Model Options (neural networks)

Model Name. You can generate the model name automatically based on the target fields or specify a custom name. The automatically generated name is the target field name. If there are multiple targets, then the model name is the field names in order, connected by ampersands. For example, if field1 field2 field3 are targets, then the model name is: field1 & field2 & field3.

Make Available for Scoring. When the model is scored, the selected items in this group should be produced. The predicted value (for all targets) and confidence (for categorical targets) are always computed when the model is scored. The computed confidence can be based on the probability of the predicted value (the highest predicted probability) or the difference between the highest predicted probability and the second highest predicted probability.

• Predicted probability for categorical targets. This produces the predicted probabilities for categorical targets. A field is created for each category.
• Propensity scores for flag targets. For models with a flag target (which return a yes or no prediction), you can request propensity scores that indicate the likelihood of the true outcome specified for the target field. The model produces raw propensity scores; if partitions are in effect, the model also produces adjusted propensity scores based on the testing partition.