud detection Genetic algorithm  \nLight gradient boost machine Particle swarm optimization Random forest classifier X-gradient boost  \nCorresponding Author:  \nThe amount of crimes committed online has undoubtedly increased as more people use the internet for e-commerce and other financial transactions. Machine learning algorithms have been created to detect payment fraud in online purchasing in order to address the issue. This study performs a thorough comparative examination of different metaheuristic optimizationsas hyperparameter tuning methods; these are particle swarm optimization (PSO) and genetic algorithm (GA) . They are used to optimize the receiver operating characteristic (ROC) area under the curve (AUC) of the three machine learning algorithms, namely X-gradient boost, random forest classifier, and light gradient boost machine. Since the study's data are unbalanced, the determined metrics were ROC AUC. PSO offers consistent conditions for finding the best solution, according to our experiment. Without the inclusion of population annihilation strategies, PSO can achieve the greatest results in various situations which are different from GA, a consistent condition for finding the best solution, according to our experiment. Without the inclusion of population annihilation strategies, PSO can achieve the greatest results in various situations. The findings indicate that random forest classifier provided the highest ROC AUC value both before and after the hyperparameter tuning process, with a score of 88.69% attained while utilizing PSO.  \nThis is an open access article under the CC BY-SA license.  \nCharleen  \nDepartment of Computer Science, Master of Computer Science, Bina Nusantara University Jakarta 11480, Indonesia  \nEmail: [charleen@binus.ac.id](charleen@binus.ac.id)  \nArticle Info ABSTRACT  \n1. INTRODUCTION  \nThe way society functions has undergone a significant change as a result of technological advancement. The development of technologies has completely changed how people could go about their everyday life and do business. Meeting personal needs is one of the improvements. They only purchase their wants using digital technologies namely online shopping. It has become a popular and practical way to buy goods and services. The number of options for online shopping has significantly increased with the development of companies like Shopee and Tokopedia. However, the increasing usage of the internet fore-commerce and other financial operations has unavoidably increased the number of crimes committed on the internet. The concealment of the complex network may provide a breeding ground for criminals to engage in fraudulent activities [1] .  \nThe merchants must deal with a wide variety of fraud and abuse. The account takeover, free-trial abuse, refund fraud, reseller fraud, fake product news, first-party fraud, payment fraud, and many more are examples of fraud [2] . All of these put the merchants' reputation and revenue at risk. Money laundering and the spread of fake news are two examples of fraud that have serious repercussions for society as a whole.  \nE-commerce fraud is increasing quickly because, unlike in the early years of the internet, today's scammers are well-funded and well-equipped professional rings. The extremely constrained window of time in which acceptance or denial must be made is the main difficulty in fraud detection. The sheer volume of transactions that must be handled at one time is also remarkable. One of the main concerns with e-commerce systems is identifying fraud as soon as possible when the transaction is being performed [3] . In realit","cbCaieoKG6pZ5UbK","https://ap.wps.com/l/cbCaieoKG6pZ5UbK","pdf",542607,1,"English","en",105,"# INTRODUCTION\n## E-commerce fraud challenges and transaction complexity\n## Machine learning for fraud detection\n## Metaheuristic optimization and hyperparameter tuning\n# RELATED WORK\n## Supervised learning for unbalanced fraud datasets\n# METHODOLOGY\n## Algorithms: XGBoost, random forest, LightGBM\n## Optimizers: PSO and GA\n# EXPERIMENT RESULTS\n## ROC AUC evaluation before and after tuning\n# CONCLUSION\n## Key findings and comparative performance","[{\"question\":\"What problem does the study focus on?\",\"answer\":\"The study focuses on detecting payment fraud in online shopping, where fraudulent and legitimate transactions coexist and rapid decisions are required.\"},{\"question\":\"Which optimization methods are compared in the research?\",\"answer\":\"The research compares particle swarm optimization (PSO) and genetic algorithm (GA) as metaheuristic hyperparameter tuning methods.\"},{\"question\":\"Which machine learning model performs best according to ROC AUC?\",\"answer\":\"The random forest classifier provides the highest ROC AUC value, reaching 88.69% when optimized with PSO.\"}]","Elevating Fraud Detection - Machine Learning Models with Computational Intelligence Optimization | PDF",1785729797,20,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"elevating-fraud-detection-machine-learning-models-with-computational-intelligence-optimization","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"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":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/elevating-fraud-detection-machine-learning-models-with-computational-intelligence-optimization/120392/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":22,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What problem does the study focus on?","Question",{"text":74,"@type":75},"The study focuses on detecting payment fraud in online shopping, where fraudulent and legitimate transactions coexist and rapid decisions are required.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"Which optimization methods are compared in the research?",{"text":79,"@type":75},"The research compares particle swarm optimization (PSO) and genetic algorithm (GA) as metaheuristic hyperparameter tuning methods.",{"name":81,"@type":72,"acceptedAnswer":82},"Which machine learning model performs best according to ROC AUC?",{"text":83,"@type":75},"The random forest classifier provides the highest ROC AUC value, reaching 88.69% when optimized with PSO.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":28,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":28,"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":105,"slug":136},19,"General","general"]