Control group configuration for predictions
Valid from Pega Version 8.5
You can now configure a control group for your predictions in Prediction Studio. Based on the control group, Prediction Studio calculates a lift score for each prediction that you can later use to monitor the success rate of your predictions.
For more information, see Customizing predictions.
Decisioning services now use default node classification
Valid from Pega Version 7.4
Decisioning services have been integrated with default node classification on Pega® Platform to provide a unified way of creating and initializing services. As a result of the integration, the Data Flow service has been divided into Batch and Real Time services to better handle different types of data flow runs. You can now specify separate subsets of Data Flow nodes for batch data flow runs and real-time data flow runs to divide the workload between these two subsets.
For more information, see Node classification, Data Flows landing page, and Services landing page.
Aggregate data in interaction history summaries
Valid from Pega Version 7.4
You can now group, aggregate, and filter interaction history data in a single strategy component. By using interaction history summaries, you can create refined data sets that simplify strategy frameworks and accelerate decision-making. Aggregated data sets are easier to process, manage, and troubleshoot.
For more information, see Data Sources landing page
New interaction history attribute
Valid from Pega Version 7.4
Pega® Platform 7.4 introduces the pySubjectType attribute that is used in interaction history aggregations. This attribute is populated for interaction history records that were created in release 7.4. For records that originated in earlier releases, the attribute must be set in the following scenarios:
- Single-level decisioning frameworks that use interaction history.
- Multi-level decisioning frameworks where interaction history is used by two or more levels of strategies that are defined on different classes.
For the single-level scenario, configure the Dynamic System Setting that sets the pySubjectType attribute when your framework reads interaction history records. The value of this Dynamic System Setting becomes the name of the customer class.
For the multi-level scenario, update the database table for all strategy levels manually. For each level, make sure that the value in the Subject Type column is set to the name of the class for the corresponding strategy. For example, the value for the top level strategy should be set to the name of the class of that strategy.
For more information about interaction history aggregations, see Data Sources landing page
For more information about multi-line strategies and contexts, see Strategy components - Embedded strategy
Response timeout configuration for predictions
Valid from Pega Version 8.5
You can now set a response timeout for your predictions in Prediction Studio. By setting a response timeout, you control how Prediction Studio registers customer responses that later serve as feedback data for your predictions.
For more information, see Customizing predictions.
Label changes for text analytic models
Valid from Pega Version 7.4
The classification analysis label has changed to topic detection and the entity extraction label has changed to text extraction. Also, the sentiment analysis, topic detection, and intent detection labels are now located under Text Categorization in the Analytics Center. These name changes reflect industry standards and provide a clearer distinction between different types of text analytics models in Pega® Platform.
For more information, see Text analytics models.