{"product_id":"applied-predictive-analytics-9781118727966","title":"Applied Predictive Analytics","description":"\u003cb\u003eBook Synopsis\u003c\/b\u003e\u003cbr\u003eWritten by one of the leading experts on predictive analytics,   Applied Predictive Analytics shows tech-savvy business managers and data analysts how to use the sophisticated techniques of predictive analytics that mine Big Data to solve practical business problems.\u003cbr\u003e\u003cbr\u003e\u003cb\u003eTrade Review\u003c\/b\u003e\u003cbr\u003eThis book provides an excellent background to predictive analytics (BCS, December 2014)\u003cbr\u003e\u003cbr\u003e\u003cb\u003eTable of Contents\u003c\/b\u003e\u003cbr\u003eIntroduction xxi  \u003cp\u003e\u003cb\u003eChapter 1 Overview of Predictive Analytics 1\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eWhat Is Analytics? 3\u003c\/p\u003e \u003cp\u003eWhat Is Predictive Analytics? 3\u003c\/p\u003e \u003cp\u003eSupervised vs. Unsupervised Learning 5\u003c\/p\u003e \u003cp\u003eParametric vs. Non-Parametric Models 6\u003c\/p\u003e \u003cp\u003eBusiness Intelligence 6\u003c\/p\u003e \u003cp\u003ePredictive Analytics vs. Business Intelligence 8\u003c\/p\u003e \u003cp\u003eDo Predictive Models Just State the Obvious? 9\u003c\/p\u003e \u003cp\u003eSimilarities between Business Intelligence and Predictive Analytics 9\u003c\/p\u003e \u003cp\u003ePredictive Analytics vs. Statistics 10\u003c\/p\u003e \u003cp\u003eStatistics and Analytics 11\u003c\/p\u003e \u003cp\u003ePredictive Analytics and Statistics Contrasted 12\u003c\/p\u003e \u003cp\u003ePredictive Analytics vs. Data Mining 13\u003c\/p\u003e \u003cp\u003eWho Uses Predictive Analytics? 13\u003c\/p\u003e \u003cp\u003eChallenges in Using Predictive Analytics 14\u003c\/p\u003e \u003cp\u003eObstacles in Management 14\u003c\/p\u003e \u003cp\u003eObstacles with Data 14\u003c\/p\u003e \u003cp\u003eObstacles with Modeling 15\u003c\/p\u003e \u003cp\u003eObstacles in Deployment 16\u003c\/p\u003e \u003cp\u003eWhat Educational Background Is Needed to Become a Predictive Modeler? 16\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 2 Setting Up the Problem 19\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003ePredictive Analytics Processing Steps: CRISP-DM 19\u003c\/p\u003e \u003cp\u003eBusiness Understanding 21\u003c\/p\u003e \u003cp\u003eThe Three-Legged Stool 22\u003c\/p\u003e \u003cp\u003eBusiness Objectives 23\u003c\/p\u003e \u003cp\u003eDefining Data for Predictive Modeling 25\u003c\/p\u003e \u003cp\u003eDefining the Columns as Measures 26\u003c\/p\u003e \u003cp\u003eDefining the Unit of Analysis 27\u003c\/p\u003e \u003cp\u003eWhich Unit of Analysis? 28\u003c\/p\u003e \u003cp\u003eDefining the Target Variable 29\u003c\/p\u003e \u003cp\u003eTemporal Considerations for Target Variable 31\u003c\/p\u003e \u003cp\u003eDefining Measures of Success for Predictive Models 32\u003c\/p\u003e \u003cp\u003eSuccess Criteria for Classifi cation 32\u003c\/p\u003e \u003cp\u003eSuccess Criteria for Estimation 33\u003c\/p\u003e \u003cp\u003eOther Customized Success Criteria 33\u003c\/p\u003e \u003cp\u003eDoing Predictive Modeling Out of Order 34\u003c\/p\u003e \u003cp\u003eBuilding Models First 34\u003c\/p\u003e \u003cp\u003eEarly Model Deployment 35\u003c\/p\u003e \u003cp\u003eCase Study: Recovering Lapsed Donors 35\u003c\/p\u003e \u003cp\u003eOverview 36\u003c\/p\u003e \u003cp\u003eBusiness Objectives 36\u003c\/p\u003e \u003cp\u003eData for the Competition 36\u003c\/p\u003e \u003cp\u003eThe Target Variables 36\u003c\/p\u003e \u003cp\u003eModeling Objectives 37\u003c\/p\u003e \u003cp\u003eModel Selection and Evaluation Criteria 38\u003c\/p\u003e \u003cp\u003eModel Deployment 39\u003c\/p\u003e \u003cp\u003eCase Study: Fraud Detection 39\u003c\/p\u003e \u003cp\u003eOverview 39\u003c\/p\u003e \u003cp\u003eBusiness Objectives 39\u003c\/p\u003e \u003cp\u003eData for the Project 40\u003c\/p\u003e \u003cp\u003eThe Target Variables 40\u003c\/p\u003e \u003cp\u003eModeling Objectives 41\u003c\/p\u003e \u003cp\u003eModel Selection and Evaluation Criteria 41\u003c\/p\u003e \u003cp\u003eModel Deployment 41\u003c\/p\u003e \u003cp\u003eSummary 42\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 3 Data Understanding 43\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eWhat the Data Looks Like 44\u003c\/p\u003e \u003cp\u003eSingle Variable Summaries 44\u003c\/p\u003e \u003cp\u003eMean 45\u003c\/p\u003e \u003cp\u003eStandard Deviation 45\u003c\/p\u003e \u003cp\u003eThe Normal Distribution 45\u003c\/p\u003e \u003cp\u003eUniform Distribution 46\u003c\/p\u003e \u003cp\u003eApplying Simple Statistics in Data Understanding 47\u003c\/p\u003e \u003cp\u003eSkewness 49\u003c\/p\u003e \u003cp\u003eKurtosis 51\u003c\/p\u003e \u003cp\u003eRank-Ordered Statistics 52\u003c\/p\u003e \u003cp\u003eCategorical Variable Assessment 55\u003c\/p\u003e \u003cp\u003eData Visualization in One Dimension 58\u003c\/p\u003e \u003cp\u003eHistograms 59\u003c\/p\u003e \u003cp\u003eMultiple Variable Summaries 64\u003c\/p\u003e \u003cp\u003eHidden Value in Variable Interactions: Simpson’s Paradox 64\u003c\/p\u003e \u003cp\u003eThe Combinatorial Explosion of Interactions 65\u003c\/p\u003e \u003cp\u003eCorrelations 66\u003c\/p\u003e \u003cp\u003eSpurious Correlations 66\u003c\/p\u003e \u003cp\u003eBack to Correlations 67\u003c\/p\u003e \u003cp\u003eCrosstabs 68\u003c\/p\u003e \u003cp\u003eData Visualization, Two or Higher Dimensions 69\u003c\/p\u003e \u003cp\u003eScatterplots 69\u003c\/p\u003e \u003cp\u003eAnscombe’s Quartet 71\u003c\/p\u003e \u003cp\u003eScatterplot Matrices 75\u003c\/p\u003e \u003cp\u003eOverlaying the Target Variable in Summary 76\u003c\/p\u003e \u003cp\u003eScatterplots in More Than Two Dimensions 78\u003c\/p\u003e \u003cp\u003eThe Value of Statistical Signifi cance 80\u003c\/p\u003e \u003cp\u003ePulling It All Together into a Data Audit 81\u003c\/p\u003e \u003cp\u003eSummary 82\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 4 Data Preparation 83\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eVariable Cleaning 84\u003c\/p\u003e \u003cp\u003eIncorrect Values 84\u003c\/p\u003e \u003cp\u003eConsistency in Data Formats 85\u003c\/p\u003e \u003cp\u003eOutliers 85\u003c\/p\u003e \u003cp\u003eMultidimensional Outliers 89\u003c\/p\u003e \u003cp\u003eMissing Values 90\u003c\/p\u003e \u003cp\u003eFixing Missing Data 91\u003c\/p\u003e \u003cp\u003eFeature Creation 98\u003c\/p\u003e \u003cp\u003eSimple Variable Transformations 98\u003c\/p\u003e \u003cp\u003eFixing Skew 99\u003c\/p\u003e \u003cp\u003eBinning Continuous Variables 103\u003c\/p\u003e \u003cp\u003eNumeric Variable Scaling 104\u003c\/p\u003e \u003cp\u003eNominal Variable Transformation 107\u003c\/p\u003e \u003cp\u003eOrdinal Variable Transformations 