Measuring rule-based LTLf process specifications: A probabilistic data-driven approach

Declarative process specifications define the behavior of processes by means of rules based on Linear Temporal Logic on Finite Traces LTLf. In a mining context, these specifications are inferred from, and checked on, multi-sets of runs recorded by information systems (namely, event logs). To this end, being able to gauge the degree to which process data comply with a specification is key. However, existing mining and verification techniques analyze the rules in isolation, thereby disregarding their interplay. In this paper, we introduce a framework to devise probabilistic measures for declarative process specifications. Thereupon, we propose a technique that measures the degree of satisfaction of specifications over event logs. To assess our approach, we conduct an evaluation with real-world data, evidencing its applicability for diverse process mining tasks, including discovery, checking, and drift detection.

Automated summary

This paper introduces a framework for designing probabilistic measures for declarative process specifications, which can assess the degree of compliance between process data and specifications. Through experiments, the applicability of the approach for various process mining tasks is demonstrated.