Includes bibliographical references and index.

Bank Fraud; Contents; Preface; Acknowledgments; About the Author; CHAPTER 1 Bank Fraud: Then and Now; THE EVOLUTION OF FRAUD; Fraud in the Present Day; Risk and Reward; Secured Lending versus Unsecured Lending; Statistical Models and the Problem of Prediction; THE EVOLUTION OF FRAUD ANALYSIS; Early Credit Card Fraud; Separating the Wheat from the Chaff; The Advent of Nonlinear Statistical Models; Tackling Fraud with Technology; SUMMARY; CHAPTER 2 Quantifying Fraud: Whose Loss Is It Anyway?; Data Storage and Statistical Thinking; Understanding Non-Fraud Behavior; Quantifying Potential Risk.

Recording the Fraud EpisodeSupervised versus Unsupervised Modeling; The Importance of Accurate Data; FRAUD IN THE CREDIT CARD INDUSTRY; Early Charge and Credit Cards; Lost-and-Stolen Fraud: The Beginnings of Fraud in Credit Cards; Card-Not-Present Fraud and Changes in the Marketplace; THE ADVENT OF BEHAVIORAL MODELS; FRAUD MANAGEMENT: AN EVOLVING CHALLENGE; FRAUD DETECTION ACROSS DOMAINS; USING FRAUD DETECTION EFFECTIVELY; SUMMARY; CHAPTER 3 In God We Trust. The Rest Bring Data!; DATA ANALYSIS AND CAUSAL RELATIONSHIPS; BEHAVIORAL MODELING IN FINANCIAL INSTITUTIONS.

Customer Expectations versus Standards of PrivacyThe Importance of Data in Implementing Good Behavioral Models; SETTING UP A DATA ENVIRONMENT; 1. Know Your Data; 2. Collect All the Data You Can from Day One; 3. Allow for Additions as the Data Grows; 4. If You Cannot Integrate the Data, You Cannot Integrate the Businesses; 5. When You Want to Change the Definition of a Field, It Is Best to Augment and Not Modify; 6. Document the Data You Have as Well as the Data You Lost; 7. When Change Happens, Document It; 8. ETL: "Extract, Translate, Load" (Not "Extract, Taint, Lose").

9. A Data Model Is an Impressionist Painting10. The Top Two Assets of Any Business Today Are People and Data; UNDERSTANDING TEXT DATA; SUMMARY; CHAPTER 4 Tackling Fraud: The Ten Commandments; 1. DATA: GARBAGE IN; GARBAGE OUT; 2. NO DOCUMENTATION? NO CHANGE!; 3. KEY EMPLOYEES ARE NOT A SUBSTITUTE FOR GOOD DOCUMENTATION; 4. RULES: MORE DOESN'T MEAN BETTER; 5. SCORE: NEVER REST ON YOUR LAURELS; 6. SCORE + RULES = WINNING STRATEGY; 7. FRAUD: IT IS EVERYONE'S PROBLEM; 8. CONTINUAL ASSESSMENT IS THE KEY; 9. FRAUD CONTROL SYSTEMS: IF THEY REST, THEY RUST.

10. CONTINUAL IMPROVEMENT: THE CYCLE NEVER ENDSSUMMARY; CHAPTER 5 It Is Not Real Progress Until It Is Operational; THE IMPORTANCE OF PRESENTING A SOLID PICTURE; BUILDING AN EFFECTIVE MODEL; 1. Operations Personnel Need to Understand the Concept of a Fraud Score; 2. The Score Development Process Must Take into Consideration Operational Use and Constraints; 3. In General, Fraud Strategies Should Complement and Not Compete with the Fraud Score; 4. Fraud Strategies and Operational Processes Should Be Well Documented; SUMMARY; CHAPTER 6 The Chain Is Only as Strong as Its Weakest Link.

DISTINCT STAGES OF A DATA-DRIVEN FRAUD MANAGEMENT SYSTEM.

"Capitalize on technology to halt bank fraudExamining the technology that is needed to combat bank fraud, Bank Fraud: Using Technology to Combat Losses equips corporate security and loss prevention managers with the necessary tools to determine an organization's unique technology needs. Looks at the technology needed to handle data intelligence Provides guidance to assess the technology necessary to battle fraud Features unique coverage of the history of fraud detection and prevention in banking Explores the challenges of fraud detection in a financial services environment; understanding corporate risk exposure; losses per assets; trending over time; benefits of technology Focusing on the financial crimes and insider frauds in operation nationally and internationally, Bank Fraud: Using Technology to Combat Losses arms fraud prevention professionals with authoritative guidance to detect and prevent such crimes in future"-- Provided by publisher.

Print version record and CIP data provided by publisher.