Advanced Data Mining Techniques

by Olson, David Louis; Delen, Dursun

• ISBN13: 9783540769163
• ISBN10: 3540769161
• Format: Paperback
• Copyright: 2008-03-04
• Publisher: Springer Verlag

Summary

This book covers the fundamental concepts of data mining, to demonstrate the potential of gathering large sets of data, and analyzing these data sets to gain useful business understanding. The book is organized in three parts. Part I introduces concepts. Part II describes and demonstrates basic data mining algorithms. It also contains chapters on a number of different techniques often used in data mining. Part III focuses on business applications of data mining.

Table of Contents

Introduction
Introduction	p. 3
What is Data Mining?	p. 5
What is Needed to Do Data Mining	p. 5
Business Data Mining	p. 7
Data Mining Tools	p. 8
Summary	p. 8
Data Mining Process	p. 9
CRISP-DM	p. 9
Business Understanding	p. 11
Data Understanding	p. 11
Data Preparation	p. 12
Modeling	p. 15
Evaluation	p. 18
Deployment	p. 18
SEMMA	p. 19
Steps in SEMMA Process	p. 20
Example Data Mining Process Application	p. 22
Comparison of CRISP & SEMMA	p. 27
Handling Data	p. 28
Summary	p. 34
Data Mining Methods as Tools
Memory-Based Reasoning Methods	p. 39
Matching	p. 40
Weighted Matching	p. 43
Distance Minimization	p. 44
Software	p. 50
Summary	p. 50
Job Application Data Set	p. 51
Association Rules in Knowledge Discovery	p. 53
Market-Basket Analysis	p. 55
Market Basket Analysis Benefits	p. 56
Demonstration on Small Set of Data	p. 57
Real Market Basket Data	p. 59
The Counting Method Without Software	p. 62
Conclusions	p. 68
Fuzzy Sets in Data Mining	p. 69
Fuzzy Sets and Decision Trees	p. 71
Fuzzy Sets and Ordinal Classification	p. 75
Fuzzy Association Rules	p. 79
Demonstration Model	p. 80
Computational Results	p. 84
Testing	p. 84
Inferences	p. 85
Conclusions	p. 86
Rough Sets	p. 87
A Brief Theory of Rough Sets	p. 88
Information System	p. 88
Decision Table	p. 89
Some Exemplary Applications of Rough Sets	p. 91
Rough Sets Software Tools	p. 93
The Process of Conducting Rough Sets Analysis	p. 93
Data Pre-Processing	p. 94
Data Partitioning	p. 95
Discretization	p. 95
Reduct Generation	p. 97
Rule Generation and Rule Filtering	p. 99
Apply the Discretization Cuts to Test Dataset	p. 100
Score the Test Dataset on Generated Rule set (and measuring the prediction accuracy)	p. 100
Deploying the Rules in a Production System	p. 102
A Representative Example	p. 103
Conclusion	p. 109
Support Vector Machines	p. 111
Formal Explanation of SVM	p. 112
Primal Form	p. 114
Dual Form	p. 114
Soft Margin	p. 114
Non-linear Classification	p. 115
Regression	p. 116
Implementation	p. 116
Kernel Trick	p. 117
Use of SVM - A Process-Based Approach	p. 118
Support Vector Machines versus Artificial Neural Networks	p. 121
Disadvantages of Support Vector Machines	p. 122
Genetic Algorithm Support to Data Mining	p. 125
Demonstration of Genetic Algorithm	p. 126
Application of Genetic Algorithms in Data Mining	p. 131
Summary	p. 132
Loan Application Data Set	p. 133
Performance Evaluation for Predictive Modeling	p. 137
Performance Metrics for Predictive Modeling	p. 137
Estimation Methodology for Classification Models	p. 140
Simple Split (Holdout)	p. 140
The k-Fold Cross Validation	p. 141
Bootstrapping and Jackknifing	p. 143
Area Under the ROC Curve	p. 144
Summary	p. 147
Applications
Applications of Methods	p. 151
Memory-Based Application	p. 151
Association Rule Application	p. 153
Fuzzy Data Mining	p. 155
Rough Set Models	p. 155
Support Vector Machine Application	p. 157
Genetic Algorithm Applications	p. 158
Japanese Credit Screening	p. 158
Product Quality Testing Design	p. 159
Customer Targeting	p. 159
Medical Analysis	p. 160
Predicting the Financial Success of Hollywood Movies	p. 162
Problem and Data Description	p. 163
Comparative Analysis of the Data Mining Methods	p. 165
Conclusions	p. 167
Bibliography	p. 169
Index	p. 177
Table of Contents provided by Ingram. All Rights Reserved.