Enhance your business applications : simple integration of advanced data mining functions / Corinne Baragoin, et al.

Format:

Book

Author/Creator:

Baragoin, Corinne.

Contributor:

International Business Machines Corporation.

Language:

English

Subjects (All):

Data mining.

Business--Data processing.

Business.

IBM Database 2.

Physical Description:

1 online resource (348 p.)

Place of Publication:

[Armonk, N.Y.] : IBM, 2002.

Language Note:

English

Contents:

Front cover

Contents

Figures

Tables

Examples

Notices

Trademarks

Preface

The team that wrote this redbook

Become a published author

Comments welcome

Part 1 Advanced data mining functions overview

Chapter 1. Data mining functions in the database

1.1 The evolution of data mining

1.2 Data mining does not stand alone anymore

1.2.1 Faster time to market and closing the loop

1.2.2 Real-time analytics

1.2.3 Leveraging existing IT skills

1.2.4 Building repeatable processes and tasks

1.2.5 Efficiency and effectiveness

1.2.6 Cost reduction of mining analytics

Chapter 2. Overview of the new data mining functions

2.1 Why relational database management system (RDBMS) functions

2.1.1 Easy use of automation and integration

2.1.2 Operational efficiency

2.1.3 Performance

2.1.4 Administrative efficiency

2.2 Scoring: Deploying data mining models

2.2.1 Scoring as an SQL extension

2.2.2 Batch mode and real time

2.2.3 Support for the new PMML 2.0 standard

2.2.4 Leveraging existing IT skills

2.3 Modeling: Building a mining model using SQL

2.3.1 Interoperability

2.3.2 Models in DB2 UDB

2.3.3 Support of the new PMML 2.0 standard

2.3.4 Required skills

2.4 Visualization: Understanding the data mining model

2.4.1 Interoperability

2.4.2 Choice in use

2.4.3 Multiplatform capability

2.4.4 Support of the new PMML 2.0 standard

2.4.5 Required skills

2.5 IM Modeling, Scoring, and Visualization interactions

2.5.1 The whole picture

2.5.2 Configurations

2.5.3 Positioning with Intelligent Miner for Data

2.6 Conclusion

Chapter 3. Business scenario deployment examples

3.1 Customer profiling

3.1.1 Business benefits

3.2 Fraud detection

3.2.1 Business benefits

3.3 Campaign management

3.3.1 Business benefits.

3.4 Up-to-date promotion

3.4.1 Business benefits

3.5 Integrating the generic components

3.5.1 Generic environment and components

3.5.2 The method

Part 2 Deploying data mining functions

Chapter 4. Customer profiling example

4.1 The business issue

4.2 Mapping the business issue to data mining functions

4.3 The business application

4.4 Environment, components, and implementation flow

4.5 Step-by-step implementation

4.5.1 Configuration

4.5.2 Workbench data mining

4.5.3 Scoring

4.5.4 Application integration

4.6 Benefits

4.6.1 End-to-end implementation

4.6.2 DB2 mining functions next to the workbench

4.6.3 Real-time analytics

4.6.4 Automated and on demand for multi-channels

Chapter 5. Fraud detection example

5.1 The business issue

5.2 Mapping the business issue to data mining functions

5.3 The business application

5.4 Environment, components, and implementation flow

5.5 Data to be used

5.5.1 Data extraction

5.5.2 Data manipulation and enrichment

5.6 Implementation in DB2 UDB V8.1

5.6.1 Enabling database for modeling and scoring

5.6.2 Installing additional UDFs and stored procedures

5.6.3 Model building

5.7 Implementation in DB2 UDB V7.2

5.7.1 Prerequisite: Initial model building

5.7.2 Data settings

5.7.3 Model parameter settings

5.7.4 Building the mining task

5.7.5 Running the model by calling a stored procedure

5.7.6 Scoring script generation

5.7.7 Applying the scoring model

5.7.8 Ranking and listing the five smallest clusters

5.7.9 Actionable result for investigation

5.7.10 Scheduling the job to run at regular intervals

5.8 Benefits

5.8.1 A system that adapts to changes in undesirable behavior

5.8.2 Fast deployment of fraud detection system

5.8.3 Better use of data mining resource.

5.8.4 A repeatable data mining process in a production environment

5.8.5 Enhanced communication

5.8.6 Leveraged IT skills for advanced analytical application

5.8.7 Actionable result

Chapter 6. Campaign management solution examples

6.1 Campaign management overview

6.2 Trigger-based marketing

6.2.1 The business issue

6.2.2 Mapping the business issue to data mining functions

6.2.3 The business application

6.2.4 Environment, components, and implementation flow

6.2.5 Step-by-step implementation

6.2.6 Benefits

6.3 Retention campaign

6.3.1 The business issue

6.3.2 Mapping the business issue to data mining functions

6.3.3 The business application

6.3.4 Environment, components, and implementation flow

6.3.5 Step-by-step implementation

6.3.6 Benefits

6.4 Cross-selling campaign

6.4.1 The business issue

