Available:*
Library | Item Barcode | Call Number | Material Type | Item Category 1 | Status |
---|---|---|---|---|---|
Searching... | 30000010141222 | HF5548.2 S554 2007 | Open Access Book | Book | Searching... |
On Order
Summary
Summary
Learn how to develop models for classification, prediction, and customer segmentation with the help of Data Mining for Business Intelligence
In today's world, businesses are becoming more capable of accessing their ideal consumers, and an understanding of data mining contributes to this success. Data Mining for Business Intelligence , which was developed from a course taught at the Massachusetts Institute of Technology's Sloan School of Management, and the University of Maryland's Smith School of Business, uses real data and actual cases to illustrate the applicability of data mining intelligence to the development of successful business models.
Featuring XLMiner, the Microsoft Office Excel add-in, this book allows readers to follow along and implement algorithms at their own speed, with a minimal learning curve. In addition, students and practitioners of data mining techniques are presented with hands-on, business-oriented applications. An abundant amount of exercises and examples are provided to motivate learning and understanding.
Data Mining for Business Intelligence:
Provides both a theoretical and practical understanding of the key methods of classification, prediction, reduction, exploration, and affinity analysis Features a business decision-making context for these key methods Illustrates the application and interpretation of these methods using real business cases and dataThis book helps readers understand the beneficial relationship that can be established between data mining and smart business practices, and is an excellent learning tool for creating valuable strategies and making wiser business decisions.
Author Notes
Galit Shmueli, PhD, is Assistant Professor of Statistics in the Decision and Information Technologies Department of the Robert H. Smith School of Business at the University of Maryland
Nitin R. Patel, PhD, is Chairman, Founder, and Chief Technology Officer of Cambridge-based Cytel Incorporated and a Visiting Professor in the Engineering Systems Division at the Massachusetts Institute of Technology
Table of Contents
Foreword | p. xiii |
Preface | p. xv |
Acknowledgments | p. xvii |
1 Introduction | p. 1 |
1.1 What Is Data Mining? | p. 1 |
1.2 Where Is Data Mining Used? | p. 2 |
1.3 The Origins of Data Mining | p. 2 |
1.4 The Rapid Growth of Data Mining | p. 3 |
1.5 Why Are There So Many Different Methods? | p. 4 |
1.6 Terminology and Notation | p. 4 |
1.7 Road Maps to This Book | p. 6 |
2 Overview of the Data Mining Process | p. 9 |
2.1 Introduction | p. 9 |
2.2 Core Ideas in Data Mining | p. 9 |
2.3 Supervised and Unsupervised Learning | p. 11 |
2.4 The Steps in Data Mining | p. 11 |
2.5 Preliminary Steps | p. 13 |
2.6 Building a Model: Example with Linear Regression | p. 21 |
2.7 Using Excel for Data Mining | p. 27 |
Problems | p. 31 |
3 Data Exploration and Dimension Reduction | p. 35 |
3.1 Introduction | p. 35 |
3.2 Practical Considerations | p. 35 |
Example 1 House Prices in Boston | p. 36 |
3.3 Data Summaries | p. 37 |
3.4 Data Visualization | p. 38 |
3.5 Correlation Analysis | p. 40 |
3.6 Reducing the Number of Categories in Categorical Variables | p. 41 |
3.7 Principal Components Analysis | p. 41 |
Example 2 Breakfast Cereals | p. 42 |
Principal Components | p. 45 |
Normalizing the Data | p. 46 |
Using Principal Components for Classification and Prediction | p. 49 |
Problems | p. 51 |
4 Evaluating Classification and Predictive Performance | p. 53 |
4.1 Introduction | p. 53 |
4.2 Judging Classification Performance | p. 53 |
Accuracy Measures | p. 53 |
Cutoff for Classification | p. 56 |
Performance in Unequal Importance of Classes | p. 60 |
Asymmetric Misclassification Costs | p. 61 |
Oversampling and Asymmetric Costs | p. 66 |
Classification Using a Triage Strategy | p. 72 |
4.3 Evaluating Predictive Performance | p. 72 |
Problems | p. 74 |
5 Multiple Linear Regression | p. 75 |
5.1 Introduction | p. 75 |
5.2 Explanatory vs. Predictive Modeling | p. 76 |
5.3 Estimating the Regression Equation and Prediction | p. 76 |
Example: Predicting the Price of Used Toyota Corolla Automobiles | p. 77 |
5.4 Variable Selection in Linear Regression | p. 81 |
Reducing the Number of Predictors | p. 81 |
How to Reduce the Number of Predictors | p. 82 |
Problems | p. 86 |
6 Three Simple Classification Methods | p. 91 |
6.1 Introduction | p. 91 |
Example 1 Predicting Fraudulent Financial Reporting | p. 91 |
Example 2 Predicting Delayed Flights | p. 92 |
6.2 The Naive Rule | p. 92 |
6.3 Naive Bayes | p. 93 |
Conditional Probabilities and Pivot Tables | p. 94 |
A Practical Difficulty | p. 94 |
A Solution: Naive Bayes | p. 95 |
Advantages and Shortcomings of the naive Bayes Classifier | p. 100 |
