Table Of Contents:
FOREWORD xiii(4)
ACKNOWLEDGMENTS xvii(2)
INTRODUCTION xix
Section I DEFINING THE DATA MINING APPROACH 1(74)
Making the Most of Your Resources 1(2)
Data Mining as Problem Solving 3(1)
An Overview of Section I 3(2)

CHAPTER 1 WHAT IS DATA MINING? 5(20)

Data Mining Defined 5(2)

Using Data Mining to Solve Specific Problems 7(5)

Improved Marketing Campaigns 7(1)

Improved Operational Procedures 8(2)

Identifying Fraud 10(1)

Examining Medical Records 11(1)

What Data Mining Is Not 12(3)

Analysis versus Monitoring 12(3)

Avoiding the Oversell 15(9)

Practical Advice before You Begin 16(1)

Justifying the Data Mining Investment 17(2)

Working Efficiently: Timeliness Is a Virtue 19(1)

Establishing the Limitations of Your Data Resources 20(1)

Defining the Problem Up Front 21(1)

Knowing Your Target Audience 21(2)

Anticipating and Overcoming Institutional Inertia 23(1)

Summing Up 24(1)

CHAPTER 2 UNDERSTANDING DATA MODELING 25(30)

Establishing the Goals of the Analysis 26(2)

Conceptualizing the Problem: A Grocery Store Example 27(1)

Object Modeling 28(7)

Assigning Attributes to Objects 29(5)

Modeling Relationships among Object Classes 34(1)

Forming Composite Representations Using Data Abstraction 35(2)

Blending Actual and Abstract Values in Your Model 36(1)

Forming Abstractions Based on Attribute Values 36(1)

Working with Metadata 37(5)

Derving Metadata from Dates 37(5)

Descriptive and Transactional Models 42(8)

Defining Descriptive Data Models 43(1)

Defining Transactional Data Models 43(2)

A Modeling Example: Phone Call Analysis 45(5)

Intra-and Inter-Domain Patterns 50(4)

Discovering Inter-Domain Patterns 52(2)

Summing Up 54(1)

CHAPTER 3 DEFINING THE PROBLEMS TO BE SOLVED 55(20)

Challenging Analysis to Think "Outside the Box" 56(2)

Driving without Maps and Cooking without Recipes 57(1)

There's More than One Way to Slice a Bagel 58(1)

Mapping Your Problem onto a Hierachical Framework 58(2)

From Objects to Networks 58(2)

Applications and Systems 60(1)

Distinguishing between "Knowing How" and "Knowing That": Procedural versus Declarative Knowledge 60(2)

Breaking Declarative Knowledge into Subcategories 61(1)

Distinguishing between Metaknowledge and Actual Knowledge 62(4)

The Information that You Know You Know (YKYK) 62(1)

The Information that You Know You Don't Know (YKDK) 63(2)

The Information that You Know You Don't Know (DKYK) 65(1)

The Information that You Don't Know You Don't Know (DKDK) 65(1)

Distinguishing between Situations and Parameter Values 66(3)

Known Situation and Established Parameter Boundaries 67(1)

Unknown Situation and Established Parameter Boundaries 68(1)

Known Situation and No Established Parameter Boundaries 68(1)

Unknown Situation and No Established Parameter Boundaries 68(1)

Performing Analyses in Reactive and Proactive Modes 69(3)

Performing Reactive Analysis 69(1)

Performing Proactive Analysis 70(1)

Combining Proactive and Reactive Techniques 71(1)

Summary Up 72(3)
Section II DATA PREPARATION AND ANALYSIS 75(122)
Overview of Section II 75(2)
Planning Your Data Mining Engagement 77(2)

CHAPTER 4 ACCESSING AND PREPARING THE DATA 79(44)

Accessing the Data 80(9)

Querying Data Sources 80(4)

Structuring Extractions 84(2)

Transferring Data from Original Sources 86(3)

Integrating the Data 89(12)

Integreating Separate Data Sets: An Example 89(7)

Performing Data Integration across Data Types 96(3)

Moving towards a Single Virtual Representation 99(2)

Converting Data 101(15)

Working with Long and Short Record Structures 101(4)

Data Cleanup 105(1)

Handling Textual Information 116(5)

Natural Language Processing 116(1)

Thematic Summarization of Text 117(4)

Summary Up 121(2)

CHAPTER 5 VISUAL METHODS FOR ANALYZING DATA 123(50)

Dynamic Observation without Preconception 124(1)

Keeping Congnitive Demands in Mind 125(4)

Cognitive Limitations on Information Processing 125(2)

Visualization Capitalizes on Cognitive Strengths 127(2)

Mapping Data onto Visualization Schemes 129(8)

Positioning Algorithms 130(4)

Controlling the Appearance of Objects within the Display 134(2)

Keeping Displays Interpretable 136(1)

Analytical Approaches 137(23)

