Published Release Notes

Connect to Amazon SageMaker models in Prediction Studio

Make the most of your custom Amazon SageMaker models in Pega Platform™ by connecting to the models in Prediction Studio. You can then run the Amazon SageMaker models as part of your decision strategies.

For more information, see Enrich your decisioning strategies with H2O and Amazon SageMaker predictive models (8.4).

Import H2O models to Prediction Studio

Make the most of your custom H2O models in Pega Platform™ by importing them to Prediction Studio. You can then include the H2O models in your decision strategies.

For more information, see Enrich your decision strategies with H2O and Amazon SageMaker predictive models (8.4).

Support for auditing adaptive model decisions

Pega Platform™ now stores all adaptive model scoring data so that you can identify the source of each decision, such as the exact model version that was used for scoring. With this feature, you can ensure that your application is auditable, transparent, and in compliance with regulatory requirements related to using adaptive models.

For more information, see Configuring the Adaptive Decision Manager service.

Create predictions in Prediction Studio

Predict customer behavior and business events by creating predictions. To create a prediction, you answer a series of questions about what you want to predict. For example, you can create a prediction to determine the likelihood of customer churn.

For more information, see Create predictions in just a few clicks (8.4).

Predictive models monitoring

In Prediction Studio, you can now monitor the predictive performance of your models to validate that they make accurate predictions. Based on that information, you can re-create or adjust the models to provide better business results, such as higher accept rates or decreased customer churn.

For more information, see Monitoring predictive models.

Kafka custom serializer

In Kafka data sets, you can now create and receive messages in your custom formats, as well as in the default JSON format. To use custom logic and formats for serializing and deserializing ClipboardPage objects, create and implement a Java class. When you create a Kafka data set, you can choose to apply JSON or your custom format that uses a PegaSerde implementation.

For more information, see Creating a Kafka data set and Kafka custom serializer/deserialized implementation.

Additional configuration options for File data sets

You can now create File data sets for more advanced scenarios by adding custom Java classes for data encryption and decryption, and by defining a file set in a manifest file.

Additionally, you can improve data management by viewing detailed information in the dedicated meta file for every file that is saved, or by automatically extending the filenames with the creation date and time.

For more information, see Creating a File data set for files on repositories and Requirements for custom stream processing in File data sets.

Simplified testing of event strategies

Evaluate event strategies by creating test runs. During each run, you can enter a number of sample events with simulated property values, such as the event time, the event key, and so on. By testing a strategy against sample data, you can understand the strategy configuration better and troubleshoot potential issues.

For more information, see Evaluate event strategies through test runs.

Data flow life cycle monitoring

You can now generate a report from the Run details section of a Data Flow rule that provides information about run events. The report includes reasons for specific events which you can analyze to troubleshoot and debug issues more quickly. You can export the report and share it with others, such as Global Customer Support.

For more information about accessing event details, see Creating a real-time run for data flows and Creating a batch run for data flows.

Data flow runs retry connections that fail

Real-time and batch data flow runs now retry dataset connections that fail when the related service is temporarily unavailable, for example, when a connection to a Cassandra database times out. With the automatic retries, you no longer need to run data-heavy and CPU-intensive jobs multiple times and the maintenance of data flow runs diminishes significantly.

For more information about accessing event details, see Creating a real-time run for data flows and Creating a batch run for data flows.