Fraud Analytics Using Descriptive, Predictive and Social Network Techniques is 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.

·Fraud: Detection, Prevention and Analytics!
·Data Collection, Sampling and Preprocessing
·Descriptive Analytics for Fraud Detection
·Predictive Analytics for Fraud Detection
·Social Network Analysis for Fraud Detection
·Fraud Analytics: Post-Processing
·Fraud Analytics: A Broader Perspective


Table of Contents:
List of Figures Foreword Preface Acknowledgments Chapter 1 Fraud: Detection, Prevention and Analytics! ·Introduction ·Fraud! ·Fraud Detection and Prevention ·Big Data for Fraud Detection ·Data-Driven Fraud Detection ·Fraud-Detection Techniques ·Fraud Cycle ·The Fraud Analytics Process Model ·Fraud Data Scientists ·A Fraud Data Scientist Should Have Solid Quantitative Skills ·A Fraud Data Scientist Should Be a Good Programmer ·A Fraud Data Scientist Should Excel in Communication and Visualization Skills ·A Fraud Data Scientist Should Have a Solid Business Understanding ·A Fraud Data Scientist Should Be Creative ·A Scientific Perspective on Fraud Chapter 2 Data Collection, Sampling and Preprocessing ·Introduction ·Types of Data Sources ·Merging Data Sources ·Sampling ·Types of Data Elements ·Visual Data Exploration and Exploratory Statistical Analysis ·Benford's Law ·Descriptive Statistics ·Missing Values ·Outlier Detection and Treatment ·Red Flags ·Standardizing Data ·Categorization ·Weights of Evidence Coding ·Variable Selection ·Principal Components Analysis ·RIDITs ·PRIDIT Analysis ·Segmentation Chapter 3 Descriptive Analytics for Fraud Detection ·Introduction ·Graphical Outlier Detection Procedures ·Statistical Outlier Detection Procedures ·Break-Point Analysis ·Peer-Group Analysis ·Association Rule Analysis ·Clustering ·Introduction ·Distance Metrics ·Hierarchical Clustering ·Example of Hierarchical Clustering Procedures ·k-Means Clustering ·Self-Organizing Maps ·Clustering with Constraints ·Evaluating and Interpreting Clustering Solutions ·One-Class SVMs Chapter 4 Predictive Analytics for Fraud Detection ·Introduction ·Target Definition ·Linear Regression ·Logistic Regression ·Basic Concepts ·Logistic Regression Properties ·Building a Logistic Regression Scorecard ·Variable Selection for Linear and Logistic Regression ·Decision Trees ·Basic Concepts ·Splitting Decision ·Stopping Decision ·Decision Tree Properties ·Regression Trees ·Using Decision Trees in Fraud Analytics ·Neural Networks ·Basic Concepts ·Weight Learning ·Opening the Neural Network Black Box ·Support Vector Machines ·Linear Programming ·The Linear Separable Case ·The Linear Non separable Case ·The Nonlinear SVM Classifier ·SVMs for Regression ·Opening the SVM Black Box ·Ensemble Methods ·Bagging ·Boosting ·Random Forests ·Evaluating Ensemble Methods ·Multiclass Classification Techniques ·Multiclass Logistic Regression ·Multiclass Decision Trees ·Multiclass Neural Networks ·Multiclass Support Vector Machines ·Evaluating Predictive Models ·Splitting Up the Data Set ·Performance Measures for Classification Models ·Performance Measures for Regression Models ·Other Performance Measures for Predictive Analytical Models ·Developing Predictive Models for Skewed Data Sets ·Varying the Sample Window ·Under sampling and Oversampling ·Synthetic Minority Oversampling Technique (SMOTE) ·Likelihood Approach ·Adjusting Posterior Probabilities ·Cost-sensitive Learning ·Fraud Performance Benchmarks Chapter 5 Social Network Analysis for Fraud Detection ·Networks: Form, Components, Characteristics and Their Applications ·Social Networks ·Network Components ·Network Representation ·Is Fraud a Social Phenomenon? An Introduction to Homophily ·Impact of the Neighborhood: Metrics ·Neighborhood Metrics ·Centrality Metrics ·Collective Inference Algorithms ·Featurization: Summary Overview ·Community Mining: Finding Groups of Fraudsters ·Extending the Graph: Toward a Bipartite Representation ·Multipartite Graphs ·Case Study: Gotcha! Chapter 6 Fraud Analytics: Post-Processing ·Introduction ·The Analytical Fraud Model Life Cycle ·Model Representation ·Traffic Light Indicator Approach ·Decision Tables ·Selecting the Sample to Investigate ·Fraud Alert and Case Management ·Visual Analytics ·Backtesting Analytical Fraud Models ·Introduction ·Backtesting Data Stability ·Backtesting Model Stability ·Backtesting Model Calibration ·Model Design and Documentation Chapter 7 Fraud Analytics: A Broader Perspective ·Introduction ·Data Quality ·Data-Quality Issues ·Data-Quality Programs and Management ·Privacy ·The RACI Matrix ·Accessing Internal Data ·Label-Based Access Control (LBAC) ·Accessing External Data ·Capital Calculation for Fraud Loss ·Expected and Unexpected Losses ·Aggregate Loss Distribution ·Capital Calculation for Fraud Loss Using Monte Carlo Simulation ·An Economic Perspective on Fraud Analytics ·Total Cost of Ownership ·Return on Investment ·In Versus Outsourcing ·Modeling Extensions ·Forecasting ·Text Analytics ·The Internet of Things ·Corporate Fraud Governance References About the Authors Index