Prediction

Prediction operators follow Modeling operators. Each modeling algorithm operator must be assembled with an input data source for analysis and a Prediction operator for running the model against a new source in order to return a predicted dataset.

There are two general types of Prediction operators.

  • Classifier
  • Predictor
Classifier Operators
A Classifier calculates a probability of each possible value for the independent variable as well as the value with the highest probability. In addition, it provides confidence values for the model.

Classifiers are terminal operators within database Workflows (no other operator can follow them).

Predictor Operators

A Predictor calculates the following:

  • For classification algorithms: the value with the highest probability
  • For numeric, regression algorithms: the predicted value

Predictors are not terminal operators within a workflow (other operators can follow them for further analysis of the returned results).