6.4 k-Nearest Neighbors | p. 103 |
Example 3 Riding Mowers | p. 104 |
Choosing k | p. 105 |
k-NN for a Quantitative Response | p. 106 |
Advantages and Shortcomings of k-NN Algorithms | p. 106 |
Problems | p. 108 |
7 Classification and Regression Trees | p. 111 |
7.1 Introduction | p. 111 |
7.2 Classification Trees | p. 113 |
7.3 Recursive Partitioning | p. 113 |
7.4 Example 1: Riding Mowers | p. 113 |
Measures of Impurity | p. 115 |
7.5 Evaluating the Performance of a Classification Tree | p. 120 |
Example 2 Acceptance of Personal Loan | p. 120 |
7.6 Avoiding Overfitting | p. 121 |
Stopping Tree Growth: CHAID | p. 121 |
Pruning the Tree | p. 125 |
7.7 Classification Rules from Trees | p. 130 |
7.8 Regression Trees | p. 130 |
Prediction | p. 130 |
Measuring Impurity | p. 131 |
Evaluating Performance | p. 132 |
7.9 Advantages, Weaknesses, and Extensions | p. 132 |
Problems | p. 134 |
8 Logistic Regression | p. 137 |
8.1 Introduction | p. 137 |
8.2 The Logistic Regression Model | p. 138 |
Example: Acceptance of Personal Loan | p. 139 |
Model with a Single Predictor | p. 141 |
Estimating the Logistic Model from Data: Computing Parameter Estimates | p. 143 |
Interpreting Results in Terms of Odds | p. 144 |
8.3 Why Linear Regression Is Inappropriate for a Categorical Response | p. 146 |
8.4 Evaluating Classification Performance | p. 148 |
Variable Selection | p. 148 |
8.5 Evaluating Goodness of Fit | p. 150 |
8.6 Example of Complete Analysis: Predicting Delayed Flights | p. 153 |
Data Preprocessing | p. 154 |
Model Fitting and Estimation | p. 155 |
Model Interpretation | p. 155 |
Model Performance | p. 155 |
Goodness of fit | p. 157 |
Variable Selection | p. 158 |
8.7 Logistic Regression for More Than Two Classes | p. 160 |
Ordinal Classes | p. 160 |
Nominal Classes | p. 161 |
Problems | p. 163 |
9 Neural Nets | p. 167 |
9.1 Introduction | p. 167 |
9.2 Concept and Structure of a Neural Network | p. 168 |
9.3 Fitting a Network to Data | p. 168 |
Example 1 Tiny Dataset | p. 169 |
Computing Output of Nodes | p. 170 |
Preprocessing the Data | p. 172 |
Training the Model | p. 172 |
Example 2 Classifying Accident Severity | p. 176 |
Avoiding overfitting | p. 177 |
Using the Output for Prediction and Classification | p. 181 |
9.4 Required User Input | p. 181 |
9.5 Exploring the Relationship Between Predictors and Response | p. 182 |
9.6 Advantages and Weaknesses of Neural Networks | p. 182 |
Problems | p. 184 |
10 Discriminant Analysis | p. 187 |
10.1 Introduction | p. 187 |
10.2 Example 1: Riding Mowers | p. 187 |
10.3 Example 2: Personal Loan Acceptance | p. 188 |
10.4 Distance of an Observation from a Class | p. 188 |
10.5 Fisher's Linear Classification Functions | p. 191 |
10.6 Classification Performance of Discriminant Analysis | p. 194 |
10.7 Prior Probabilities | p. 195 |
10.8 Unequal Misclassification Costs | p. 195 |
10.9 Classifying More Than Two Classes | p. 196 |
Example 3 Medical Dispatch to Accident Scenes | p. 196 |
10.10 Advantages and Weaknesses | p. 197 |
Problems | p. 200 |
11 Association Rules | p. 203 |
11.1 Introduction | p. 203 |
11.2 Discovering Association Rules in Transaction Databases | p. 203 |
11.3 Example 1: Synthetic Data on Purchases of Phone Faceplates | p. 204 |
11.4 Generating Candidate Rules | p. 204 |
The Apriori Algorithm | p. 205 |
11.5 Selecting Strong Rules | p. 206 |
Support and Confidence | p. 206 |
Lift Ratio | p. 207 |
Data Format | p. 207 |
The Process of Rule Selection | p. 209 |
Interpreting the Results | p. 210 |
Statistical Significance of Rules | p. 211 |
11.6 Example 2: Rules for Similar Book Purchases | p. 212 |
11.7 Summary | p. 212 |
Problems | p. 215 |
12 Cluster Analysis | p. 219 |
12.1 Introduction | p. 219 |
12.2 Example: Public Utilities | p. 220 |
12.3 Measuring Distance Between Two Records | p. 222 |
Euclidean Distance | p. 223 |
Normalizing Numerical Measurements | p. 223 |
Other Distance Measures for Numerical Data | p. 223 |
Distance Measures for Categorical Data | p. 226 |
Distance Measures for Mixed Data | p. 226 |
12.4 Measuring Distance Between Two Clusters | p. 227 |
12.5 Hierarchical (Agglomerative) Clustering | p. 228 |
Minimum Distance (Single Linkage) | p. 229 |
Maximum Distance (Complete Linkage) | p. 229 |
Group Average (Average Linkage) | p. 230 |
Dendrograms: Displaying Clustering Process and Results | p. 230 |
Validating Clusters | p. 231 |
Limitations of Hierarchical Clustering | p. 232 |
12.6 Nonhierarchical Clustering: The k-Means Algorithm | p. 233 |
Initial Partition into k Clusters | p. 234 |
Problems | p. 237 |
13 Cases | p. 241 |
13.1 Charles Book Club | p. 241 |
13.2 German Credit | p. 250 |
13.3 Tayko Software Cataloger | p. 254 |
13.4 Segmenting Consumers of Bath Soap | p. 258 |
13.5 Direct-Mail Fundraising | p. 262 |
13.6 Catalog Cross-Selling | p. 265 |
13.7 Predicting Bankruptcy | p. 267 |
References | p. 271 |
Index | p. 273 |