108\u003c\/p\u003e \u003cp\u003eDate and Time Variable Features 109\u003c\/p\u003e \u003cp\u003eZIP Code Features 110\u003c\/p\u003e \u003cp\u003eWhich Version of a Variable Is Best? 110\u003c\/p\u003e \u003cp\u003eMultidimensional Features 112\u003c\/p\u003e \u003cp\u003eVariable Selection Prior to Modeling 117\u003c\/p\u003e \u003cp\u003eSampling 123\u003c\/p\u003e \u003cp\u003eExample: Why Normalization Matters for K-Means Clustering 139\u003c\/p\u003e \u003cp\u003eSummary 143\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 5 Itemsets and Association Rules 145\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eTerminology 146\u003c\/p\u003e \u003cp\u003eCondition 147\u003c\/p\u003e \u003cp\u003eLeft-Hand-Side, Antecedent(s) 148\u003c\/p\u003e \u003cp\u003eRight-Hand-Side, Consequent, Output, Conclusion 148\u003c\/p\u003e \u003cp\u003eRule (Item Set) 148\u003c\/p\u003e \u003cp\u003eSupport 149\u003c\/p\u003e \u003cp\u003eAntecedent Support 149\u003c\/p\u003e \u003cp\u003eConfi dence, Accuracy 150\u003c\/p\u003e \u003cp\u003eLift 150\u003c\/p\u003e \u003cp\u003eParameter Settings 151\u003c\/p\u003e \u003cp\u003eHow the Data Is Organized 151\u003c\/p\u003e \u003cp\u003eStandard Predictive Modeling Data Format 151\u003c\/p\u003e \u003cp\u003eTransactional Format 152\u003c\/p\u003e \u003cp\u003eMeasures of Interesting Rules 154\u003c\/p\u003e \u003cp\u003eDeploying Association Rules 156\u003c\/p\u003e \u003cp\u003eVariable Selection 157\u003c\/p\u003e \u003cp\u003eInteraction Variable Creation 157\u003c\/p\u003e \u003cp\u003eProblems with Association Rules 158\u003c\/p\u003e \u003cp\u003eRedundant Rules 158\u003c\/p\u003e \u003cp\u003eToo Many Rules 158\u003c\/p\u003e \u003cp\u003eToo Few Rules 159\u003c\/p\u003e \u003cp\u003eBuilding Classification Rules from Association Rules 159\u003c\/p\u003e \u003cp\u003eSummary 161\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 6 Descriptive Modeling 163\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eData Preparation Issues with Descriptive Modeling 164\u003c\/p\u003e \u003cp\u003ePrincipal Component Analysis 165\u003c\/p\u003e \u003cp\u003eThe PCA Algorithm 165\u003c\/p\u003e \u003cp\u003eApplying PCA to New Data 169\u003c\/p\u003e \u003cp\u003ePCA for Data Interpretation 171\u003c\/p\u003e \u003cp\u003eAdditional Considerations before Using PCA 172\u003c\/p\u003e \u003cp\u003eThe Effect of Variable Magnitude on PCA Models 174\u003c\/p\u003e \u003cp\u003eClustering Algorithms 177\u003c\/p\u003e \u003cp\u003eThe K-Means Algorithm 178\u003c\/p\u003e \u003cp\u003eData Preparation for K-Means 183\u003c\/p\u003e \u003cp\u003eSelecting the Number of Clusters 185\u003c\/p\u003e \u003cp\u003eThe Kohonen SOM Algorithm 192\u003c\/p\u003e \u003cp\u003eVisualizing Kohonen Maps 194\u003c\/p\u003e \u003cp\u003eSimilarities with K-Means 196\u003c\/p\u003e \u003cp\u003eSummary 197\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 7 Interpreting Descriptive Models 199\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eStandard Cluster Model Interpretation 199\u003c\/p\u003e \u003cp\u003eProblems with Interpretation Methods 202\u003c\/p\u003e \u003cp\u003eIdentifying Key Variables in Forming Cluster Models 203\u003c\/p\u003e \u003cp\u003eCluster Prototypes 209\u003c\/p\u003e \u003cp\u003eCluster Outliers 210\u003c\/p\u003e \u003cp\u003eSummary 