{"product_id":"fraud-analytics-using-descriptive-predictive-and-social-network-techniques-isbn-9781119133124","title":"Fraud Analytics Using Descriptive, Predictive, and Social Network Techniques","description":"\u003cb\u003eDetect fraud earlier to mitigate loss and prevent cascading damage\u003c\/b\u003e \u003cp\u003e\u003ci\u003eFraud Analytics Using Descriptive, Predictive, and Social Network Techniques \u003c\/i\u003eis an authoritative guidebook for setting up a comprehensive fraud detection analytics solution. Early detection is a key factor in mitigating fraud damage, but it involves more specialized techniques than detecting fraud at the more advanced stages. This invaluable guide details both the theory and technical aspects of these techniques, and provides expert insight into streamlining implementation. Coverage includes data gathering, preprocessing, model building, and post-implementation, with comprehensive guidance on various learning techniques and the data types utilized by each. These techniques are effective for fraud detection across industry boundaries, including applications in insurance fraud, credit card fraud, anti-money laundering, healthcare fraud, telecommunications fraud, click fraud, tax evasion, and more, giving you a highly practical framework for fraud prevention.\u003c\/p\u003e \u003cp\u003eIt is estimated that a typical organization loses about 5% of its revenue to fraud every year. More effective fraud detection is possible, and this book describes the various analytical techniques your organization must implement to put a stop to the revenue leak.\u003c\/p\u003e \u003cul\u003e \u003cli\u003eExamine fraud patterns in historical data\u003c\/li\u003e \u003cli\u003eUtilize labeled, unlabeled, and networked data\u003c\/li\u003e \u003cli\u003eDetect fraud before the damage cascades\u003c\/li\u003e \u003cli\u003eReduce losses, increase recovery, and tighten security\u003c\/li\u003e \u003c\/ul\u003e \u003cp\u003eThe longer fraud is allowed to go on, the more harm it causes. It expands exponentially, sending ripples of damage throughout the organization, and becomes more and more complex to track, stop, and reverse. Fraud prevention relies on early and effective fraud detection, enabled by the techniques discussed here. \u003ci\u003eFraud Analytics Using Descriptive, Predictive, and Social Network Techniques\u003c\/i\u003e helps you stop fraud in its tracks, and eliminate the opportunities for future occurrence.\u003c\/p\u003e \u003cp\u003eList of Figures xv\u003c\/p\u003e \u003cp\u003eForeword xxiii\u003c\/p\u003e \u003cp\u003ePreface xxv\u003c\/p\u003e \u003cp\u003eAcknowledgments xxix\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 1 Fraud: Detection, Prevention, and Analytics! 1\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eIntroduction 2\u003c\/p\u003e \u003cp\u003eFraud! 2\u003c\/p\u003e \u003cp\u003eFraud Detection and Prevention 10\u003c\/p\u003e \u003cp\u003eBig Data for Fraud Detection 15\u003c\/p\u003e \u003cp\u003eData-Driven Fraud Detection 17\u003c\/p\u003e \u003cp\u003eFraud-Detection Techniques 19\u003c\/p\u003e \u003cp\u003eFraud Cycle 22\u003c\/p\u003e \u003cp\u003eThe Fraud Analytics Process Model 26\u003c\/p\u003e \u003cp\u003eFraud Data Scientists 30\u003c\/p\u003e \u003cp\u003eA Fraud Data Scientist Should Have Solid Quantitative Skills 30\u003c\/p\u003e \u003cp\u003eA Fraud Data Scientist Should Be a Good Programmer 31\u003c\/p\u003e \u003cp\u003eA Fraud Data Scientist Should Excel in Communication and Visualization Skills 31\u003c\/p\u003e \u003cp\u003eA Fraud Data Scientist Should Have a Solid Business Understanding 32\u003c\/p\u003e \u003cp\u003eA Fraud Data Scientist Should Be Creative 32\u003c\/p\u003e \u003cp\u003eA Scientific Perspective on Fraud 33\u003c\/p\u003e \u003cp\u003eReferences 35\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 2 Data Collection, Sampling, and Preprocessing 37\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eIntroduction 38\u003c\/p\u003e \u003cp\u003eTypes of Data Sources 38\u003c\/p\u003e \u003cp\u003eMerging Data Sources 43\u003c\/p\u003e \u003cp\u003eSampling 45\u003c\/p\u003e \u003cp\u003eTypes of Data Elements 46\u003c\/p\u003e \u003cp\u003eVisual Data Exploration and Exploratory Statistical Analysis 47\u003c\/p\u003e \u003cp\u003eBenford’s Law 48\u003c\/p\u003e \u003cp\u003eDescriptive Statistics 51\u003c\/p\u003e \u003cp\u003eMissing Values 52\u003c\/p\u003e \u003cp\u003eOutlier Detection and Treatment 53\u003c\/p\u003e \u003cp\u003eRed Flags 57\u003c\/p\u003e \u003cp\u003eStandardizing Data 59\u003c\/p\u003e \u003cp\u003eCategorization 60\u003c\/p\u003e \u003cp\u003eWeights of Evidence Coding 63\u003c\/p\u003e \u003cp\u003eVariable Selection 65\u003c\/p\u003e \u003cp\u003ePrincipal Components Analysis 68\u003c\/p\u003e \u003cp\u003eRIDITs 72\u003c\/p\u003e \u003cp\u003ePRIDIT Analysis 73\u003c\/p\u003e \u003cp\u003eSegmentation 74\u003c\/p\u003e \u003cp\u003eReferences 75\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 3 Descriptive Analytics for Fraud Detection 77\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eIntroduction 78\u003c\/p\u003e \u003cp\u003eGraphical Outlier Detection Procedures 79\u003c\/p\u003e \u003cp\u003eStatistical Outlier Detection Procedures 83\u003c\/p\u003e \u003cp\u003eBreak-Point Analysis 84\u003c\/p\u003e \u003cp\u003ePeer-Group Analysis 85\u003c\/p\u003e \u003cp\u003eAssociation Rule Analysis 87\u003c\/p\u003e \u003cp\u003eClustering 89\u003c\/p\u003e \u003cp\u003eIntroduction 89\u003c\/p\u003e \u003cp\u003eDistance Metrics 90\u003c\/p\u003e \u003cp\u003eHierarchical Clustering 94\u003c\/p\u003e \u003cp\u003eExample of Hierarchical Clustering Procedures 97\u003c\/p\u003e \u003cp\u003e\u003ci\u003ek-Means Clustering 104\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003eSelf-Organizing Maps 109\u003c\/p\u003e \u003cp\u003eClustering with Constraints 111\u003c\/p\u003e \u003cp\u003eEvaluating and Interpreting Clustering Solutions 114\u003c\/p\u003e \u003cp\u003eOne-Class SVMs 117\u003c\/p\u003e \u003cp\u003eReferences 118\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 4 Predictive Analytics for Fraud Detection 121\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eIntroduction 122\u003c\/p\u003e \u003cp\u003eTarget Definition 123\u003c\/p\u003e \u003cp\u003eLinear Regression 125\u003c\/p\u003e \u003cp\u003eLogistic Regression 127\u003c\/p\u003e \u003cp\u003eBasic Concepts 127\u003c\/p\u003e \u003cp\u003eLogistic Regression Properties 129\u003c\/p\u003e \u003cp\u003eBuilding a Logistic Regression Scorecard 131\u003c\/p\u003e \u003cp\u003eVariable Selection for Linear and Logistic Regression 133\u003c\/p\u003e \u003cp\u003eDecision Trees 136\u003c\/p\u003e \u003cp\u003eBasic Concepts 136\u003c\/p\u003e \u003cp\u003eSplitting Decision 137\u003c\/p\u003e \u003cp\u003eStopping Decision 140\u003c\/p\u003e \u003cp\u003eDecision Tree Properties 141\u003c\/p\u003e \u003cp\u003eRegression Trees 142\u003c\/p\u003e \u003cp\u003eUsing Decision Trees in Fraud Analytics 143\u003c\/p\u003e \u003cp\u003eNeural Networks 144\u003c\/p\u003e \u003cp\u003eBasic Concepts 144\u003c\/p\u003e \u003cp\u003eWeight Learning 147\u003c\/p\u003e \u003cp\u003eOpening the Neural Network Black Box 150\u003c\/p\u003e \u003cp\u003eSupport Vector Machines 155\u003c\/p\u003e \u003cp\u003eLinear Programming 155\u003c\/p\u003e \u003cp\u003eThe Linear Separable Case 156\u003c\/p\u003e \u003cp\u003eThe Linear Nonseparable Case 159\u003c\/p\u003e \u003cp\u003eThe Nonlinear SVM Classifier 160\u003c\/p\u003e \u003cp\u003eSVMs for Regression 161\u003c\/p\u003e \u003cp\u003eOpening the SVM Black Box 163\u003c\/p\u003e \u003cp\u003eEnsemble Methods 164\u003c\/p\u003e \u003cp\u003eBagging 164\u003c\/p\u003e \u003cp\u003eBoosting 165\u003c\/p\u003e \u003cp\u003eRandom Forests 166\u003c\/p\u003e \u003cp\u003eEvaluating Ensemble Methods 167\u003c\/p\u003e \u003cp\u003eMulticlass Classification Techniques 168\u003c\/p\u003e \u003cp\u003eMulticlass Logistic Regression 168\u003c\/p\u003e \u003cp\u003eMulticlass Decision Trees 170\u003c\/p\u003e \u003cp\u003eMulticlass Neural Networks 170\u003c\/p\u003e \u003cp\u003eMulticlass Support Vector Machines 171\u003c\/p\u003e \u003cp\u003eEvaluating Predictive Models 172\u003c\/p\u003e \u003cp\u003eSplitting Up the Data Set 172\u003c\/p\u003e \u003cp\u003ePerformance Measures for Classification Models 176\u003c\/p\u003e \u003cp\u003ePerformance Measures for Regression Models 185\u003c\/p\u003e \u003cp\u003eOther Performance Measures for Predictive Analytical Models 188\u003c\/p\u003e \u003cp\u003eDeveloping Predictive Models for Skewed Data Sets 189\u003c\/p\u003e \u003cp\u003eVarying the Sample Window 190\u003c\/p\u003e \u003cp\u003eUndersampling and Oversampling 190\u003c\/p\u003e \u003cp\u003eSynthetic Minority Oversampling Technique (SMOTE) 192\u003c\/p\u003e \u003cp\u003eLikelihood Approach 194\u003c\/p\u003e \u003cp\u003eAdjusting Posterior Probabilities 197\u003c\/p\u003e \u003cp\u003eCost-sensitive Learning 198\u003c\/p\u003e \u003cp\u003eFraud Performance Benchmarks 200\u003c\/p\u003e \u003cp\u003eReferences 201\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 5 Social Network Analysis for Fraud Detection 207\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eNetworks: Form, Components, Characteristics, and Their Applications 209\u003c\/p\u003e \u003cp\u003eSocial Networks 211\u003c\/p\u003e \u003cp\u003eNetwork Components 214\u003c\/p\u003e \u003cp\u003eNetwork Representation 219\u003c\/p\u003e \u003cp\u003eIs Fraud a Social Phenomenon? An Introduction to Homophily 222\u003c\/p\u003e \u003cp\u003eImpact of the Neighborhood: Metrics 227\u003c\/p\u003e \u003cp\u003eNeighborhood Metrics 228\u003c\/p\u003e \u003cp\u003eCentrality Metrics 238\u003c\/p\u003e \u003cp\u003eCollective Inference Algorithms 246\u003c\/p\u003e \u003cp\u003eFeaturization: Summary Overview 254\u003c\/p\u003e \u003cp\u003eCommunity Mining: Finding Groups of Fraudsters 254\u003c\/p\u003e \u003cp\u003eExtending the Graph: Toward a Bipartite Representation 266\u003c\/p\u003e \u003cp\u003eMultipartite Graphs 269\u003c\/p\u003e \u003cp\u003eCase Study: Gotcha! 270\u003c\/p\u003e \u003cp\u003eReferences 277\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 6 Fraud Analytics: Post-Processing 279\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eIntroduction 280\u003c\/p\u003e \u003cp\u003eThe Analytical Fraud Model Life Cycle 280\u003c\/p\u003e \u003cp\u003eModel Representation 281\u003c\/p\u003e \u003cp\u003eTraffic Light Indicator Approach 282\u003c\/p\u003e \u003cp\u003eDecision Tables 283\u003c\/p\u003e \u003cp\u003eSelecting the Sample to Investigate 286\u003c\/p\u003e \u003cp\u003eFraud Alert and Case Management 290\u003c\/p\u003e \u003cp\u003eVisual Analytics 296\u003c\/p\u003e \u003cp\u003eBacktesting Analytical Fraud Models 302\u003c\/p\u003e \u003cp\u003eIntroduction 302\u003c\/p\u003e \u003cp\u003eBacktesting Data Stability 302\u003c\/p\u003e \u003cp\u003eBacktesting Model Stability 305\u003c\/p\u003e \u003cp\u003eBacktesting Model Calibration 308\u003c\/p\u003e \u003cp\u003eModel Design and Documentation 311\u003c\/p\u003e \u003cp\u003eReferences 312\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 7 Fraud Analytics: A Broader Perspective 313\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eIntroduction 314\u003c\/p\u003e \u003cp\u003eData Quality 314\u003c\/p\u003e \u003cp\u003eData-Quality Issues 314\u003c\/p\u003e \u003cp\u003eData-Quality Programs and Management 315\u003c\/p\u003e \u003cp\u003ePrivacy 317\u003c\/p\u003e \u003cp\u003eThe RACI Matrix 318\u003c\/p\u003e \u003cp\u003eAccessing Internal Data 319\u003c\/p\u003e \u003cp\u003eLabel-Based Access Control (LBAC) 324\u003c\/p\u003e \u003cp\u003eAccessing External Data 325\u003c\/p\u003e \u003cp\u003eCapital Calculation for Fraud Loss 326\u003c\/p\u003e \u003cp\u003eExpected and Unexpected Losses 327\u003c\/p\u003e \u003cp\u003eAggregate Loss Distribution 329\u003c\/p\u003e \u003cp\u003eCapital Calculation for Fraud Loss Using Monte Carlo Simulation 331\u003c\/p\u003e \u003cp\u003eAn Economic Perspective on Fraud Analytics 334\u003c\/p\u003e \u003cp\u003eTotal Cost of Ownership 334\u003c\/p\u003e \u003cp\u003eReturn on Investment 335\u003c\/p\u003e \u003cp\u003eIn Versus Outsourcing 337\u003c\/p\u003e \u003cp\u003eModeling Extensions 338\u003c\/p\u003e \u003cp\u003eForecasting 338\u003c\/p\u003e \u003cp\u003eText Analytics 340\u003c\/p\u003e \u003cp\u003eThe Internet of Things 342\u003c\/p\u003e \u003cp\u003eCorporate Fraud Governance 344\u003c\/p\u003e \u003cp\u003eReferences 346\u003c\/p\u003e \u003cp\u003eAbout the Authors 347\u003c\/p\u003e \u003cp\u003eIndex 349 \u003c\/p\u003e \u003cp\u003e\u003cb\u003eBART BAESENS\u003c\/b\u003e is a full professor at KU Leuven, and a lecturer at the University of Southampton. He has done extensive research on analytics, customer relationship management, web analytics, fraud detection, and credit risk management. He regularly advises and provides consulting support to international firms with respect to their analytics and credit risk management strategy.\u003c\/p\u003e \u003cp\u003e\u003cb\u003eVÉRONIQUE VAN VLASSELAER\u003c\/b\u003e is a PhD researcher in the Department of Decision Sciences and Information Management at KU Leuven. Her research focuses on the development of new techniques for fraud detection by combining predictive and network analytics. \u003c\/p\u003e\u003cp\u003e\u003cb\u003eWOUTER VERBEKE\u003c\/b\u003e is an assistant professor at Vrije Universiteit Brussel (Brussels, Belgium). His research is situated in the field of predictive analytics and complex network analysis with applications in fraud, marketing, credit risk, human resources management, and mobility.  \u003c\/p\u003e\u003cp\u003eThe sooner fraud detection occurs the better—as the likelihood of further losses is lower, potential recoveries are higher, and security issues can be addressed more rapidly. Catching fraud in an early stage, though, is more difficult than detecting it later, and requires specific techniques. Packed with numerous real-world examples, \u003ci\u003eFraud Analytics Using Descriptive, Predictive, and Social Network Techniques\u003c\/i\u003e authoritatively shows you how to put historical data to work against fraud.\u003c\/p\u003e \u003cp\u003eAuthors Bart Baesens, Véronique Van Vlasselaer, and Wouter Verbeke expertly discuss the use of unsupervised learning, supervised learning, and social network learning using techniques across a wide variety of fraud applications, such as insurance fraud, credit card fraud, anti-money laundering, healthcare fraud, telecommunications fraud, click fraud, and tax evasion. This book provides the essential guidance you need to examine fraud patterns from historical data in order to detect fraud early in the process. \u003c\/p\u003e\u003cp\u003eProviding a clear look at the pivotal role analytics plays in managing fraud, this book includes straightforward guidance on: \u003c\/p\u003e\u003cul\u003e\n\u003cli\u003eFraud detection, prevention, and analytics\u003c\/li\u003e \u003cli\u003eData collection, sampling, and preprocessing\u003c\/li\u003e \u003cli\u003eDescriptive analytics for fraud detection\u003c\/li\u003e \u003cli\u003ePredictive analytics for fraud detection\u003c\/li\u003e \u003cli\u003eSocial network analytics for fraud detection\u003c\/li\u003e \u003cli\u003ePost processing of fraud analytics\u003c\/li\u003e \u003cli\u003eFraud analytics from an economic perspective\u003c\/li\u003e\n\u003c\/ul\u003e \u003cp\u003eRead \u003ci\u003eFraud Analytics Using Descriptive, Predictive, and Social Network Techniques\u003c\/i\u003e for a comprehensive overview of fraud detection analytical techniques and implementation guidance for an effective fraud prevention solution that works for your organization.\u003c\/p\u003e","brand":"Wiley","offers":[{"title":"Default Title","offer_id":47989242396901,"sku":"NP9781119133124","price":52.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1842\/7735\/files\/9781119133124.jpg?v=1761783345","url":"https:\/\/k12savings.com\/es\/products\/fraud-analytics-using-descriptive-predictive-and-social-network-techniques-isbn-9781119133124","provider":"K12savings","version":"1.0","type":"link"}