Efnisyfirlit

• Cover
• Half Title
• Title Page
• Copyright Page
• Contents
• List of Figures
• List of Tables
• Preface
• Acknowledgments
• Author
• SECTION I Data Mining Fundamentals
• CHAPTER 1 ■ Data Mining: A First View
• CHAPTER OBJECTIVES
• 1.1 DATA SCIENCE, ANALYTICS, MINING, AND KNOWLEDGE DISCOVERY IN DATABASES
• 1.1.1 Data Science and Analytics
• 1.1.2 Data Mining
• 1.1.3 Data Science versus Knowledge Discovery in Databases
• 1.2 WHAT CAN COMPUTERS LEARN?
• 1.2.1 Three Concept Views
• 1.2.1.1 The Classical View
• 1.2.1.2 The Probabilistic View
• 1.2.1.3 The Exemplar View
• 1.2.2 Supervised Learning
• 1.2.3 Supervised Learning: A Decision Tree Example
• 1.2.4 Unsupervised Clustering
• 1.3 IS DATA MINING APPROPRIATE FOR MY PROBLEM?
• 1.3.1 Data Mining or Data Query?
• 1.3.2 Data Mining versus Data Query: An Example
• 1.4 DATA MINING OR KNOWLEDGE ENGINEERING?
• 1.5 A NEAREST NEIGHBOR APPROACH
• 1.6 A PROCESS MODEL FOR DATA MINING
• 1.6.1 Acquiring Data
• 1.6.1.1 The Data Warehouse
• 1.6.1.2 Relational Databases and Flat Files
• 1.6.1.3 Distributed Data Access
• 1.6.2 Data Preprocessing
• 1.6.3 Mining the Data
• 1.6.4 Interpreting the Results
• 1.6.5 Result Application
• 1.7 DATA MINING, BIG DATA, AND CLOUD COMPUTING
• 1.7.1 Hadoop
• 1.7.2 Cloud Computing
• 1.8 DATA MINING ETHICS
• 1.9 INTRINSIC VALUE AND CUSTOMER CHURN
• 1.10 CHAPTER SUMMARY
• 1.11 KEY TERMS
• CHAPTER 2 ■ Data Mining: A Closer Look
• CHAPTER OBJECTIVES
• 2.1 DATA MINING STRATEGIES
• 2.1.1 Classification
• 2.1.2 Estimation
• 2.1.3 Prediction
• 2.1.4 Unsupervised Clustering
• 2.1.5 Market Basket Analysis
• 2.2 SUPERVISED DATA MINING TECHNIQUES
• 2.2.1 The Credit Card Promotion Database
• 2.2.2 Rule-Based Techniques
• 2.2.3 Neural Networks
• 2.2.4 Statistical Regression
• 2.3 ASSOCIATION RULES
• 2.4 CLUSTERING TECHNIQUES
• 2.5 EVALUATING PERFORMANCE
• 2.5.1 Evaluating Supervised Learner Models
• 2.5.2 Two-Class Error Analysis
• 2.5.3 Evaluating Numeric Output
• 2.5.4 Comparing Models by Measuring Lift
• 2.5.5 Unsupervised Model Evaluation
• 2.6 CHAPTER SUMMARY
• 2.7 KEY TERMS
• CHAPTER 3 ■ Basic Data Mining Techniques
• CHAPTER OBJECTIVES
• 3.1 DECISION TREES
• 3.1.1 An Algorithm for Building Decision Trees
• 3.1.2 Decision Trees for the Credit Card Promotion Database
• 3.1.3 Decision Tree Rules
• 3.1.4 Other Methods for Building Decision Trees
• 3.1.5 General Considerations
• 3.2 A BASIC COVERING RULE ALGORITHM
• 3.3 GENERATING ASSOCIATION RULES
• 3.3.1 Confidence and Support
• 3.3.2 Mining Association Rules: An Example
• 3.3.3 General Considerations
• 3.4 THE K-MEANS ALGORITHM
