Key Featurs of Decision Management
- Proposition Management:
is how propositions are defined, stored and managed in Pega Decision Management. Propositions are anything that can be offered to a customer. (advertisements, products, offer bundles, customer service actions) - Decision Strategies:
match propositions with customers. They combine data about the customer with rules and predictive analytics to determine the Next-Best-Action for a customer during each interaction. - Interaction History:
is what gives Pega Decision Management its long-term memory. It captures every customer response to every Next-Best-Action and provides it as input for determining what the Next-Best-Action should be. - Visual Business Director (VBD):
is a 3-D graphical environment for simulating and analyzing the results of decision strategies and customer interactions in real time. This helps ensure that your strategies are on target to meet your goals.
This means that if you add a new proposition it will immediately picked up and analyzed by VBD. VBD enables you to monitor Key Performance Indicators (KPIs) which you can create and maintain based on previously defined interaction outcomes. - Adaptive Decision Manager:
enables automatic development and deployment of adaptive predictive models. These models learn and gather data on-the-fly to predict future customer behavior. - Predictive Analytics Director:
provides a safe and heavily automated environment in which business users can easily develop fit-for-purpose, non-adaptive predictive models that use historical data to predict future customer behavior.
What is Run Interaction
The Run Interaction flow shape invokes a decision strategy, which
determines how and when to make a proposition to the customer, and
then captures the customer’s response to the proposition.
Decision rule types
- Predictive Model:
Used to execute predictive models created with Pega Predictive Analytics Director. - Adaptive Model:
used to configure the adaptive analytics decision models that are managed by the Adaptive Decision Manager service. - The Interaction:
used to execute a decision strategy from a
workflow and capture the details of the customer interaction - Scorecards:
used to implement industry standard scorecards such as
the FICO scorecard. - Decision Components:
are the building blocks of decision strategies. They are the language used by the business to express how
they want to do business through their strategies.
7 groups of Decision Components:
- The Import components:
- bring additional data into the decision strategy, such as external data, interaction history data or the propositions that you want to offer to the customer.
- Business Rules components:
components apply business rules, such as eligibility
requirements. - Decision Analytics components:
components make predictions about the customer, such as, what is their propensity, or, likelihood that they will accept an offer? - Enrichment components:
can do calculations, such as a margin calculation based on the price and cost. - Arbitration components:
filter out propositions that are less relevant for the customer. They also filter out propositions that a customer is not eligible for. - Selection components:
allow propositions to be ranked, so the top offers for each customer can be selected - Aggregation components:
allow the calculation of aggregate numbers.
Landing Pages
- Monitoring: This page enables you to monitor decisions through reports
- Decisions: This page enables you to define and manage all aspects of the decisioning hierarchy
- Predictive Analytics: This page enables you to manage all aspects of the development and implementation of predictive and adaptive models
- Infrastructure: This page enables you to configure, view and manage resource usage and various operational settings.
What is the need for associating the classes with a dedicated database table in Pega Decision Management?
To test decision strategies using database records. Database records can be used when testing a decision strategy using simulation sor using an Input Definition in the Auto-run.
Decision Architect can do by default
• Propositions: create, delete and modify existing propositions
• Adaptive models: clear and delete adaptive models; change the parameters of the adaptive
models, like for e.g. Memory, Grouping granularity, Correlation threshold etc.
• Key performance indicators: add, delete and change KPIs which can be later viewed in Visual
Business Director
• Data sources: delete simulation data sources and change start time of these data sources
• Saved views: delete views created in Visual Business Director
