Published Release Notes

Improvements for the PMML models

The Pega 7 Platform extends support for the PMML models to include PMML 4.2 features and validations. Additionally, the PMML files that contain custom functions can be imported into the Pega 7 Platform and used in strategies.

For more information, see Predictive Model rule form.

Improvements to the adaptive models management

There are several improvements for managing large sets of adaptive models that make model management faster and easier. In the Adaptive Models Management landing page, you can clear and delete models in bulk. In the Predictors tab of the Adaptive Model rule, you can add multiple predictors. In the Memory estimation tab of the Adaptive Model rule, you can estimate the memory that the Adaptive Decision Manager (ADM) system needs to accommodate the models that use the adaptive model configuration.

For more information, see:

• Adaptive Models Management landing page
• Adaptive model form - Completing the Predictors tab
• Adaptive model form - Complating the Memory estimation tab

Improvements to the HBase data set, HFDS data set, and Hadoop host configuration

The Pega 7 Platform features maintenance improvements to the Hadoop host configuration, HBase data set, and Apache Hadoop File System (HDFS) data set. System architects can more easily make HDFS and HBase storage available to business scientists for exploratory analysis and predictive model building.

For more information, see Big data functionality enhancements.

Data Flow rule enhancements

The enhancements to the Data Flow rule facilitate decision execution in real time, batch, and Pega 7 Platform applications. The DataFlow-Execute method in activities can be used to execute and monitor batch runs and real time data flows. In addition, you can configure pre- and post-activities that are executed before and after data flow execution.

For more information, see the following Pega 7 Platform help topics:

• About data flow rules
• DataFlow-Execute method
• Pre- and post-processing of data flows

Strategy canvas enhancements

The Strategy canvas in Decision Management has been enhanced to let you to create, edit, and display your strategy more easily. You can keep your strategy in order using the Smart Mini Map, improved selection capability, and the new Align and Distribute options. Additionally, you can perform the most common operations using keyboard shortcuts and accelerators.

For more information, see Strategy rule enhancements.

Enhanced adaptive model reporting

The new Model report replaces the Behavior and the Performance overview reports to improve report usability and provide consistent information. You can export your Model reports into PDF or Excel files to view or share them outside the Pega® Platform. The Model report also includes information on the groups of correlated predictors where the best performing predictor from each group is active in the model and other remain inactive; this information helps you understand why predictors are active or inactive.

For more information, see Generating a model report.

Use Kinesis data sets in Pega Decision Management

You can create Kinesis data set instances to connect to Amazon Kinesis Data Streams and use this data set in decision management for processing real-time streaming data. Integrating Kinesis data streams into Pega® Platform in the cloud provides a fault-tolerant and scalable solution for processing IT infrastructure log data, application logs, social media, market data feeds, and web clickstream data.

For more information, see Creating a Kinesis data set.

Store and scale the processing of Stream data records on multiple nodes

You can configure the Stream service on Pega^® Platform to ingest, route, and deliver high volumes of low-latency data such as web clicks, transactions, sensor data, and customer interaction history. You can store streams of records in a fault-tolerant way and process stream records as they occur. Add or remove Stream nodes to increase or decrease the use of the Stream service and optimize data processing.

For more information, see Stream service overview.

Decisioning services now use default node classification

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.

Train machine learning models for extracting named entities and detecting intents

Data scientists can train machine learning-based text extraction and intent detection models by using the Analytics Center. With text extraction, you can train a Conditional Random Fields (CRF) model to detect whether the content contains specified entity types such as person names, company and organization names, locations, dates and times, percentages, and monetary amounts. For intent detection, you can train a maximum entropy model to understand user intentions expressed in written content. With these two new capabilities, you can quickly react to customer queries and comments by taking appropriate action against the information that you extracted.

For more information, see Creating machine learning-based text extraction models and Creating machine learning-based intent analysis models.