DISCOVERING KNOWLEDGE IN DATA
CONTENTS INTRODUCTION TO DATA MINING WHAT IS DATA MINING? WHY DATA MINING? NEED FOR HUMAN DIRECTION OF DATA MINING CROSS-INDUSTRY STANDARD PROCESS: CRISP–DM CASE STUDY 1: ANALYZING AUTOMOBILE WARRANTY CLAIMS: EXAMPLE OF THE CRISP–DM INDUSTRY STANDARD PROCESS IN ACTION FALLACIES OF DATA MINING WHAT TASKS CAN DATA MINING ACCOMPLISH? DESCRIPTION ESTIMATION PREDICTION CLASSI?CATION CLUSTERING ASSOCIATION CASE STUDY 2: PREDICTING ABNORMAL STOCK MARKET RETURNS USING NEURAL NETWORKS CASE STUDY 3: MINING ASSOCIATION RULES FROM LEGAL DATABASES CASE STUDY 4: PREDICTING CORPORATE BANKRUPTCIES USING DECISION TREES CASE STUDY 5: PRO?LING THE TOURISM MARKET USING K-MEANS CLUSTERING ANALYSIS REFERENCES EXERCISES DATA PREPROCESSING WHY DO WE NEED TO PREPROCESS THE DATA? DATA CLEANING HANDLING MISSING DATA IDENTIFYING MISCLASSI?CATIONS GRAPHICAL METHODS FOR IDENTIFYING OUTLIERS DATA TRANSFORMATION MIN–MAX NORMALIZATION Z-SCORE STANDARDIZATION NUMERICAL METHODS FOR IDENTIFYING OUTLIERS EXPLORATORY DATA ANALYSIS HYPOTHESIS TESTING VERSUS EXPLORATORY DATA ANALYSIS GETTING TO KNOW THE DATA SET DEALING WITH CORRELATED VARIABLES EXPLORING CATEGORICAL VARIABLES USING EDA TO UNCOVER ANOMALOUS FIELDS EXPLORING NUMERICAL VARIABLES EXPLORING MULTIVARIATE RELATIONSHIPS SELECTING INTERESTING SUBSETS OF THE DATA FOR FURTHER INVESTIGATION BINNING SUMMARY STATISTICAL APPROACHES TO ESTIMATION AND PREDICTION DATA MINING TASKS IN DISCOVERING KNOWLEDGE IN DATA STATISTICAL APPROACHES TO ESTIMATION AND PREDICTION UNIVARIATE METHODS: MEASURES OF CENTER AND SPREAD STATISTICAL INFERENCE HOW CON?DENT ARE WE IN OUR ESTIMATES? CON?DENCE INTERVAL ESTIMATION BIVARIATE METHODS: SIMPLE LINEAR REGRESSION DANGERS OF EXTRAPOLATION CON?DENCE INTERVALS FOR THE MEAN VALUE OF Y GIVEN X PREDICTION INTERVALS FOR A RANDOMLY CHOSEN VALUE OF Y GIVEN X MULTIPLE REGRESSION VERIFYING MODEL ASSUMPTIONS K-NEAREST NEIGHBOR ALGORITHM SUPERVISED VERSUS UNSUPERVISED METHODS METHODOLOGY FOR SUPERVISED MODELING BIAS–VARIANCE TRADE-OFF CLASSI?CATION TASK K-NEAREST NEIGHBOR ALGORITHM DISTANCE FUNCTION COMBINATION FUNCTION SIMPLE UNWEIGHTED VOTING WEIGHTED VOTING QUANTIFYING ATTRIBUTE RELEVANCE: STRETCHING THE AXES DATABASE CONSIDERATIONS K-NEAREST NEIGHBOR ALGORITHM FOR ESTIMATION AND PREDICTION CHOOSING K REFERENCE DECISION TREES CLASSI?CATION AND REGRESSION TREES C4 5 ALGORITHM DECISION RULES COMPARISON OF THE C5 0 AND CART ALGORITHMS APPLIED TO REAL DATA NEURAL NETWORKS INPUT AND OUTPUT ENCODING NEURAL NETWORKS FOR ESTIMATION AND PREDICTION SIMPLE EXAMPLE OF A NEURAL NETWORK SIGMOID ACTIVATION FUNCTION BACK-PROPAGATION GRADIENT DESCENT METHOD BACK-PROPAGATION RULES EXAMPLE OF BACK-PROPAGATION TERMINATION CRITERIA LEARNING RATE MOMENTUM TERM SENSITIVITY ANALYSIS APPLICATION OF NEURAL NETWORK MODELING HIERARCHICAL AND K-MEANS CLUSTERING CLUSTERING TASK HIERARCHICAL CLUSTERING METHODS SINGLE-LINKAGE CLUSTERING COMPLETE-LINKAGE CLUSTERING K-MEANS CLUSTERING EXAMPLE OF K-MEANS CLUSTERING AT WORK APPLICATION OF K-MEANS CLUSTERING USING SAS ENTERPRISE MINER USING CLUSTER MEMBERSHIP TO PREDICT CHURN KOHONEN NETWORKS SELF-ORGANIZING MAPS KOHONEN NETWORKS EXAMPLE OF A KOHONEN NETWORK STUDY CLUSTER VALIDITY APPLICATION OF CLUSTERING USING KOHONEN NETWORKS INTERPRETING THE CLUSTERS CLUSTER PRO?LES USING CLUSTER MEMBERSHIP AS INPUT TO DOWNSTREAM DATA MINING MODELS ASSOCIATION RULES AF?NITY ANALYSIS AND MARKET BASKET ANALYSIS DATA REPRESENTATION FOR MARKET BASKET ANALYSIS SUPPORT, CON?DENCE, FREQUENT ITEMSETS, AND THE A PRIORI PROPERTY HOW DOES THE A PRIORI ALGORITHM WORK (PART 1)? GENERATING FREQUENT ITEMSETS HOW DOES THE A PRIORI ALGORITHM WORK (PART 2)? GENERATING ASSOCIATION RULES EXTENSION FROM FLAG DATA TO GENERAL CATEGORICAL DATA INFORMATION-THEORETIC APPROACH: GENERALIZED RULE INDUCTION METHOD J-MEASURE APPLICATION OF GENERALIZED RULE INDUCTION WHEN NOT TO USE ASSOCIATION RULES DO ASSOCIATION RULES REPRESENT SUPERVISED OR UNSUPERVISED LEARNING? LOCAL PATTERNS VERSUS GLOBAL MODELS MODEL EVALUATION TECHNIQUES MODEL EVALUATION TECHNIQUES FOR THE DESCRIPTION TASK MODEL EVALUATION TECHNIQUES FOR THE ESTIMATION AND PREDICTION TASKS MODEL EVALUATION TECHNIQUES FOR THE CLASSI?CATION TASK ERROR RATE, FALSE POSITIVES, AND FALSE NEGATIVES MISCLASSI?CATION COST ADJUSTMENT TO RE?ECT REAL-WORLD CONCERNS DECISION COST/BENE?T ANALYSIS LIFT CHARTS AND GAINS CHARTS INTERWEAVING MODEL EVALUATION WITH MODEL BUILDING CON?UENCE OF RESULTS: APPLYING A SUITE OF MODELS EPILOGUE: “WE’VE ONLY JUST BEGUN”