Oracle Consulting Oracle Training Oracle Support Development
Home
Catalog
Oracle Books
SQL Server Books
IT Books
Job Interview Books
eBooks
Rampant Horse Books
911 Series
Pedagogue Books

Oracle Software
image
Write for Rampant
Publish with Rampant
Rampant News
Rampant Authors
Rampant Staff
 Phone
 800-766-1884
Oracle News
Oracle Forum
Oracle Tips
Articles by our Authors
Press Releases
SQL Server Books
image
image

Oracle 11g Books

Oracle tuning

Oracle training

Oracle support

Remote Oracle

STATSPACK Viewer

Privacy Policy

  

 

ISBN
0-9744486-3-X
  
ISBN 13
978-0974448633
Library of Congress Number: 2006934081
268 pages
Perfect bind - 9.25x7.5
PD 1207
Shelving: Database/Oracle Oracle In-Focus Series # 25

  Oracle Data Mining
Mining Gold from your Warehouse

Dr. Carolyn K. Hamm      

Retail Price $39.95 /  £29.95 

Key Features About the Authors Table of Contents
Index Topics Reader Comments Errata

- Includes Oracle10g!

Praise from Oracle Corporation:

Dr. Hamm's book, "Oracle Data Mining, Mining Gold from your Warehouse" provides an easy to read, step-by-step, practical guide for learning about data mining using Oracle Data Mining.  It is a must read for anyone looking to harvest insights, predictions and valuable new information from their Oracle data.

Charles Berger
Senior Director of Product Management,
Life & Health Sciences Industries and Data Mining Technologies
Oracle Corporation


Oracle experts know that data mining is one of the most complex and challenging areas of any data warehouse.

In this concise book, Dr. Carolyn Hamm shares the secrets for success in data mining.  Using proven techniques and approaches, Dr. Hamm explains how to perform complex predictive analysis without having a PhD in multivariate statistics.

This indispensable book show how to glean hidden trends and correlations from terabytes of Oracle data, using proven tools such as SAS and ODM.

Targeted at the data warehouse professional, Dr. Hamm explains the complex concepts in plain English and give you a framework to help you get started fast.

Your time savings from a single tip is worth the price of this great book.

 

          
                 
                 Learn
                 expert
             data mining
                secrets!
Key Features

* Learn tricks for creating user-defined cohorts and classifications

* Understand how to use SAS with Oracle data

* See how to create predictive models with Oracle Data Mining (ODM)

* Get examples of Oracle Support Vector Machines (SVM)

* Learn to use ODM for linear regression

* Discover unobtrusive trends with multivariate analysis

* See how the ODM classification model simplifies multivariate analysis

* See Non-negative Matrix Factorization (NMF) for creating attribute sets

About the Author:
 
 
  Dr. Carolyn Hamm
 

Dr. Carolyn Hamm is a recognized expert in Oracle data warehouse technologies, advanced analytics and Oracle data mining.  Dr. Hamm specializes in Oracle Discoverer, Oracle OLAP and Oracle Data Warehouse Builder, and is an expert in multivariate statistics using SAS, SPSS and Clementine. 

Earning her Ph.D. in Experimental Psychology, Dr. Hamm has spent the past 8 years developing web-enabled data systems for population health, accessed by research, clinical and administrative staff.

Table of Contents:

Foreword by Donald K. Burleson  

Oracle Data Mining and Predictive Analytics  

Why this book is important  

 

Chapter 1: Introduction to Model Building  

What is Data Mining?  