• 3.4.1 An Example Using K-means
• 3.4.2 General Considerations
• 3.5 GENETIC LEARNING
• 3.5.1 Genetic Algorithms and Supervised Learning
• 3.5.2 General Considerations
• 3.6 CHOOSING A DATA MINING TECHNIQUE
• 3.7 CHAPTER SUMMARY
• 3.8 KEY TERMS
• SECTION II Tools for Knowledge Discovery
• CHAPTER 4 ■ Weka—An Environment for Knowledge Discovery
• CHAPTER OBJECTIVES
• 4.1 GETTING STARTED WITH WEKA
• 4.2 BUILDING DECISION TREES
• 4.3 GENERATING PRODUCTION RULES WITH PART
• 4.4 ATTRIBUTE SELECTION AND NEAREST NEIGHBOR CLASSIFICATION
• 4.5 ASSOCIATION RULES
• 4.6 COST/BENEFIT ANALYSIS, (OPTIONAL)
• 4.7 UNSUPERVISED CLUSTERING WITH THE K-MEANS ALGORITHM
• 4.8 CHAPTER SUMMARY
• CHAPTER 5 ■ Knowledge Discovery with RapidMiner
• CHAPTER OBJECTIVES
• 5.1 GETTING STARTED WITH RAPIDMINER
• 5.1.1 Installing RapidMiner
• 5.1.2 Navigating the Interface
• 5.1.3 A First Process Model
• 5.1.4 A Decision Tree for the Credit Card Promotion Database
• 5.1.5 Breakpoints
• 5.2 BUILDING DECISION TREES
• 5.2.1 Scenario 1: Using a Training and Test Set
• 5.2.2 Scenario 2: Adding a Subprocess
• 5.2.3 Scenario 3: Creating, Saving, and Applying the Final Model
• 5.2.3.1 Saving a Model to an Output File
• 5.2.3.2 Reading and Applying a Model
• 5.2.4 Scenario 4: Using Cross-Validation
• 5.3 GENERATING RULES
• 5.3.1 Scenario 1: Tree to Rules
• 5.3.2 Scenario 2: Rule Induction
• 5.3.3 Scenario 3: Subgroup Discovery
• 5.4 ASSOCIATION RULE LEARNING
• 5.4.1 Association Rules for the Credit Card Promotion Database
• 5.4.2 The Market Basket Analysis Template
• 5.5 UNSUPERVISED CLUSTERING WITH K-MEANS
• 5.6 ATTRIBUTE SELECTION AND NEAREST NEIGHBOR CLASSIFICATION
• 5.7 CHAPTER SUMMARY
• CHAPTER 6 ■ The Knowledge Discovery Process
• CHAPTER OBJECTIVES
• 6.1 A PROCESS MODEL FOR KNOWLEDGE DISCOVERY
• 6.2 GOAL IDENTIFICATION
• 6.3 CREATING A TARGET DATA SET
• 6.4 DATA PREPROCESSING
• 6.4.1 Noisy Data
• 6.4.1.1 Locating Duplicate Records
• 6.4.1.2 Locating Incorrect Attribute Values
• 6.4.1.3 Data Smoothing
• 6.4.1.4 Detecting Outliers
• 6.4.2 Missing Data
• 6.5 DATA TRANSFORMATION
• 6.5.1 Data Normalization
• 6.5.2 Data Type Conversion
• 6.5.3 Attribute and Instance Selection
• 6.5.3.1 Wrapper and Filtering Techniques
• 6.5.3.2 More Attribute Selection Techniques
• 6.5.3.3 Genetic Learning for Attribute Selection
• 6.5.3.4 Creating Attributes
• 6.5.3.5 Instance Selection
• 6.6 DATA MINING
• 6.7 INTERPRETATION AND EVALUATION
• 6.8 TAKING ACTION
• 6.9 THE CRISP-DM PROCESS MODEL
• 6.10 CHAPTER SUMMARY
• 6.11 KEY TERMS
• CHAPTER 7 ■ Formal Evaluation Techniques
• CHAPTER OBJECTIVES
• 7.1 WHAT SHOULD BE EVALUATED?
