What is a scorecard? A scorecard is a special type of concept. A scorecard serves as a static variable. You can use a scorecard resource to track key performance indicators or any other information.
The FraudCriteria scorecard will store the criteria used to determine fraud, not any specific data about customer accounts. In this example, you will use this scorecard in rules.
How are scorecards created? Unlike concepts, there is only one instance of a scorecard. You create the scorecard at design time. Its values can be viewed and updated using rules.
It is more accurate to say there is one instance of a scorecard per inference agent (rule session). This tutorial uses one inference agent. However, in the next tutorial you will deploy multiple agents in a group, and each has its own instance of the scorecard.
You have now set up the channel for the project, and its ontology, that is, the definitions of all the entity types (events, concepts, and scorecards) that are needed to store information (facts) about possible fraud detection.