Tab navigation
- Overview
- Objectives- selected tab,
- Test preparation
Business Understanding (5%)
- Review the CRISP methodology
General Operations in Modeler (20%)
- Build streams
- Run streams
- Read different types of files into Modeler
Data Understanding (30%)
- Extent of missing data
- Outliers
- Field distribution and summary statistics
- Auto checking for missing and out of bounds data
- Bivariate relationships between variables
Data Preparation (40%)
- Create new variables with the Derive Node
- Create new variables with the Reclassify Node
- Combine data files
- Restructure data
- Aggregate data
- Remove duplicates
- Sampling cases
- Balance data
- Data caching
- Partitione data
- Missing Value replacement
Modeling (5%)
- Predictive models
- Cluster models
- Association models
- NOTE: Business partners who take this exam are only expected to familiar with each class of model and the steps that are necessary to prepare the data prior creating the models in the software.
