Advanced Predictive Modeling Using IBM SPSS Modeler v18.1.1 0A038G

• Preparing data for modeling
• Reducing data with PCA/Factor
• Exploring advanced supervised models
• Combining models
• Finding the best supervised model

1: Preparing data for modeling

• Address general data quality issues

• Handle anomalies

• Select important predictors

• Partition the data to better evaluate models

Balance the data to build better models

• 2: Reducing data with PCA/Factor

• Explain the idea behind PCA/Factor

• Determine the number of components/factors

Explain the principle of rotating a solution

• 4: Exploring advanced supervised models

• Explain the principles of Support Vector Machine (SVM)

• Explain the principles of Random Trees

Explain the principles of XGBoost

• 5: Combining models

• Use the Ensemble node to combine model predictions

Improve model performance by meta-level modeling

• 6: Finding the best supervised model

• Use the Auto Classifier node to find the best model for categorical targets

Use the Auto Numeric node to find the best model for continuous targets