Customer and Business Analytics: Applied Data Mining for Business Decision Making Using R

by Putler; Daniel S.

• ISBN13: 9781466503960
• ISBN10: 1466503963
• Edition: 1st
• Format: Nonspecific Binding
• Copyright: 2012-05-07
• Publisher: Chapman & Hall

Summary

A practical hands-on guide, this book covers database marketing, surveys, and other data sources for businesses. Each chapter introduces a method or model and ends with a detailed tutorial that guides students through an analysis of a real case. The book takes a data mining approach yet readers are encouraged to consider the substantive business problem rather than taking a purely exploratory approach to customer analytics. The text is suitable for advanced undergraduate or Master's courses on marketing studying customer analytics, data mining for marketing, database marketing, marketing analytics, or business intelligence.

Table of Contents

List of Figures	p. xiii
List of Tables	p. xxi
Preface	p. xxiii
Purpose and Process	p. 1
Database Marketing and Data Mining	p. 3
Database Marketing	p. 4
Common Database Marketing Applications	p. 5
Obstacles to Implementing a Database Marketing Program	p. 8
Who Stands to Benefit the Most from the Use of Database Marketing?	p. 9
Data Mining	p. 9
Two Definitions of Data Mining	p. 9
Classes of Data Mining Methods	p. 10
Grouping Methods	p. 10
Predictive Modeling Methods	p. 11
Linking Methods to Marketing Applications	p. 14
A Process Model for Data Mining-CRISP-DM	p. 17
History and Background	p. 17
The Basic Structure of CRISP-DM	p. 19
CRISP-DM Phases	p. 19
The Process Model within a Phase	p. 21
The CRISP-DM Phases in More Detail	p. 21
Business Understanding	p. 21
Data Understanding	p. 22
Data Preparation	p. 23
Modeling	p. 25
Evaluation	p. 26
Deployment	p. 27
The Typical Allocation of Effort across Project Phases	p. 28
Predictive Modeling Tools	p. 31
Basic Tools for Understanding Data	p. 33
Measurement Scales	p. 34
Software Tools	p. 36
Getting R	p. 37
Installing R on Windows	p. 41
Installing R on OS X	p. 43
Installing the RcmdrPlugin.BCA Package and Its Dependencies	p. 45
Reading Data into R Tutorial	p. 48
Creating Simple Summary Statistics Tutorial	p. 57
Frequency Distributions and Histograms Tutorial	p. 63
Contingency Tables Tutorial	p. 73
Multiple Linear Regression	p. 81
Jargon Clarification	p. 82
Graphical and Algebraic Representation of the Single Predictor Problem	p. 83
The Probability of a Relationship between the Variables	p. 89
Outliers	p. 91
Multiple Regression	p. 91
Categorical Predictors	p. 92
Nonlinear Relationships and Variable Transformations	p. 94
Too Many Predictor Variables: Overfitting and Adjusted R2	p. 97
Summary	p. 98
Data Visualization and Linear Regression Tutorial	p. 99
Logistic Regression	p. 117
A Graphical Illustration of the Problem	p. 118
The Generalized Linear Model	p. 121
Logistic Regression Details	p. 124
Logistic Regression Tutorial	p. 126
Highly Targeted Database Marketing	p. 126
Oversampling	p. 127
Overfitting and Model Validation	p. 128
Lift Charts	p. 147
Constructing Lift Charts	p. 147
Predict, Sort, and Compare to Actual Behavior	p. 147
Correcting Lift Charts for Oversampling	p. 151
Using Lift Charts	p. 154
Lift Chart Tutorial	p. 159
Tree Models	p. 165
The Tree Algorithm	p. 166
Calibrating the Tree on an Estimation Sample	p. 167
Stopping Rules and Controlling Overfitting	p. 170
Trees Models Tutorial	p. 172
Neural Network Models	p. 187
The Biological Inspiration for Artificial Neural Networks	p. 187
Artificial Neural Networks as Predictive Models	p. 192
Neural Network Models Tutorial	p. 194
Putting It All Together	p. 201
Stepwise Variable Selection	p. 201
The Rapid Model Development Framework	p. 204
Up-Selling Using the Wesbrook Database	p. 204
Think about the Behavior That You Are Trying to Predict	p. 205
Carefully Examine the Variables Contained in the Data Set	p. 205
Use Decision Trees and Regression to Find the Important Predictor Variables	p. 207
Use a Neural Network to Examine Whether Nonlinear Relationships Are Present	p. 208
If There Are Nonlinear Relationships, Use Visualization to Find and Understand Them	p. 209
Applying the Rapid Development Framework Tutorial	p. 210
Grouping Methods	p. 233
Ward's Method of Cluster Analysis and Principal Components	p. 235
Summarizing Data Sets	p. 235
Ward's Method of Cluster Analysis	p. 236
A Single Variable Example	p. 238
Extension to Two or More Variables	p. 240
Principal Components	p. 242
Ward's Method Tutorial	p. 248
K-Centroids Partitioning Cluster Analysis	p. 259
How K-Centroid Clustering Works	p. 260
The Basic Algorithm to Find K-Centroids Clusters	p. 260
Specific K-Centroid Clustering Algorithms	p. 261
Cluster Types and the Nature of Customer Segments	p. 264
Methods to Assess Cluster Structure	p. 267
The Adjusted Rand Index to Assess Cluster Structure Reproducibility	p. 268
The Calinski-Harabasz Index to Assess within Cluster Homogeneity and between Cluster Separation	p. 274
K-Centroids Clustering Tutorial	p. 275
Bibliography	p. 283
Index	p. 287
Table of Contents provided by Ingram. All Rights Reserved.