Components of Oracle Data Miner  

Sampling Data from the Database  

Concentrating on a customer  

Building a Classification Model  

Naming Data Mining Activities  

Running a Data Mining Activity  

Viewing your Results  

The ODM ROC Curve  

Applying changes to a Model  

Attribute Importance in the Naïve Bayes Model  

Building Naïve Bayes Model with Fewer Attributes  

Applying the Model  

Using the Create View Wizard  

Scoring New Data  

Viewing Top Rankings  

Conclusion  

 

Chapter 2: Adaptive Bayes Network and Decision Trees  

Introduction to Classification  

Data Mining Classification Models  

Using the Models  

Importing a Dataset  

Exploring and Reducing the Dataset  

Viewing Attribute Histograms  

Attribute Importance  

Comparing Naïve Bayes Models for Forest Cover  

Adaptive Bayes Single Feature Model  

Building the Adaptive Bayes Network Model  

Sampling  

Viewing Adaptive Bayes Network Results  

Interpreting Adaptive Bayes Network Results  

Building the Adaptive Bayes Multi Feature Model  

Using the ROC Feature  

Introducing Cost Bias to the Classification Model  

Building a Decision Tree  

The Decision Tree Classification Model  

Decision Tree Classification Rules  

Conclusion  

 

Chapter 3: Using Support Vector Machines  

Introduction to Support Vector Machine  

Inside Support Vector Machines  

Importing the Irish Wind Data File  

Computing a New Attribute with Compute Field Transformation Wizard  

Building the SVM Model  

Handling Outlier Values in SVM Analysis  

Missing Values in SVM Analysis  

Sparse Data in SVM Analysis  

Normalization of SVM Data  

Linear and Gaussian Kernels  

SVM and Over-fitting  

SVM Results with Gaussian Kernel  

Importing Boston House Price Data  

Building SVM Classification Models  

Interpreting the SVM Results  

Refining the SVM Model  

Building a SVM Regression Model  

Regression Model Results  

Linear Regression Analysis  

Drilling into the SVM Data  

Using Text Data in SVM Predictive Models  

Importing CLOB Data  

Loading CLOB Data into the Oracle Database  

Building a SVM Text Model  

Interpreting the SVM text Data  

Conclusion  

Chapter 4: Creating Clusters and Cohorts  

Clustering and Cohorts  

The k-Means Cluster  

Using O-Cluster  

O-Cluster Sensitivity Settings  

Using K-Means for Clustering  

Examining the CoIL Data  

Building a K-Means Cluster  

Finding majority cohort values  

Comparing data sub-sets with K-Means  

Choosing the Appropriate Data Mining Algorithm  

When to use K-Means Analysis  

When to use O-Cluster Analysis  

Applying the Cluster  

Publishing the Cluster Results  

Publishing to a File  

Using the Discoverer Gateway for Publication  

Publishing to an Oracle Database  

Importing the model to a different Oracle database  

Conclusion  

 

Chapter 5: Inside Oracle Data Miner  

Exploring Data Miner  

Data Miner Activity Builder Tasks  

Quantile Binning  

Using the Discretize Transform Wizard  

Customizing Discretize Transformations  

Using the Aggregate Transformation Wizard  

Recode Transformation Wizard  

Using the Split Transformation Wizard  

Using the Stratified Sample Transformation Wizard  

Using the Filter Single-Record Transformation Wizard  

Inside the Sample Transformation Wizard  

Preparing datasets for Data Mining Activities  

Using the Missing Values Transformation Wizard  

Using the Normalize Transformation Wizard  

Using the Numeric Transformation Wizard  

Using the Outlier Treatment Transformation Wizard  

Conclusion  

 

Chapter 6: Predictive Analytics  

Predictive Analytics in Data Mining  

Explain Procedure  

Predict Procedure  

Explain Wizard  

Predict Wizard  

Applying Predictive Analytics  

Conclusion  

 

Chapter 7: Personalized Form Letter Generation with Oracle BI Publisher  

Scenarios for using ODM with BI Publisher  

Building a Decision Tree Model  

Results of the Decision Tree Model  

Scoring the Apply Dataset.  