Analyzing Structural Features 138(4)

Analyzing Network Structures 142(7)

Discovering Emergent Patterns of Connectivity 149(5)

Analyzing Temporal Patterns 154(4)

Visualizing Temporal Patterns 158(2)

Presenting Your Results 160(12)

Keeping the Target Audience in Mind 160(7)

Telling a Story 167(1)

Keeping Displays Understandable 168(1)

Creating Summary Displays 169(2)

Backing Up Conclusions with Documentation 171(1)

Summing Up 172(1)

CHAPTER 6 NONVISUAL ANALYTICAL METHODS 173(24)

Statistical Methods 174(7)

Assessing Group Differences 174(3)

Predictive Regression Analyses 177(1)

When to Use Statistical Analysis 178(3)

Decision Trees 181(5)

Segregating the Data 181(3)

Using Decision Trees to Build Rules 184(1)

Node Splitting and Fan-Out Effects 185(1)

When to Use Decision Trees 186(1)

Association Rules 186(3)

The Cross-Correlation Matrix 187(2)

When to Use Association Rules 189(1)

Neural Networks 189(3)

Supervised Learning 189(1)

Unsupervised Learning 190(1)

When to Use Unsupervised Neural Networks 191(1)

Genetic Algorithms 192(3)

Selection 193(1)

Crossover 193(1)

Mutation 194(1)

When to Use Genetic Algorithms 195(1)

Summing Up 195(2)
Section III ASSESSING DATA MINING TOOLS AND TECHNOLOGIES 197(244)
Assessing Current Data Mining Systems 198(1)
Using the CD-ROM 199(2)

CHAPTER 7 LINK ANALYSIS TOOLS 201(64)

Introduction 201(1)

NETMAP 202(13)

Accessing Data in NETMAP 202(1)

NETMAP's Support Functions 203(1)

The Unconventional Displays of NETMAP 203(9)

The NETMAP Presentations Tool 212(3)

Analyst's Notebook 215(13)

Incorporating Data Sets into Analyst's Notebook 215(1)

Using the Link Notebook 216(6)

Working with the Case Notebook 222(6)

Imagix 4D 228(20)

Importing Data in Imagix 4D 230(2)

Using Imagix 4D "Outside the Box" 232(1)

Working with Data Sources in Imagix 4D 233(4)

Navigating the Imagix 4D Displays 237(1)

Analysing Data Using Imagix 4D 238(8)

Generating Imagix 4D Output 246(1)

Imagix 4D and the Year 2000 247(1)

Daisy 248(9)

Manipulating Your Data in Daisy 249(1)

Information Layout in Daisy 249(2)

Aggregating Data in Daisy 251(2)

Navigating the Daisy Display 253(4)

Other Link Analysis Systems 257(7)

ORION Systems 257(3)

Watson 260(2)

Crime Link 262(2)

Summing Up 264(1)

CHAPTER 8 LANDSCAPE VISUALIZATION TOOLS 265(54)

Introduction 265(1)

MineSet 2.0 265(24)

Operating the Tool Manager and DataMover 267(2)

Interacting with Visual Displays in MineSet 269(4)

Invoking the Scatter Visualizer 273(2)

Working with the Map Visualizer 275(4)

Interacting with the Rules Visualizer 279(2)

Understanding the Rules Visualizer 281(5)

Using the Evidence Visualizer 286(3)

Metaphor Mixer 289(10)

Defining the MM Displays 291(4)

Defining MM Navigation Techniques 295(1)

Working with the Interactive Agent 296(2)

Controlling the Environment 298(1)

Future Directions of MM 299(1)

Visible Decisions In3D 299(6)

Working with In3D 301(1)

Viewing the Data 301(2)

Manipulating In3D Display Characteristics 303(2)

Interacting with In3D 305(1)

Other Landscape Visualization Systems 305(12)

Spotfire 308(2)

Visual Insights 310(2)

AVS/Express 312(4)

IBM Visualization Data Explorer 316(1)

Summing Up 317(2)

CHAPTER 9 QUANTITATIVE DATA MINING TOOLS 319(58)

Introduction 319(1)

Clementine 320(12)

Clementine's Graphical Interface 321(1)

Data Formatting in Clementine 321(2)

Manipulating Data in Clementine 323(2)

Displaying Data in Clementine 325(4)

Modeling Data in Clementine 329(3)

Enterprise Miner 332(11)

Accessing Functions in Enterprise Miner 332(2)

Sampling Your Data in Enterprise Miner 334(2)

Exploratory Analysis Options in Enterprise Miner 336(1)

Modeling Your Data in Enterprise Miner 337(5)

Assessing Results in Enterprise Miner 342(1)

Diamond 343(12)

Formatting and Loading Data in Diamond 344(2)

Manipulating Your Data Set in Diamond 346(1)

Displaying Data in Diamond 347(8)

