Pega 7.1.9 provides several updates to the Decision Management ruleset, including the following updates:

• PMML validation in the Predictive Model rule
• Simulation and testing for the Strategy rule
• Extensions to the Data Flow rule
• New types of data sets

PMML validation in the Predictive Model rule

The Predictive Model rule form provides the XML schema preview for the uploaded PMML models.

The Predictive model tab on the Predictive Model rule form

You can use this preview to view the structure of a model and to correct errors before saving the rule. The uploaded PMML models go through multiple layers of validation:

• XSD validation to check the structure of the XML model
• Functional validation to identify any missing relationships in PMML
• Model validation to check for the supported models

When the model contains errors, error messages are displayed in the Errors section at the bottom of the rule.

Simulation and testing for the Strategy rule

The Strategy tab of the Strategy rule form contains a new Test runs panel from which you test strategies for single and multiple customers and run simulations.

The Strategy tab on the Strategy rule form

You can modify your strategies and test them to make sure that they work as intended. You can run simulations to see how users respond to changes in strategies. Also, when you run a simulation for multiple customers, you can identify the most popular propositions offered to the customers, check the overall strategy performance, and examine the performance of the individual components.

Extensions to the Data Flow rule

Two updates have been made to the Data Flow rule form:

• Data flows can use report definitions as primary and secondary sources. Additionally, such data flows can be distributed on multiple nodes.
• When using a database table data set as the destination of the data flow, you need to select one of the save options for the data set (insert records or insert and update records).

New types of data sets

New types of data sets are required when you create instances of the Free Text Model rule in order to analyze the text-based content on social media. These data sets include:

• Facebook – Required for connecting with the Facebook API
• Twitter – Required for connecting with the Twitter API
• YouTube – Required for connecting with the YouTube Data API