[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122878-en":3,"doc-seo-122878-105":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},122878,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",8,"Research & Report","Fraud Detection in Vehicle Insurance Claims using Machine Learning","Insurance fraud creates major financial and operational pressure on insurers, especially through fraudulent vehicle insurance claims. This dissertation applies machine learning methods to identify fraud accurately using an imbalanced dataset. Six classifiers—Logistic Regression, Random Forest, Gaussian Naive Bayes, Decision Tree, XGBoost, and Gradient Boosting—are compared with class-imbalance remedies including SMOTE, Borderline SMOTE, and ADASYN. Models are evaluated with F1 score, recall, and AUC. XGBoost and Gradient Boosting show the best overall balance of precision and recall, while Gaussian Naive Bayes achieves exceptional recall for reducing missed fraud cases.","UCLA  \nUCLA Electronic Theses and Dissertations  \nTitle  \nFraud Detection in Vehicle Insurance Claims using Machine Learning  \nPermalink  \n[https://escholarship.org/uc/item/0jx1h48j](https://escholarship.org/uc/item/0jx1h48j)  \nAuthor  \nZhang, Ziyang  \nPublication Date  \n2024  \nPeer reviewed|Thesis/dissertation  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nUNIVERSITY OF CALIFORNIA  \nLos Angeles  \nFraud Detection in Vehicle Insurance Claims using Machine Learning  \nA dissertation submitted in partial satisfaction of the requirements for the degree Master of Applied Statistics and Data Science  \nby  \nZiyang Zhang  \n2024  \n© Copyright by Ziyang Zhang 2024  \nABSTRACT OF THE DISSERTATION  \nFraud Detection in Vehicle Insurance Claims using Machine Learning  \nby  \nZiyang Zhang  \nMaster of Applied Statistics and Data Science  \nUniversity of California, Los Angeles, 2024  \nProfessor Yingnian Wu, Chair  \nInsurance fraud poses a significant financial burden on the industry, with fraudulent vehicle insurance claims being a major contributor. This study explores the application of machine learning techniques to accurately detect fraudulent vehicle insurance claims. Six different models-Logistic Regression, Random Forest, Gaussian Naive Bayes, Decision Tree, XGBoost, and Gradient Boosting classifiers-are evaluated on an imbalanced dataset. To address class imbalance, oversampling techniques like SMOTE, Borderline SMOTE, and ADASYN are employed. Performance is assessed using metrics such as F1 score, recall, and AUC. Results indicate that XGBoost and Gradient Boosting models demonstrate superior overall performance, effectively balancing precision and recall. The Gaussian Naive Bayes model exhibits exceptional recall, making it suitable for minimizing missed fraud cases.  \nThe dissertation of Ziyang Zhang is approved.  \nNicolas Christou  \nOscar H. Madrid Padilla  \nYingnian Wu, Committee Chair  \nUniversity of California, Los Angeles 2024  \nTABLE OF CONTENTS  \n1 Introduction ...................................... 1  \n2 Exploratory Data Analysis ............................. 3  \n2.1 Data Set ...................................... 3  \n2.2 Preparing data for modeling ........................... 4  \n2.2.1 Data Cleaning ............................... 4  \n2.2.2 Feature Engineering ........................... 4  \n2.2.3 Feature Selection ............................. 16  \n3 Methodology ..................................... 19  \n3.1 Model Introduction ................................ 19  \n3.1.1 Logistic Regression ............................ 19  \n3.1.2 Random Forest Classifier ......................... 20  \n3.1.3 Gaussian Naive Bayes .......................... 21  \n3.1.4 Decision Tree Classifier .......................... 22  \n3.1.5 XGBoost Classifier ............................ 24  \n3.1.6 Gradient Boosting Classifier ....................... 25  \n3.2 Handling Imbalanced Data ............................ 27  \n3.2.1 Under-sampling .............................. 27  \n3.2.2 Over-sampling ............................... 27  \n3.2.3 Synthetic Sampling ............................ 28  \n3.3 Criteria to Measure Performance ........................ 29  \n3.3.1 Accuracy ................................. 29  \n3.3.2 Precision .................................. 29  \n3.3.3 Recall ................................... 30  \n3.3.4 F1 Score .................................. 30  \n3.3.5 AUC .................................... 31  \n4 Models ......................................... 32  \n4.1 Model Establishment ............................... 32  \n4.2 Results Analysis and Comparison ........................ 32  \n4.2.1 Evaluation Metrics Selection ....................... 32  \n4.2.2 F1 Score Analysis ............................. 33  \n4.2.3 Recall Analysis .............................. 34  \n4.2.4 AUC Analysis ............................... 35  \n4.3 Comprehensive Analysis ............................. 36  \n5 Lim","cbCaidowegCd2grh","https://ap.wps.com/l/cbCaidowegCd2grh","pdf",1004407,1,48,"English","en",105,"# Introduction\n# Exploratory Data Analysis\n## Data Set\n## Preparing data for modeling\n### Data Cleaning\n### Feature Engineering\n### Feature Selection\n# Methodology\n## Model Introduction\n### Logistic Regression\n### Random Forest Classifier\n### Gaussian Naive Bayes\n### Decision Tree Classifier\n### XGBoost Classifier\n### Gradient Boosting Classifier\n## Handling Imbalanced Data\n### Under-sampling\n### Over-sampling\n### Synthetic Sampling\n## Criteria to Measure Performance\n### Accuracy\n### Precision\n### Recall\n### F1 Score\n### AUC\n# Models\n## Model Establishment\n## Results Analysis and Comparison\n### Evaluation Metrics Selection\n### F1 Score Analysis\n### Recall Analysis\n### AUC Analysis\n## Comprehensive Analysis\n# Limitations and Conclusion\n# References","[{\"question\":\"What problem does the dissertation address in vehicle insurance?\",\"answer\":\"It targets insurance fraud, focusing on fraudulent vehicle insurance claims that cause substantial financial losses and undermine industry integrity.\"},{\"question\":\"Which machine learning models are evaluated for fraud detection?\",\"answer\":\"The study compares Logistic Regression, Random Forest, Gaussian Naive Bayes, Decision Tree, XGBoost, and Gradient Boosting classifiers.\"},{\"question\":\"How does the dissertation handle the imbalanced nature of fraud data?\",\"answer\":\"It uses oversampling and related techniques such as SMOTE, Borderline SMOTE, and ADASYN to mitigate class imbalance.\"}]","Fraud Detection in Vehicle Insurance Claims using Machine Learning | PDF",1785813475,121,{"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-detection-in-vehicle-insurance-claims-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/fraud-detection-in-vehicle-insurance-claims-using-machine-learning/122878/",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","2026-08-04",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 dissertation address in vehicle insurance?","Question",{"text":75,"@type":76},"It targets insurance fraud, focusing on fraudulent vehicle insurance claims that cause substantial financial losses and undermine industry integrity.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning models are evaluated for fraud detection?",{"text":80,"@type":76},"The study compares Logistic Regression, Random Forest, Gaussian Naive Bayes, Decision Tree, XGBoost, and Gradient Boosting classifiers.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the dissertation handle the imbalanced nature of fraud data?",{"text":84,"@type":76},"It uses oversampling and related techniques such as SMOTE, Borderline SMOTE, and ADASYN to mitigate class imbalance.","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"]