DAT-640: Predictive Analytics

• Data Summarization and Visualization
• Part 1: Summarization 1: Building Blocks Of Data Analysis
• Part 2: Visualization: Graphs and Tables For Summarizing And Organizing Data
• Part 3: Summarization 2: Measures Of Center, Variability, and Position
• Part 4: Summarization And Visualization Of Bivariate Relationships

• The Clustering Task
• Hierarchical Clustering Methods
• Single-Linkage Clustering
• Complete-Linkage Clustering
• k-Means Clustering
• Example of k-Means Clustering at Work
• Behavior of MSB, MSE, and Pseudo-F as the k-Means Algorithm Proceeds
• Application of k-Means Clustering Using SAS Enterprise Miner
• Using Cluster Membership to Predict Churn
• The R Zone
• R References
• Exercises
• Hands-On Analysis

1 LiveLab in this lesson — see the labs panel →

• Rationale for Measuring Cluster Goodness
• The Silhouette Method
• Silhouette Example
• Silhouette Analysis of the IRIS Data Set
• The Pseudo-F Statistic
• Example of the Pseudo-F Statistic
• Pseudo-F Statistic Applied to the IRIS Data Set
• Cluster Validation
• Cluster Validation Applied to the Loans Data Set
• The R Zone
• R References
• Exercises

3 LiveLab in this lesson — see the labs panel →

• What is a Decision Tree?
• Requirements for Using Decision Trees
• Classification and Regression Trees
• C4.5 Algorithm
• Decision Rules
• Comparison of the C5.0 and CART Algorithms Applied to Real Data
• The R Zone
• R References
• Exercises

2 LiveLab in this lesson — see the labs panel →

• Rationale for Using an Ensemble of Classification Models
• Bias, Variance, and Noise
• When to Apply, and not to apply, Bagging
• Bagging
• Boosting
• Application of Bagging and Boosting Using IBM/SPSS Modeler
• References
• The R Zone
• R Reference
• Exercises

2 LiveLab in this lesson — see the labs panel →

• Simple Example of Logistic Regression
• Maximum Likelihood Estimation
• Interpreting Logistic Regression Output
• Inference: Are the Predictors Significant?
• Odds Ratio and Relative Risk
• Interpreting Logistic Regression for a Dichotomous Predictor
• Interpreting Logistic Regression for a Polychotomous Predictor
• Interpreting Logistic Regression for a Continuous Predictor
• Assumption of Linearity
• Zero-Cell Problem
• Multiple Logistic Regression
• Introducing Higher Order Terms to Handle Nonlinearity
• Validating the Logistic Regression Model
• WEKA: Hands-On Analysis Using Logistic Regression
• The R Zone
• R References
• Exercises

4 LiveLab in this lesson — see the labs panel →

• Model Evaluation Techniques for the Description Task
• Model Evaluation Techniques for the Estimation and Prediction Tasks
• Model Evaluation Measures for the Classification Task
• Accuracy and Overall Error Rate
• Sensitivity and Specificity
• False-Positive Rate and False-Negative Rate
• Proportions of True Positives, True Negatives, False Positives, and False Negatives
• Misclassification Cost Adjustment to Reflect Real-World Concerns
• Decision Cost/Benefit Analysis
• Lift Charts and Gains Charts
• Interweaving Model Evaluation with Model Building
• Confluence of Results: Applying a Suite of Models
• The R Zone
• R References
• Exercises
• Hands-On Analysis

2 LiveLab in this lesson — see the labs panel →

• Decision Invariance Under Row Adjustment
• Positive Classification Criterion
• Demonstration Of The Positive Classification Criterion
• Constructing The Cost Matrix
• Decision Invariance Under Scaling
• Direct Costs and Opportunity Costs
• Case Study: Cost-Benefit Analysis Using Data-Driven Misclassification Costs
• Rebalancing as a Surrogate for Misclassification Costs
• The R Zone
• R References
• Exercises

2 LiveLab in this lesson — see the labs panel →