You are previewing Real-time Fraud Detection Analytics on IBM System z.
O'Reilly logo
Real-time Fraud Detection Analytics on IBM System z

Book Description

Payment fraud can be defined as an intentional deception or misrepresentation that is designed to result in an unauthorized benefit. Fraud schemes are becoming more complex and difficult to identify. It is estimated that industries lose nearly $1 trillion USD annually because of fraud. The ideal solution is where you avoid making fraudulent payments without slowing down legitimate payments. This solution requires that you adopt a comprehensive fraud business architecture that applies predictive analytics.

This IBM® Redbooks® publication begins with the business process flows of several industries, such as banking, property/casualty insurance, and tax revenue, where payment fraud is a significant problem. This book then shows how to incorporate technological advancements that help you move from a post-payment to pre-payment fraud detection architecture. Subsequent chapters describe a solution that is specific to the banking industry that can be easily extrapolated to other industries. This book describes the benefits of doing fraud detection on IBM System z®.

This book is intended for financial decisionmakers, consultants, and architects, in addition to IT administrators.

Table of Contents

  1. Front cover
  2. Notices
    1. Trademarks
  3. Preface
    1. The team who wrote this book
    2. Now you can become a published author, too!
    3. Comments welcome
    4. Stay connected to IBM Redbooks
  4. Chapter 1. Introduction
    1. 1.1 Fraud as a cross-industry problem
    2. 1.2 Fraud solutions
      1. 1.2.1 Why fraud detection is difficult
      2. 1.2.2 The new fraud solution
    3. 1.3 Fraud in the health insurance industry
      1. 1.3.1 Detecting suspicious transactions
      2. 1.3.2 Analyzing historical and real-time data
      3. 1.3.3 Integrating fraud detection with case management
      4. 1.3.4 Optimizing software on System z
    4. 1.4 Fraud in property and casualty insurance
      1. 1.4.1 Recognizing suspicious transactions and behaviors
      2. 1.4.2 Analyzing data
      3. 1.4.3 Integrating with case management
      4. 1.4.4 Optimizing System z software
  5. Chapter 2. Solution overview
    1. 2.1 Business need for this solution
    2. 2.2 Fraud detection process flow
    3. 2.3 More benefits
  6. Chapter 3. IBM Scoring Adapter
    1. 3.1 IBM SPSS Modeler Server Scoring Adapter
    2. 3.2 About scoring
    3. 3.3 Scoring adapter for various database products
    4. 3.4 How the DB2 scoring adapter works on z/OS
  7. Chapter 4. Installation and configuration
    1. 4.1 IBM SPSS Modeler Premium 15.0
    2. 4.2 Installing SPSS Modeler Premium 15.0
    3. 4.3 Installing Data Access Pack 6.1
      1. 4.3.1 Deploying Data Access Technology
      2. 4.3.2 ODBC data sources
      3. 4.3.3 Installing
    4. 4.4 Setting up the ODBC connection to host database
    5. 4.5 Configuring the IBM SPSS Modeler Client 15.0
    6. 4.6 Installing the SPSS Modeler Server Scoring Adapter 15 for DB2 for z/OS
    7. 4.7 Configuring the IBM SPSS Modeler 15 Scoring Adapter for DB2 for z/OS
  8. Chapter 5. Building a scenario
    1. 5.1 Overview
    2. 5.2 Understanding and preparing data
    3. 5.3 Training and modeling
      1. 5.3.1 Basics of neural networks
    4. 5.4 Evaluation and deployment
      1. 5.4.1 Publishing an antifraud model to the DB2 scoring adapter on System z
    5. 5.5 Business rules logic program
    6. 5.6 CICS front-end application
  9. Chapter 6. Use case model
    1. 6.1 Use case
    2. 6.2 Setting up the transaction
    3. 6.3 Database design
      1. 6.3.1 Static tables
      2. 6.3.2 Dynamic tables
    4. 6.4 A real-time illustration
      1. 6.4.1 Logging on and installing code in the CICS region
      2. 6.4.2 Starting the transaction
    5. 6.5 Processing flow
  10. Appendix A. Scenario predictors
  11. Appendix B. Transaction processing tables
  12. Related publications
    1. IBM Redbooks
    2. Other publications
    3. Online resources
    4. Help from IBM
  13. Back cover