Support for predictive models in PMML version 4.4
Valid from Pega Version 8.5
Pega Platform™ now supports the import of predictive models in Predictive Model Markup Language (PMML) version 4.4. With this feature, you can import PMML models that use the anomaly detection algorithm.
For a list of all supported PMML models, see Supported models for import.
Support for Apache HBase 2.1 and Hadoop 3.0
Valid from Pega Version 8.5
Support for these versions extends Pega Platform™ compatibility with HBase releases to ensure that your database implementations integrate seamlessly with Pega Platform.
Pega Platform now supports:
- Apache HBase 2.1 for the HBase data set
- Apache Hadoop Distributed File System (HDFS) 3.0 for the HDFS data set
For more information, see Enhance your data sets with Apache HBase 2.1 and Hadoop 3.0 (8.5).
Enhancing your revision management process with Deployment Manager pipelines
Valid from Pega Version 8.5
Pega Platform 8.5 offers improved synergy between revision management and the automated deployment process provided by Pega's Deployment Manager 4.8 pipelines. Use Deployment Manager 4.8 to increase the efficiency of business-as-usual application changes and automatize the deployment of revision packages.
For more information, see Managing the business-as-usual changes.
Support for Cloud AutoML topic detection models
Valid from Pega Version 8.5
In Prediction Studio, you can now connect to topic detection models that you create in Cloud AutoML, Google's cloud-based machine learning service. You can then use the models to categorize and route messages from your customers.
For more information, see Broaden your selection of topic detection models by connecting to third-party services (8.5).
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.
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.
Optimization check utility available for legacy strategies
Valid from Pega Version 8.5
Ensure that your strategies are compatible with the optimized strategy execution engine introduced in Pega Platform™ 8.1 by running a post-upgrade utility that checks strategies within your application for areas that you can optimize, for example, by reducing the number of page properties that are copied from one shape to another. Running the utility produces a report that you can use to plan the required updates to your strategies.
For more information, see Make your strategies compatible with the optimized strategy execution engine by using a check utility.
More flexibility for Date Time predictors in adaptive models
Valid from Pega Version 8.5
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.