This two-day course demonstrates how to develop models to predict categorical and continuous outcomes, using such techniques as neural networks, decision trees and logistic regression. Feature selection and detection of outliers are also discussed. Expert options for each modeling node are discussed in detail and advice is provided on when and how to use each model. You will also learn how to combine two or more models to improve prediction.
Prerequisite: General computer literacy. Experience using Clementine, including familiarity with the Clementine environment, creating streams, reading in data files, assessing data quality and handling missing data (including the Type and Data Audit nodes), basic data manipulation (including the Derive and Select nodes), and creation of models. Prior completion of the 'Introduction to Clementine and Data Mining' course or the 'Preparing Data for Data Mining' course is strongly encouraged. An introductory course in statistics, or equivalent experience, would be helpful for the statistics-based modeling techniques.
- Preparing data for modeling
- Neural Networks
- Decision Trees/Rule Induction
- Linear Regression
- Logistic Regression
- Discriminant Analysis
- Data Reduction: Principal Components
- Time Series Analysis
- Decision List
- Finding the Best Model for Binary Outcomes
- Getting the Most from Models
Course Duration: 2 Full Days
Venues: Gauteng and Cape Town
.jpg)