Summarization of Multidimensional Process Traces for Analysis under Edit-distance Constraints

Abstract

Motivation: Business processes and workflows exhibit data models in the form of multi-dimensional sequence of objects. As exemplified in Figure 1 , a business processes, represented as a directed acyclic graph of activities, generates execution traces as a sequence of activities with associated multi-dimensional attributes. For example, an activity in the loan application process can contain information about the person and the department that are responsible for the activity, the person who performs the activity, and the group to which she belongs. Businesses analyze operational data for insights such as understanding workflow patterns and bottlenecks [1] , verifying conformance to policies or regulations [2] , or revealing clusters of common behavior [3] .