• 7.2 TOOLS FOR EVALUATION
• 7.2.1 Single-Valued Summary Statistics
• 7.2.2 The Normal Distribution
• 7.2.3 Normal Distributions and Sample Means
• 7.2.4 A Classical Model for Hypothesis Testing
• 7.3 COMPUTING TEST SET CONFIDENCE INTERVALS
• 7.4 COMPARING SUPERVISED LEARNER MODELS
• 7.4.1 Comparing the Performance of Two Models
• 7.4.2 Comparing the Performance of Two or More Models
• 7.5 UNSUPERVISED EVALUATION TECHNIQUES
• 7.5.1 Unsupervised Clustering for Supervised Evaluation
• 7.5.2 Supervised Evaluation for Unsupervised Clustering
• 7.5.3 Additional Methods for Evaluating an Unsupervised Clustering
• 7.6 EVALUATING SUPERVISED MODELS WITH NUMERIC OUTPUT
• 7.7 COMPARING MODELS WITH RAPIDMINER
• 7.8 ATTRIBUTE EVALUATION FOR MIXED DATA TYPES
• 7.9 PARETO LIFT CHARTS
• 7.10 CHAPTER SUMMARY
• 7.11 KEY TERMS
• SECTION III Building Neural Networks
• CHAPTER 8 ■ Neural Networks
• CHAPTER OBJECTIVES
• 8.1 FEED-FORWARD NEURAL NETWORKS
• 8.1.1 Neural Network Input Format
• 8.1.2 Neural Network Output Format
• 8.1.3 The Sigmoid Evaluation Function
• 8.2 NEURAL NETWORK TRAINING: A CONCEPTUAL VIEW
• 8.2.1 Supervised Learning with Feed-Forward Networks
• 8.2.1.1 Training a Neural Network: Backpropagation Learning
• 8.2.1.2 Training a Neural Network: Genetic Learning
• 8.2.2 Unsupervised Clustering with Self-Organizing Maps
• 8.3 NEURAL NETWORK EXPLANATION
• 8.4 GENERAL CONSIDERATIONS
• 8.5 NEURAL NETWORK TRAINING: A DETAILED VIEW
• 8.5.1 The Backpropagation Algorithm: An Example
• 8.5.2 Kohonen Self-Organizing Maps: An Example
• 8.6 CHAPTER SUMMARY
• 8.7 KEY TERMS
• CHAPTER 9 ■ Building Neural Networks with Weka
• CHAPTER OBJECTIVES
• 9.1 DATA SETS FOR BACKPROPAGATION LEARNING
• 9.1.1 The Exclusive-OR Function
• 9.1.2 The Satellite Image Data Set
• 9.2 MODELING THE EXCLUSIVE-OR FUNCTION: NUMERIC OUTPUT
• 9.3 MODELING THE EXCLUSIVE-OR FUNCTION: CATEGORICAL OUTPUT
• 9.4 MINING SATELLITE IMAGE DATA
• 9.5 UNSUPERVISED NEURAL NET CLUSTERING
• 9.6 CHAPTER SUMMARY
• 9.7 KEY TERMS
• CHAPTER 10 ■ Building Neural Networks with RapidMiner
• CHAPTER OBJECTIVES
• 10.1 MODELING THE EXCLUSIVE-OR FUNCTION
• 10.2 MINING SATELLITE IMAGE DATA
• 10.3 PREDICTING CUSTOMER CHURN
• 10.4 RAPIDMINER’S SELF-ORGANIZING MAP OPERATOR
• 10.5 CHAPTER SUMMARY
• SECTION IV Advanced Data Mining Techniques
• CHAPTER 11 ■ Supervised Statistical Techniques
• CHAPTER OBJECTIVES
• 11.1 NAÏVE BAYES CLASSIFIER
• 11.1.1 Naïve Bayes Classifier: An Example
• 11.1.2 Zero-Valued Attribute Counts
• 11.1.3 Missing Data
• 11.1.4 Numeric Data
• 11.1.5 Implementations of the Naïve Bayes Classifier
• 11.1.6 General Considerations
• 11.2 SUPPORT VECTOR MACHINES
• 11.2.1 Linearly Separable Classes
• 11.2.2 The Nonlinear Case
• 11.2.3 General Considerations
• 11.2.4 Implementations of Support Vector Machines
• 11.3 LINEAR REGRESSION ANALYSIS
• 11.3.1 Simple Linear Regression
• 11.3.2 Multiple Linear Regression