CrossGraphs 355(18)

Platform Support and Development Environment of CrossGraphs 355(1)

Importing and Processing the Data in CrossGraphs 356(1)

Creating a CrossGraphs Design 357(2)

Presenting Data Using CrossGraphs 359(14)

Other Quantitative Visualization Systems 373(2)

Graf-FX 373(1)

TempleMVV 374(1)

Summing Up 375(2)

CHAPTER 10 FUTURE TRENDS IN VISUAL DATA MINING 377(64)

Introduction 377(2)

Visual Navigation 379(19)

Navigating the Internet 379(1)

Working with File, Network, and Web Visualizers 380(13)

A Different Perspective for Navigating Data 393(5)

Text Visualization 398(8)

Representing Semantic Content in Topographic Maps 398(1)

Using Latent Semantic Analysis in Free Text Processing 399(7)

Full Scope Systems 406(27)

Pathfinder 407(10)

Generic Visualization Architecture (GVA) 417(16)

Other Systems 433(1)

Overlaying Visualization onto Existing Systems 433(5)

Layered Visualization 434(4)

Summing Up 438(3)
Section IV CASE STUDIES 441(146)

CHAPTER 11 MAPPING THE HUMAN GENOME 443(14)

LifeSeq: A Genetic Database 445(4)

Organizing Knowledge in LifeSeq 445(1)

Using LifeSeq to Answer Research Questions 446(1)

Future Uses of the LifeSeq Database 453(2)

Incyte's LifeSeq 3D 449(6)

Protein Function Hierarchy 450(1)

MultiGene Northern Visualization 450(3)

Using LifeSeq 3D for Quality Control 453(2)

Summing Up 455(2)

CHAPTER 12 TELECOMMUNICATION SERVICES 457(20)

The CallPlus Calling System 458(2)

Call Distribution and Queuing 459(1)

Voice Processing 459(1)

Network Processing 459(1)

The NetPlus Calling System 460(4)

CallBack 461(1)

CallThrough 461(1)

Working within the Telecommunications Community 461(1)

Monitoring Operational Problems 462(1)

System Throughput 463(1)

Telecom Information Management 464(1)

The Need for Data Mining 465(1)

Daisy Data Mining 466(9)

System Faults and Capacity 467(4)

Customer Profiles 471(4)

Summing Up 475(2)

CHAPTER 13 BANKING AND FINANCE 477(24)

Technology Assessment Team 478(1)

Fostering Corporate Acceptance of Data Mining 479(2)

Consumer Credit Policy 481(12)

Using a Geographical Landscape Paradigm 482(1)

Predicting Loan Payment Performance 482(5)

Evaluating Correlations a among Customer Variables 487(1)

Industry Classification for Commercial Loans 488(5)

Analyzing Customer Clusters for Targeted Marketing Efforts 493(3)

Data Acquisition and Integration 494(1)

Identifying Customer Clusters 494(1)

Visualizing Customer Clusters 495(1)

A Generic Application 496(3)

Summing Up 499(2)

CHAPTER 14 RETAIL DATA MINING 501(30)

Retail Marketing and Sales Patterns 501(14)

Managing Marketing Saturation of Individual Customers 504(3)

Using Data Mining to Investigate Customer Loyalty 507(1)

Marketing Approaches Based on Life Stages 508(2)

Integrating Customer Data across Business Subunits 510(2)

Using Visualization for Marketing Analyses 512(3)

Videocassette Distribution 515(15)

Using Neural Networks to Segment Data Sets 516(1)

Implementation of Data Visualization in Diamond 517(1)

Evaluating the Success of the Videocassette

Sales Application 528(2)

Summing Up 530(1)

CHAPTER 15 FINANCIAL MARKET DATA MINING 531(20)

Background 531(3)

Portfolio Management Operations 532(2)

Managing Investments in an Unstable Asian Banking Market 534(9)

Managing Declines in the Technical Sector 543(1)

Discovery of Insider Trading Patterns 544(4)

It Pays to Keep Careful Records 548(1)

Summing Up 548(3)

CHAPTER 16 MONEY LAUNDERING AND OTHER FINANCIAL CRIMES 551(36)

Background 551(5)

Financial Reporting Regulations 552(2)

Regulatory Agencies 554(1)

Discovery in Financial Crimes Analysis 555(1)

Analyzing Financial Crime Data 556(13)

Data Preparation 557(6)

Information Analysis 563(4)

Presenting Results 567(2)

Money Laundering Examples 569(15)

Banking Investigations 569(1)

Transferring Funds by Wire 570(1)

Using the Department of Motor Vehicles 571(1)

Working with a Casa de Cambio 571(2)

Working a Real Case 573(11)

Summing Up 584(3)
APPENDIX A TOOL AND TECHNOLOGY RESOURCES 587(8)
WHAT'S ON THE CD-ROM 595(8)
INDEX 603