[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118488-en":3,"doc-seo-118488-105":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},118488,1374391974468,"Eden","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Investigating Fraudulent E-Commerce Transactions - A Data-driven Approach Using Machine Learning","This project investigates fraudulent e-commerce transactions through a data-driven machine learning workflow. It defines the problem statement, reviews relevant literature, and details a full modeling pipeline including data sourcing, exploratory data analysis, and data preprocessing. The approach includes removing non-informative features, encoding categorical variables, and handling unlabeled data with semi-supervised learning. Multiple model families are trained and compared, including Random Forest, XGBoost, KNN, Logistic Regression, deep learning with TensorFlow and Keras, and stacking ensembles, evaluated with precision, recall, F1-score, accuracy, and confusion matrices.","Investigating Fraudulent E-Commerce Transactions: A Data-driven Approach Using Machine  \nLearning  \nCreative Component Project Report  \nBy:  \nJoel Alan Buehler  \nMaster of Science in Information Systems and Professional Business Administration  \nSubmitted in partial fulfillment of the requirements for the degrees of Master of Science in Information Systems (MSIS) and Master of Professional Business Administration (PMBA) .  \nMajor Professors: Dr. Anthony Townsend and Dr. Valentina Salotti  \nIvy College of Business  \nIowa State University Ames, Iowa  \n2024  \nTable of Contents  \nAcknowledgment...................................................................................................................................... 5  \nAbstract..................................................................................................................................................... 6  \nIntroduction .............................................................................................................................................. 7  \nProblem Statement.................................................................................................................................... 7  \nLiterature Review ..................................................................................................................................... 8  \nProject Methodology .............................................................................................................................. 11  \nData Source ......................................................................................................................................... 11  \nExploratory Data Analysis .................................................................................................................. 12  \nData Preprocessing.............................................................................................................................. 15  \nRemoving Non-informative Features:............................................................................................. 15  \nHandling Categorical Variables with Label Encoding: ................................................................... 16  \nHandling Unlabeled Data: Semi-supervised Learning.................................................................... 17  \nImportance of Balancing Labeling and Feature Processing............................................................ 17  \nSelection of Machine Learning Models, Frameworks, and APIs ........................................................... 18  \nRandom Forest Classifier.................................................................................................................... 18  \nXGBoost Classifier ............................................................................................................................. 19  \nK-Nearest Neighbors (KNN) .............................................................................................................. 19  \nLogistic Regression............................................................................................................................. 20  \nTensorFlow and Keras: Deep Learning Models ................................................................................. 21  \nStacking Classifier: Combining Traditional and Deep Learning Models ........................................... 21  \nSemi-Supervised Learning (Label Spreading) .................................................................................... 22  \nModel Architecture and Hyperparameters .......................................................................................... 23  \nKeras Dense Model (for Feature Extraction) .................................................................................. 23  \nKeras LSTM Model (for Additional Feature Extraction) ................................................................ 24  \nBase Models in Stacking Classifier............","cbCaig4kuvgL8FlW","https://ap.wps.com/l/cbCaig4kuvgL8FlW","pdf",1135940,1,58,"English","en",105,"# Table of Contents\n## Acknowledgment\n## Abstract\n## Introduction\n## Problem Statement\n## Literature Review\n## Project Methodology\n## Data Source\n## Exploratory Data Analysis\n## Data Preprocessing\n## Removing Non-informative Features\n## Handling Categorical Variables with Label Encoding\n## Handling Unlabeled Data: Semi-supervised Learning\n## Selection of Machine Learning Models, Frameworks, and APIs\n## Evaluation of Models\n## Conclusion","[{\"question\":\"What is the main goal of the project?\",\"answer\":\"The project aims to detect fraudulent e-commerce transactions using a data-driven machine learning approach.\"},{\"question\":\"How does the methodology prepare the dataset before modeling?\",\"answer\":\"It uses exploratory data analysis and data preprocessing, including removing non-informative features, encoding categorical variables, and applying semi-supervised learning for unlabeled data.\"},{\"question\":\"Which evaluation metrics and comparison methods are used for the models?\",\"answer\":\"Model performance is assessed with precision, recall, F1-score, accuracy, and confusion matrices, followed by comparisons across different classifiers.\"}]","Investigating Fraudulent E-Commerce Transactions - A Data-driven Approach Using Machine Learning | PDF",1785683850,146,{"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},"investigating-fraudulent-e-commerce-transactions-a-data-driven-approach-using-machine-learning","",{"@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/investigating-fraudulent-e-commerce-transactions-a-data-driven-approach-using-machine-learning/118488/",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 is the main goal of the project?","Question",{"text":75,"@type":76},"The project aims to detect fraudulent e-commerce transactions using a data-driven machine learning approach.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the methodology prepare the dataset before modeling?",{"text":80,"@type":76},"It uses exploratory data analysis and data preprocessing, including removing non-informative features, encoding categorical variables, and applying semi-supervised learning for unlabeled data.",{"name":82,"@type":73,"acceptedAnswer":83},"Which evaluation metrics and comparison methods are used for the models?",{"text":84,"@type":76},"Model performance is assessed with precision, recall, F1-score, accuracy, and confusion matrices, followed by comparisons across different classifiers.","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"]