This defines the percentage of available records that are used for training. This value should be set to a number that is greater than 0 but less than 100 (percent).

The random seed represents the starting point that Attribution Modeler uses to select records randomly.

This property specifies the maximum time, in hours, that Attribution Modeler spends training itself. It sets a time limit on the training process as it iterates over the data in an effort to reach the goal set by the converganceThreshold property.This time limit helps administrators limit the resources that Attribution Modeler consumes. The monitoring screen shows a run status of Overrun if SIRA exceeds this training time limit.

If you set this property to 0 (zero), then you are not allowing any changes to the results from one training iteration to the next; this is the most rigorous standard. If you set this property to a value higher than 0, then you are allowing the training results to be more flexible; the standard is less rigorous and training might be completed sooner.