• 11.3.2.1 Linear Regression—Weka
• 11.3.2.2 Linear Regression—RapidMiner
• 11.4 REGRESSION TREES
• 11.5 LOGISTIC REGRESSION
• 11.5.1 Transforming the Linear Regression Model
• 11.5.2 The Logistic Regression Model
• 11.6 CHAPTER SUMMARY
• 11.7 KEY TERMS
• CHAPTER 12 ■ Unsupervised Clustering Techniques
• CHAPTER OBJECTIVES
• 12.1 AGGLOMERATIVE CLUSTERING
• 12.1.1 Agglomerative Clustering: An Example
• 12.1.2 General Considerations
• 12.2 CONCEPTUAL CLUSTERING
• 12.2.1 Measuring Category Utility
• 12.2.2 Conceptual Clustering: An Example
• 12.2.3 General Considerations
• 12.3 EXPECTATION MAXIMIZATION
• 12.3.1 Implementations of the EM Algorithm
• 12.3.2 General Considerations
• 12.4 GENETIC ALGORITHMS AND UNSUPERVISED CLUSTERING
• 12.5 CHAPTER SUMMARY
• 12.6 KEY TERMS
• CHAPTER 13 ■ Specialized Techniques
• CHAPTER OBJECTIVES
• 13.1 TIME-SERIES ANALYSIS
• 13.1.1 Stock Market Analytics
• 13.1.2 Time-Series Analysis—An Example
• 13.1.2.1 Creating the Target Data Set—Numeric Output
• 13.1.2.2 Data Preprocessing and Transformation
• 13.1.2.3 Creating the Target Data Set—Categorical Output
• 13.1.2.4 Mining the Data—RapidMiner
• 13.1.2.5 Mining the Data—Weka
• 13.1.2.6 Interpretation, Evaluation, and Action
• 13.1.3 General Considerations
• 13.2 MINING THE WEB
• 13.2.1 Web-Based Mining: General Issues
• 13.2.1.1 Identifying the Goal
• 13.2.2 Preparing the Data
• 13.2.2.1 Mining the Data
• 13.2.2.2 Interpreting and Evaluating Results
• 13.2.2.3 Taking Action
• 13.2.3 Data Mining for Website Evaluation
• 13.2.4 Data Mining for Personalization
• 13.2.5 Data Mining for Website Adaptation
• 13.2.6 PageRank and Link Analysis
• 13.2.7 Operators for Web-Based Mining
• 13.3 MINING TEXTUAL DATA
• 13.3.1 Analyzing Customer Reviews
• 13.4 TECHNIQUES FOR LARGE-SIZED, IMBALANCED, AND STREAMING DATA
• 13.4.1 Large-Sized Data
• 13.4.2 Dealing with Imbalanced Data
• 13.4.2.1 Methods for Addressing Rarity
• 13.4.2.2 Receiver Operating Characteristics Curves
• 13.4.3 Methods for Streaming Data
• 13.5 ENSEMBLE TECHNIQUES FOR IMPROVING PERFORMANCE
• 13.5.1 Bagging
• 13.5.2 Boosting
• 13.5.3 AdaBoost—An Example
• 13.6 CHAPTER SUMMARY
• 13.7 KEY TERMS
• CHAPTER 14 ■ The Data Warehouse
• CHAPTER OBJECTIVES
• 14.1 OPERATIONAL DATABASES
• 14.1.1 Data Modeling and Normalization
• 14.1.2 The Relational Model
• 14.2 DATA WAREHOUSE DESIGN
• 14.2.1 Entering Data into the Warehouse
• 14.2.2 Structuring the Data Warehouse: The Star Schema
• 14.2.2.1 The Multidimensionality of the Star Schema
• 14.2.2.2 Additional Relational Schemas
• 14.2.3 Decision Support: Analyzing the Warehouse Data
• 14.3 ONLINE ANALYTICAL PROCESSING
• 14.3.1 OLAP: An Example
• 14.3.2 General Considerations
• 14.4 EXCEL PIVOT TABLES FOR DATA ANALYTICS
• 14.5 CHAPTER SUMMARY
• 14.6 KEY TERMS
• APPENDIX A—SOFTWARE AND DATA SETS FOR DATA MINING
• APPENDIX B—STATISTICS FOR PERFORMANCE EVALUATION
• BIBLIOGRAPHY
• INDEX