Using SQL to View Results of Scored Data  

Creating a Report using BI Publisher Enterprise Server  

Using Template Builder for Oracle BI Publisher  

Adding Fields to the Word Template using BI Publisher Template Builder  

Creating a Personalized Customer Letter with Three Offers  

Scenario for Personalizing a Form Letter  

Building a Decision Tree Model using Oracle Data Miner  

Accuracy of the Fund Raiser DT Model  

Results of the Fund Raiser DT Model  

Generating XML Data using BI Publisher  

Creating a Form Letter with the Template Builder  

Conclusion  

Book Conclusion  

 

Appendix A: Installing Oracle Data Miner  

ODM Tutorial  

Purpose  

Time to Complete  

Topics  

Overview  

Prerequisites  

Enabling the DMSYS Account  

Creating and Configuring A Data Mining Account  

Installing Oracle Data Miner  

Summary  

 

Appendix B: Script to Create ODM User  

Scripts

Index Topics:

A

Adaptive Bayes Network

Adaptive Bayes Network Single Feature model

advanced analytics

Advanced Settings Dialog

AFFINITY_CARD

APEX

Apply Data Mining Activity

Apply Data Source

Apply Result

Artificial Intelligence

Attribute Importance feature

average accuracy

B

Build Activity

 

C

Campos

centroid attributes

centroids

Classification Apply Option

Classification function type

classifier

CLOB

Cluster Build Model

Cluster Detail

Clustering Large Databases with Numeric and Nominal Values Using Orthogonal Projections

coefficients

cohorts

COIL

CoIL Challenge

Compute Field

compute wizard

confusion matrix

control files

correlations

COVER_TYPE_IMP

 

D

Data Summarization viewer

Decision Support System

Decision Tree

Discoverer

Discretize

discretizing

disretize

DMUSER

 

E

Economics & Management

End User Layer

ETL

Excel format

F

False Negative

False Positive

favoring

Filter Single-Record Transformation Wizard

 

G

Gartner Group

Gaussian

Generate Default Bins

 

H

Harrison D

histogram

HTML-DB

Hypothesis testing

 

I

importing

J

Java API

 

K

k-Means

 

L

Lift Curve

 

M

Maximum Buffer Size

Milenova

Min/Max

Mining Activity

Mining Activity Build wizard

MINING_DATA_BUILD_V

Missing Values Transformation Wizard

Most Probable

Multivariate statistics

 

N

Naïve Bayes

Naïve Bayes Classification model

New Activity Wizard

normalization

Normalize Transformation Wizard

NOX

Numeric Transformation Wizard

 

O

O-Cluster

ODM models

ODM Navigator

ODMr

Oracle Application Express

Oracle Data Miner Tutorial

Orthogonal Partitioning Clustering

Outlier Treatment Transformation Wizard

overall accuracy

overfitting

P

Predict Wizard

predictive accuracy

Predictive Analytics

Predictive Confidence

 

Q

Quartile Binning

 

R

Receiver Operating Characteristic

Recode the Transformation Wizard

recoding

RMSE

ROC

Root Mean Square Error

Rubinfeld D.L.

Rules tab

 

S

sampling

Sensitivity setting

Show Leaves Only

Show Summary Single Record

skewing

Specific Target Values

Split Transformation Wizard

SQL*Loader

sqlldr

statlib

Stengard

Stratified Sample Transformation Wizard

Support Vector Machine

Support Vector Machines

SVM algorithm

SVM classification

SVM classification model

Syskill Webert Web Data

 

T

TARGET

text attribute

Tolerance value

Top N

total cost

transformations

 

U

Using Data Pump technology

 

V

View Lineage

 

W

Width Binning

Reviews:

Praise from Oracle Corporation:

Dr. Hamm's book, "Oracle Data Mining, Mining Gold from your Warehouse" provides an easy to read, step-by-step, practical guide for learning about data mining using Oracle Data Mining.  It is a must read for anyone looking to harvest insights, predictions and valuable new information from their Oracle data.

Charles Berger
Senior Director of Product Management,
Life & Health Sciences Industries and Data Mining Technologies
Oracle Corporation

 

Errata:

 

 

   

 Copyright © 1996 -2016 by Burleson. All rights reserved.


Oracle® is the registered trademark of Oracle Corporation. SQL Server® is the registered trademark of Microsoft Corporation. 
Many of the designations used by computer vendors to distinguish their products are claimed as Trademarks