Published Release Notes

Uploading customer responses into adaptive models is no longer available

The option to train adaptive models by uploading a static list of historical interaction records has been deprecated in Pega Platform™ 8.5.

Upgrade impact

In versions of Pega Platform earlier than 8.5, it was possible to train an adaptive model by uploading historical data of customer interaction. After the upgrade to version 8.5, this option is no longer available.

What steps are required to update the application to be compatible with this change?

Use data from a report definition to train adaptive models. For more information, see Training adaptive models.

More flexibility for Date Time predictors in adaptive models

You can configure adaptive model predictors that indicate the amount of time that has elapsed since a particular event. In versions of Pega Platform™ earlier than 8.5, you could only specify the absolute date and time, for example, the date when a subscriber last visited one of your brick-and-mortar store locations. In Pega Platform 8.5, you can also indicate the amount of time that has passed, for example, the number of days since a subscriber purchased a new service plan.

For more information, see Adding a predictor to an adaptive model.

Decision Strategy Manager

Fixes were made that improve the configuration and execution of Batch Decisions. In particular,  the capability to use Structured Data has been enhanced. Some notable improvements have also been made to the UI of Visual Business Director.

• The structured data input configuration will now work even though there is no data.
• VBD has been enhanced to work with Version 7.1.
• The structured data input configuration will now work with nested structures.
• Association rules from Version 6.3 will now work with 7.1 structured data.

Deploy revisions directly in target environments

As a revision manager, you can now directly deploy or migrate completed revisions to multiple Pega 7 Platform environments that were configured as targets by the system architect. The revision management process is faster because you do not need to package a revision as a JAR file, and then manually import that file to the Pega 7 Platform. Additionally, this solution gives business users more control over application rulesets and enables them to act more independently.

For more information, see Direct deployment of revisions.

Delegation experience in revision management

Revision managers can now control rule authoring by assigning a delegation experience to any rule that is part of a revision management change request. Delegation experience types offer different rule authoring capabilities, so the revision manager can select the appropriate delegation experience for the task and the strategy designer’s experience.

File data set

You can now create a File data set that reads data from a file that is in CSV or JSON format. You can use this type of data set to test data flows and strategies.

For more information, see Creating a File data set record.

Analyze intentions in text analytics

You can now analyze text content to determine whether it contains any underlying intention. Through intent analysis, you can determine whether your customers are likely to continue subscribing to your services, want to know more about your products, or whether you are facing customer churn. Based on the detected intentions, you can take appropriate actions to ensure the growth of your business and minimize customer churn. Intent analysis is supported only for the English language.

For more information, see Intent analysis and filtering.

Decision Analytics portal replaces Predictive Analytics Director portal

The Decision Analytics portal replaces the Predictive Analytics Director (PAD) portal, the Text Analytics landing page, and the Adaptive Models Reporting landing page. In this new work area for predictive analytics and text analytics, the business scientist can control the full model life cycle by building predictive models, importing PMML models, building sentiment analysis and text classification models, creating and monitoring adaptive models, and updating any existing models.

For more information, see Overview of the Decision Analytics work area.

Event type browsing on the Customer Movie landing page

Event Browser is a new option on the Customer Movie landing page that provides insight into the history of customer interactions. You can retrieve data from the Event Store data set for a particular customer or a group of customers, display the events in a timeline, and browse a list of event types.

For more information, see Browsing events for a customer or a group of customers.

Select multiple nodes for the Adaptive Decision Manager service

You can select multiple Pega Platform nodes and assign them to the Adaptive Decision Manager (ADM) service as worker nodes. Adaptive learning is no longer restricted to a single server, which provides resilience and scalability. You can add or remove nodes from the ADM service while the system processes customer responses.

For more information, see Changes to Adaptive Decision Manager.