Explainable Verification of Hierarchical Workflows Mined from Event Logs with Shapley Values
By: Radoslaw Klimek, Jakub Blazowski
Workflow mining discovers hierarchical process trees from event logs, but it remains unclear why such models satisfy or violate logical properties, or how individual elements contribute to overall behavior. We propose to translate mined workflows into logical specifications and analyze properties such as satisfiability, liveness, and safety with automated theorem provers. On this basis, we adapt Shapley values from cooperative game theory to attribute outcomes to workflow elements and quantify their contributions. Experiments on benchmark datasets show that this combination identifies critical nodes, reveals redundancies, and exposes harmful structures. This outlines a novel direction for explainable workflow analysis with direct relevance to software engineering practice, supporting compliance checks, process optimization, redundancy reduction, and the design of next-generation process mining tools.
Similar Papers
Logic Mining from Process Logs: Towards Automated Specification and Verification
Software Engineering
Helps computers understand how real-world processes work.
SHAining on Process Mining: Explaining Event Log Characteristics Impact on Algorithms
Machine Learning (CS)
Finds what makes computer process analysis better.
A Theoretical Framework for Explaining Reinforcement Learning with Shapley Values
Machine Learning (CS)
Explains how smart computer programs make decisions.