A PMML file cannot be used to create a predictive model
The PMML file that you uploaded contains unsupported features in its model definition.
Cause
This problem occurs when one of the following conditions apply:
- The PMML file does not contain the attribute version for the PMML root element in the model definition. The version is used to determine the schema definition that is required to validate the model source file.
- The PMML file does not have an output. The output can be defined as part of the MiningSchema, Output, or Target element.
- The PMML file has an empty data dictionary.
- The PMML file has mining fields that do not have corresponding data field elements.
- The PMML file has the ampersand character (&) as part of the name or ID of any of the data field elements.
- The PMML file contains the TableLocator element.
Solution
Ask a PMML developer to investigate the error message that indicates the nature of the error and fix the problem. Note that not all PMML model types are supported in the Pega 7 Platform. For more information, see Supported models for import.
Previous topic Troubleshooting decision management components Next topic A strategy uses multiple models with parameterized predictors, but their values are not recorded