212\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 8 Predictive Modeling 213\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eDecision Trees 214\u003c\/p\u003e \u003cp\u003eThe Decision Tree Landscape 215\u003c\/p\u003e \u003cp\u003eBuilding Decision Trees 218\u003c\/p\u003e \u003cp\u003eDecision Tree Splitting Metrics 221\u003c\/p\u003e \u003cp\u003eDecision Tree Knobs and Options 222\u003c\/p\u003e \u003cp\u003eReweighting Records: Priors 224\u003c\/p\u003e \u003cp\u003eReweighting Records: Misclassifi cation Costs 224\u003c\/p\u003e \u003cp\u003eOther Practical Considerations for Decision Trees 229\u003c\/p\u003e \u003cp\u003eLogistic Regression 230\u003c\/p\u003e \u003cp\u003eInterpreting Logistic Regression Models 233\u003c\/p\u003e \u003cp\u003eOther Practical Considerations for Logistic Regression 235\u003c\/p\u003e \u003cp\u003eNeural Networks 240\u003c\/p\u003e \u003cp\u003eBuilding Blocks: The Neuron 242\u003c\/p\u003e \u003cp\u003eNeural Network Training 244\u003c\/p\u003e \u003cp\u003eThe Flexibility of Neural Networks 247\u003c\/p\u003e \u003cp\u003eNeural Network Settings 249\u003c\/p\u003e \u003cp\u003eNeural Network Pruning 251\u003c\/p\u003e \u003cp\u003eInterpreting Neural Networks 252\u003c\/p\u003e \u003cp\u003eNeural Network Decision Boundaries 253\u003c\/p\u003e \u003cp\u003eOther Practical Considerations for Neural Networks 253\u003c\/p\u003e \u003cp\u003eK-Nearest Neighbor 254\u003c\/p\u003e \u003cp\u003eThe k-NN Learning Algorithm 254\u003c\/p\u003e \u003cp\u003eDistance Metrics for k-NN 258\u003c\/p\u003e \u003cp\u003eOther Practical Considerations for k-NN 259\u003c\/p\u003e \u003cp\u003eNaïve Bayes 264\u003c\/p\u003e \u003cp\u003eBayes’ Theorem 264\u003c\/p\u003e \u003cp\u003eThe Naïve Bayes Classifier 268\u003c\/p\u003e \u003cp\u003eInterpreting Naïve Bayes Classifi ers 268\u003c\/p\u003e \u003cp\u003eOther Practical Considerations for Naïve Bayes 269\u003c\/p\u003e \u003cp\u003eRegression Models 270\u003c\/p\u003e \u003cp\u003eLinear Regression 271\u003c\/p\u003e \u003cp\u003eLinear Regression Assumptions 274\u003c\/p\u003e \u003cp\u003eVariable Selection in Linear Regression 276\u003c\/p\u003e \u003cp\u003eInterpreting Linear Regression Models 278\u003c\/p\u003e \u003cp\u003eUsing Linear Regression for Classification 279\u003c\/p\u003e \u003cp\u003eOther Regression Algorithms 280\u003c\/p\u003e \u003cp\u003eSummary 281\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 9 Assessing Predictive Models 283\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eBatch Approach to Model Assessment 284\u003c\/p\u003e \u003cp\u003ePercent Correct Classifi cation 284\u003c\/p\u003e \u003cp\u003eRank-Ordered Approach to Model Assessment 293\u003c\/p\u003e \u003cp\u003eAssessing Regression Models 301\u003c\/p\u003e \u003cp\u003eSummary 304\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 10 Model Ensembles 307\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eMotivation for Ensembles 307\u003c\/p\u003e \u003cp\u003eThe Wisdom of Crowds 308\u003c\/p\u003e \u003cp\u003eBias Variance Tradeoff 309\u003c\/p\u003e \u003cp\u003eBagging 311\u003c\/p\u003e \u003cp\u003eBoosting 316\u003c\/p\u003e \u003cp\u003eImprovements to Bagging and Boosting 320\u003c\/p\u003e \u003cp\u003eRandom Forests 320\u003c\/p\u003e \u003cp\u003eStochastic Gradient Boosting 321\u003c\/p\u003e \u003cp\u003eHeterogeneous Ensembles 