Decision management services

Decision management is a Pega Platform™ capability that provides technology for decision-making, such as proposition management, Interaction History, adaptive and Predictive Models, decision strategies, and other features on which Pega Customer Decision Hub™ builds. Decision management is intended for organizations that want to make intelligent, automated decisions in customer service and process automation.

Decision management services comprise the technical foundation of decision management. Decision management services are responsible for the following functional areas of decision management:

Decision Data Store

The Decision Data Store (DDS) service manages the Cassandra cluster and stores decision management data in a Cassandra database. The Decision Data Store is the repository for analytical data from various sources and is deployed as part of the Pega Platform node cluster. The Decision Data Store consists of nodes that connect to an external Cassandra cluster using one-to-many relationships.

Each node that comprises the Decision Data Store handles data in the JSON format for each customer from different sources. The data is distributed and replicated around the cluster and is stored in the node file system.

For more information, see Configuring the Decision Data Store service.

Adaptive Decision Manager

The Adaptive Decision Manager (ADM) creates and updates adaptive models by processing customer responses in real time. By including adaptive models in your next-best-action strategies, you can make better decisions for your business based on accurately predicted customer behavior.

The ADM service is native to Pega Platform and is supported by the DM node-type infrastructure. Therefore, the ADM service does not require dedicated hardware or operating system environments.

Data Flow

The Data Flow service enables running Data Flows in batch and real-time (stream) modes. Data flows are data pipelines that read, transform, and write data. With Data Flows, you can, for example, run decisions, perform text analysis, and run real-time aggregations.

In the Data Flow service, you can run Data Flows in batch mode or in real-time (stream) mode. Specify the number of Pega Platform threads that you want to use for running Data Flows in each mode. Batch and real-time modes process data independently and do not affect each other. The higher the number of nodes for a mode, the higher the use of the mode.

Real-Time Data Grid

The Real-Time Data Grid (RTDG) service performs historical analysis and forecasting for your next-best-action strategies. With the RTDG service, you can monitor the results of your next-best-action decisions in real time.

You can view the results in the Visual Business Director (VBD) planner, along with visualizations for different aspects of your business. Pega Platform uses a native real-time data grid implementation as the back-end technology for the Visual Business Director. The new RTDG service replaced the Hazelcast-based service, which was used in earlier releases.

Stream

The Stream service enables the asynchronous flow of data between processes in Pega Platform. The Stream service is a multi-node component that is based on Apache Kafka.

For more information, see Enabling decision management services.

Check your knowledge with the following interaction:

---

This Topic is available in the following Module:

• Prediction Studio and collaboration v3