7.00.02 - Random Forest Functions - Aster Analytics

Teradata Aster® Analytics Foundation User GuideUpdate 2

Aster Analytics
Release Number
Release Date
September 2017
Content Type
Programming Reference
User Guide
Publication ID
English (United States)

The random forest functions create a predictive model based on a combination of the Classification and Regression Trees (CART) algorithm for training decision trees and the ensemble learning method of bagging.

The random forest functions are:

  • Forest_Drive, which builds a predictive model based on training data.
  • Forest_Predict, which uses the model generated by the Forest_Drive function to analyze the input data and make predictions.
  • Forest_Analyze, which analyzes the model generated by the Forest_Drive function and gives weights to the variables used in the model. This helps you understand the basis by which the Forest_Predict function makes predictions.

You can use the Forest_Drive and Forest_Predict functions to generate predictions input for the Receiver Operating Characteristic (ROC) function.