321\u003c\/p\u003e \u003cp\u003eModel Ensembles and Occam’s Razor 323\u003c\/p\u003e \u003cp\u003eInterpreting Model Ensembles 323\u003c\/p\u003e \u003cp\u003eSummary 326\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 11 Text Mining 327\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eMotivation for Text Mining 328\u003c\/p\u003e \u003cp\u003eA Predictive Modeling Approach to Text Mining 329\u003c\/p\u003e \u003cp\u003eStructured vs. Unstructured Data 329\u003c\/p\u003e \u003cp\u003eWhy Text Mining Is Hard 330\u003c\/p\u003e \u003cp\u003eText Mining Applications 332\u003c\/p\u003e \u003cp\u003eData Sources for Text Mining 333\u003c\/p\u003e \u003cp\u003eData Preparation Steps 333\u003c\/p\u003e \u003cp\u003ePOS Tagging 333\u003c\/p\u003e \u003cp\u003eTokens 336\u003c\/p\u003e \u003cp\u003eStop Word and Punctuation Filters 336\u003c\/p\u003e \u003cp\u003eCharacter Length and Number Filters 337\u003c\/p\u003e \u003cp\u003eStemming 337\u003c\/p\u003e \u003cp\u003eDictionaries 338\u003c\/p\u003e \u003cp\u003eThe Sentiment Polarity Movie Data Set 339\u003c\/p\u003e \u003cp\u003eText Mining Features 340\u003c\/p\u003e \u003cp\u003eTerm Frequency 341\u003c\/p\u003e \u003cp\u003eInverse Document Frequency 344\u003c\/p\u003e \u003cp\u003eTF-IDF 344\u003c\/p\u003e \u003cp\u003eCosine Similarity 346\u003c\/p\u003e \u003cp\u003eMulti-Word Features: N-Grams 346\u003c\/p\u003e \u003cp\u003eReducing Keyword Features 347\u003c\/p\u003e \u003cp\u003eGrouping Terms 347\u003c\/p\u003e \u003cp\u003eModeling with Text Mining Features 347\u003c\/p\u003e \u003cp\u003eRegular Expressions 349\u003c\/p\u003e \u003cp\u003eUses of Regular Expressions in Text Mining 351\u003c\/p\u003e \u003cp\u003eSummary 352\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 12 Model Deployment 353\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eGeneral Deployment Considerations 354\u003c\/p\u003e \u003cp\u003eDeployment Steps 355\u003c\/p\u003e \u003cp\u003eSummary 375\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 13 Case Studies 377\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eSurvey Analysis Case Study: Overview 377\u003c\/p\u003e \u003cp\u003eBusiness Understanding: Defining the Problem 378\u003c\/p\u003e \u003cp\u003eData Understanding 380\u003c\/p\u003e \u003cp\u003eData Preparation 381\u003c\/p\u003e \u003cp\u003eModeling 385\u003c\/p\u003e \u003cp\u003eDeployment: “What-If” Analysis 391\u003c\/p\u003e \u003cp\u003eRevisit Models 392\u003c\/p\u003e \u003cp\u003eDeployment 401\u003c\/p\u003e \u003cp\u003eSummary and Conclusions 401\u003c\/p\u003e \u003cp\u003eHelp Desk Case Study 402\u003c\/p\u003e \u003cp\u003eData Understanding: Defining the Data 403\u003c\/p\u003e \u003cp\u003eData Preparation 403\u003c\/p\u003e \u003cp\u003eModeling 405\u003c\/p\u003e \u003cp\u003eRevisit Business Understanding 407\u003c\/p\u003e \u003cp\u003eDeployment 409\u003c\/p\u003e \u003cp\u003eSummary and Conclusions 411\u003c\/p\u003e \u003cp\u003eIndex 413\u003c\/p\u003e","brand":"John Wiley \u0026 Sons Inc","offers":[{"title":"Default Title","offer_id":48866376384855,"sku":"9781118727966","price":37.99,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0817\/1739\/5799\/files\/9781118727966.jpg?v=1722278357","url":"https:\/\/bookcurl.com\/products\/applied-predictive-analytics-9781118727966","provider":"Book Curl","version":"1.0","type":"link"}