6.4.2 Mapping the business issue to data mining functions

6.4.3 The business application

6.4.4 Environment, components, and implementation flow

6.4.5 Step-by-step implementation

6.4.6 Other considerations

Chapter 7. Up-to-date promotion example

7.1 The business issue

7.2 Mapping the business issue to data mining functions

7.3 The business application

7.4 Environment, components, and implementation flow

7.5 Step-by-step implementation

7.5.1 Configuration

7.5.2 Data model

7.5.3 Modeling

7.5.4 Application integration

7.6 Benefits

7.6.1 Automating models: Easy to use

7.6.2 Calibration: New data = new model

Chapter 8. Other possibilities of integration

8.1 Real-time scoring on the Web (using Web analytics)

8.1.1 The business issue

8.1.2 Mapping the business issue to data mining functions

8.1.3 The business application

8.1.4 Integration with the application example

8.2 Business Intelligence integration.

8.2.1 Integration with DB2 OLAP

8.2.2 Integration with QMF

8.3 Integration with e-commerce

8.4 Integration with WebSphere Personalization

8.5 Integration using Java

8.5.1 Online scoring with IM Scoring Java Beans

8.5.2 Typical business issues

8.5.3 Mapping to mining functions using IM Scoring Java Beans

8.5.4 The business application

8.5.5 Integration with the application example

8.6 Conclusion

Part 3 Configuring the DB2 functions for data mining

Chapter 9. IM Scoring functions for existing mining models

9.1 Scoring functions

9.1.1 Scoring mining models

9.1.2 Scoring results

9.2 IM Scoring configuration steps

9.3 Step-by-step configuration

9.3.1 Configuring the DB2 UDB instance

9.3.2 Configuring the database

9.3.3 Exporting models from the modeling environment

9.3.4 Importing the data mining model in the relational database management system (RDBMS)

9.3.5 Scoring the data

9.3.6 Exploiting the results

9.4 Conclusion

Chapter 10. Building the mining models using IM Modeling functions

10.1 IM Modeling functions

10.2 Data mining process with IM Modeling

10.3 Configuring a database for mining

10.3.1 Enabling the DB2 UDB instance for modeling

10.3.2 Configuring the individual database for modeling

10.3.3 IM Modeling in DB2 UDB V8.1

10.4 Specifying mining data

10.4.1 Defining mining settings

10.4.2 Defining mining tasks

10.4.3 Building and storing mining models

10.4.4 Testing the classification models

10.4.5 Working with mining models and test results

10.5 Hybrid modeling

10.6 Conclusion

Chapter 11. Using IM Visualization functions

11.1 IM Visualization functions

11.1.1 Common and different tasks

11.1.2 Applets or Java API

11.2 Configuration settings

11.2.1 Loading a model from a local file system.

11.2.2 Loading a model from a database

11.3 Using IM Visualizers

11.3.1 Using IM Visualizers as applets

11.3.2 Complete example script

11.4 Examples of IM Visualization

Part 4 Appendixes

Appendix A. SQL script to configure database for data mining function

Appendix B. SQL scripts for the customer profiling scenario

Script to create and load the customer segment table

Script to score new customers

Appendix C. SQL scripts for the fraud detection scenario

Script to prepare the data

Script to build the data mining model

Script to score the data

Script to get the scoring results

Appendix D. SQL scripts for the retention campaign scenario

Script to create a table

Script to import the data mining model with PMML file

Script to create a view of the resulting score

Script to create a table with the resulting score

Appendix E. SQL scripts for the up-to-date promotion scenario

Script for function to build the associations rule model

Script for a function that transforms the resulting rule model

Script to build the rules model

Script to extract rules to a table

Appendix F. UDF to create data mining models

Appendix G. UDF to extract rules from a model to a table

Appendix H. Embedding an IM Visualization applet

Syntax to embed the IM Visualization applet

Parameters to use

Appendix I. IM Scoring Java Bean code example

Source code of IM Scoring Java Bean

Setting up the environment variables: The paths.bat file

Appendix J. Demographic clustering: Technical differences

Appendix K. Additional material

Locating the Web material

Using the Web material

System requirements for downloading the Web material

How to use the Web material

Glossary

Abbreviations and acronyms

Related publications

IBM Redbooks

Other resources

Referenced Web sites.

How to get IBM Redbooks.

Notes:

"December 2002."

"This edition applied to IBM DB2 intelligent miner modeling version 8.1, IBM DB2 intelligent miner scoring version 8.1, and IBM DB2 intelligent miner visualization version 8.1."

Includes bibliographical references and index.

OCLC:

560375972