FCA stands for Formal Concept Analysis.
It is a principled way of deriving a concept hierarchy or formal ontology from a collection of objects and their properties.
Each concept in the hierarchy represents the objects sharing some set of properties; and each sub-concept in the hierarchy represents a subset of the objects (as well as a superset of the properties) in the concepts above it.
It can be then easily used to run analysis over the input schema and train ML models for a specific task, such as Relational Learning.
The theoretical assumptions grounding the FCA encoding are explained in Entity Type Recognition -- dealing with the Diversity of Knowledge.