A framework for comparing process mining algorithms

Abstract

There are many process mining algorithms with different theoretical foundations and aims, raising the question of how to choose the best for a particular situation. A framework is proposed for objectively comparing algorithms for process discovery against a known ground truth, with an implementation using existing tools. Results from an experimental evaluation of five algorithms against basic process structures confirm the validity of the approach. In general, numbers of traces for mining are predictable from the structure and probabilities in the model, but there are some algorithm-specific differences.