Process discovery methods have obtained remarkable achievements in ProcessMining, delivering comprehensible process models to enhance managementcapabilities . But selecting the suitable method for a specific event loghighly relies on human expertise, hindering its broad application . Solutionsbased on Meta-learning (MtL) have been promising for creating systems with reduced human assistance . This paper presents a MtL solution for recommendingprocess discovery methods that maximize model quality according tocomplementary dimensions . Thanks to our MtL pipeline, it was possible torecommend a discovery method with 92% of accuracy using light-weight featuresthat describe the event log .

Author(s) : Sylvio Barbon Jr, Paolo Ceravolo, Ernesto Damiani, Gabriel Marques Tavares

Links : PDF - Abstract

Code :
Coursera

Keywords : discovery - mtl - methods - process - method -

Leave a Reply

Your email address will not be published. Required fields are marked *