Process mining assumes event data to be stored in an event log, which is technically either a relational table (attributes as columns) or a stream of events (attribute value pairs). Recently, we developed a new technique to store event data in a Graph database such as Neo4j. This allows to do process mining over various dimensions such as shared resources, shared data, or multiple interacting cases allowing for a more complete view on an entire organization. The objective of this assignment is to develop new process mining use cases and techniques enabled by this format and to showcase their application in a proof-of-concept implementation.
Contact: Dr. Dirk Fahland.