Contents. List of Figures List of Tables. Structure of the Book How to Use this Book Online Resources Acknowledgements

Transcription

1 Contents List of Figures List of Tables Preface Notation Structure of the Book How to Use this Book Online Resources Acknowledgements Notational Conventions Notational Conventions for Probabilities xiii xxix xxxvii xxxviii xxxix xl xl xliii xliii xlv 1 Machine Learning for Predictive Data Analytics What Is Predictive Data Analytics? What Is Machine Learning? How Does Machine Learning Work? What Can Go Wrong with Machine Learning? The Predictive Data Analytics Project Lifecycle: CRISP-DM Predictive Data Analytics Tools The Road Ahead Exercises 19 2 Data to Insights to Decisions Converting Business Problems into Analytics Solutions Case Study: Motor Insurance Fraud Assessing Feasibility Case Study: Motor Insurance Fraud Designing the Analytics Base Table Case Study: Motor Insurance Fraud Designing & Implementing Features Different Types of Data Different Types of Features Handling Time Legal Issues Implementing Features Case Study: Motor Insurance Fraud Summary Further Reading Exercises 50

2 viii Contents 3 Data Exploration The Data Quality Report Case Study: Motor Insurance Fraud Getting to Know the Data The Normal Distribution Case Study: Motor Insurance Fraud Identifying Data Quality Issues Missing Values Irregular Cardinality Outliers Case Study: Motor Insurance Fraud Handling Data Quality Issues Handling Missing Values Handling Outliers Case Study: Motor Insurance Fraud Advanced Data Exploration Visualizing Relationships Between Features Measuring Covariance & Correlation Data Preparation Normalization Binning Sampling Summary Further Reading Exercises Information-based Learning Big Idea Fundamentals Decision Trees Shannon s Entropy Model Information Gain Standard Approach: The ID3 Algorithm A Worked Example: Predicting Vegetation Distributions Extensions & Variations Alternative Feature Selection & Impurity Metrics 138

3 Contents ix Handling Continuous Descriptive Features Predicting Continuous Targets Tree Pruning Model Ensembles Summary Further Reading Exercises Similarity-based Learning Big Idea Fundamentals Feature Space Measuring Similarity Using Distance Metrics Standard Approach: The Nearest Neighbor Algorithm A Worked Example Extensions & Variations Handling Noisy Data Efficient Memory Search Data Normalization Predicting Continuous Targets Other Measures of Similarity Feature Selection Summary Further Reading Epilogue Exercises Probability-based Learning Big Idea Fundamentals Bayes Theorem Bayesian Prediction Conditional Independence & Factorization Standard Approach: The Naive Bayes Model A Worked Example Extensions & Variations Smoothing 262

4 x Contents Handling Continuous Features: Probability Density Functions Handling Continuous Features: Binning Bayesian Networks Summary Further Reading Exercises Error-based Learning Big Idea Fundamentals Simple Linear Regression Measuring Error Error Surfaces Standard Approach: Multivariable Linear Regression with Gradient Descent Multivariable Linear Regression Gradient Descent Choosing Learning Rates & Initial Weights A Worked Example Extensions & Variations Interpreting Multivariable Linear Regression Models Setting the Learning Rate Using Weight Decay Handling Categorical Descriptive Features Handling Categorical Target Features: Logistic Regression Modeling Non-linear Relationships Multinomial Logistic Regression Support Vector Machines Summary Further Reading Exercises Evaluation Big Idea Fundamentals Standard Approach: Misclassification Rate on a Hold-out Test Set Extensions & Variations 391

5 Contents xi Designing Evaluation Experiments Performance Measures: Categorical Targets Performance Measures: Prediction Scores Performance Measures: Multinomial Targets Performance Measures: Continuous Targets Evaluating Models after Deployment Summary Further Reading Exercises Case Study: Customer Churn Business Understanding Data Understanding Data Preparation Modeling Evaluation Deployment Case Study: Galaxy Classification Business Understanding Situational Fluency Data Understanding Data Preparation Modeling Baseline Models Feature Selection The 5-level Model Evaluation Deployment The Art of Machine Learning for Predictive Data Analytics Different Perspectives on Prediction Models Choosing a Machine Learning Approach Matching Machine Learning Approaches to Projects Matching Machine Learning Approaches to Data Your Next Steps 509

6 xii Contents A Descriptive Statistics & Data Visualization for Machine Learning 513 A.1 Descriptive Statistics for Continuous Features 513 A.1.1 Central Tendency 513 A.1.2 Variation 515 A.2 Descriptive Statistics for Categorical Features 518 A.3 Populations & Samples 520 A.4 Data Visualization 522 A.4.1 Bar Plots 522 A.4.2 Histograms 523 A.4.3 Box Plots 526 B Introduction to Probability for Machine Learning 529 B.1 Probability Basics 529 B.2 Probability Distributions & Summing Out 534 B.3 Some Useful Probability Rules 536 B.4 Summary 538 C Differentiation Techniques for Machine Learning 539 C.1 Derivatives of Continuous Functions 540 C.2 The Chain Rule 542 C.3 Partial Derivatives 543 Bibliography 545 Index 553