Lift Detail

The Lift Detail Dialog displays statistics for each quantile from 1 to 100. Click OK to dismiss the dialog box.

Threshold probability does not always reflect standard probability. For example, the Classification node enables you to specify three different performance settings:

• Balanced: Apply balance weighting to all target class values.

• Natural: Do not apply any weighting.

• Custom: Apply user- created custom weights file.

The default for Classification models is Balanced. Balanced is implemented by passing weights or costs into the model, depending on the algorithm used.

The threshold probability actually reflects cost rather than standard probability.

To see the difference between Balanced and Natural:

1. Create a Classification model.

2. Select the performance setting options and view the lift details:

   • Natural: The threshold probability values are the greatest probabilities for each quantile.

   • Balanced: The threshold reflects cost. You see the lowest cost value for each quantile.