Mining Your Own Business in Retail Using DB2 Intelligent Miner for Data

Table of contents

1. Preface
   1. The team that wrote this redbook
   2. Special notice
   3. IBM trademarks
   4. Comments welcome
2. Chapter 1: Introduction
   1. Why you should mine your own business
   2. What are the retail business issues to address?
   3. How this book is structured
   4. Who should read this book?
3. Chapter 2: Business Intelligence architecture overview
   1. Business Intelligence
   2. Data warehouse
      1. Data sources
      2. Extraction/propagation
      3. Transformation/cleansing
      4. Data refining
      5. Datamarts
      6. Metadata
      7. Operational Data Store (ODS)
   3. Analytical users requirements
      1. Reporting and query
      2. On-Line Analytical Processing (OLAP)
      3. Statistics
      4. Data mining
   4. Data warehouse, OLAP and data mining summary
4. Chapter 3: A generic data mining method
   1. What is data mining?
   2. What is new with data mining?
   3. Data mining techniques
      1. Types of techniques
      2. Different applications that data mining can be used for
   4. The generic data mining method
      1. Step 1 — Defining the business issue
      2. Step 2 — Defining a data model to use
      3. Step 3 — Sourcing and preprocessing the data
      4. Step 4 — Evaluating the data model
      5. Step 5 — Choosing the data mining technique
      6. Step 6 — Interpreting the results
      7. Step 7 — Deploying the results
      8. Skills required
      9. Effort required
5. Chapter 4: How can I characterize my customers from the mix of products that they purchase?
   1. The business issue
      1. How can data mining help?
      2. Where should I start?
   2. The data to be used
      1. The types of data that can be used for data mining
      2. Suggested data models
      3. A transaction level aggregation (TLA) data model
   3. Sourcing and preprocessing the data
      1. An example data set (1/2)
      2. An example data set (2/2)
   4. Evaluating the data
      1. Step 1 — Visual inspection
      2. Step 2 — Identifying missing values
      3. Step 3 — Selecting the best variables
   5. The mining technique
      1. Choosing the clustering technique
      2. Applying the mining technique (1/2)
      3. Applying the mining technique (2/2)
   6. Interpreting the results
      1. How to read and interpret the cluster results?
      2. How do we compare different cluster results? (1/2)
      3. How do we compare different cluster results? (2/2)
      4. What does it all mean? — Mapping out your business
   7. Deploying the mining results
      1. Scoring your customers
      2. Using the cluster results to score all your customers
      3. Using the cluster results to score selected customers
6. Chapter 5: How can I categorize my customers and identify new potential customers?
   1. The business issue
      1. Outline of the solution
   2. The data to be used
   3. Sourcing and preprocessing the data
      1. Creating the training and test data sets
   4. Evaluating the data
   5. The mining technique
      1. The classification of mining techniques
      2. Decision tree classifiers (1/2)
      3. Decision tree classifiers (2/2)
      4. Radial Basis Function (RBF) (1/2)
      5. Radial Basis Function (RBF) (2/2)
      6. Making decisions using classifier models
   6. Interpreting the results
      1. Decision tree classifier (using CLA data model)
      2. Decision tree classifier (using TLA model)
      3. Measuring classification performance (gains charts)
      4. RBF results (TLA model)
      5. Comparison of the decision tree and RBF results
   7. Deploying the mining results
      1. Direct mail and targeted marketing campaigns
      2. Point Of Sale and kiosk offers
7. Chapter 6: How can I decide which products to recommend to my customers?
   1. The business issue
      1. What is required?
      2. Outline of the solution
   2. The data to be used
      1. Data model required
   3. Sourcing and preprocessing the data
      1. Additional considerations
      2. The example data set
   4. Evaluating the data
   5. The mining technique
      1. The associations mining technique
      2. Applying the mining technique (1/2)
      3. Applying the mining technique (2/2)
      4. Using the associations results to compute the product records
      5. Generating scores using only the product hierarchy
      6. Generating scores including association rules
      7. Selecting the products to recommend
   6. Interpreting the results
      1. Interpreting the recommendations that were made
   7. Deploying the mining results
      1. The typical deployment scenario
      2. Evaluating customers’ responses to the recommendations
8. Chapter 7: The value of DB2 Intelligent Miner For Data
   1. What benefits does IM for Data offer?
   2. Overview of IM for Data
      1. Data preparation functions
      2. Statistical functions
      3. Mining functions
      4. Creating and visualizing the results
   3. DB2 Intelligent Miner Scoring
9. Related publications
   1. IBM Redbooks
      1. Other resources
   2. Referenced Web sites
   3. How to get IBM Redbooks
      1. IBM Redbooks collections
10. Special notices
11. Glossary
12. Index (1/2)
13. Index (2/2)
14. Back cover