Behavioural Clustering by Extensive Declarative Specifications Measurements(Extended Abstract)

Alessio Cecconi

Publication: Chapter in book/Conference proceedingContribution to conference proceedings

22 Downloads (Pure)


The recognition, classification and grouping of distinctprocess behaviours in an event log is a key aspect of processanalysis. In unstructured and flexible processes contexts thisis not straightforward and the literature devises differenttechniques to tackle the problem. An effective one has beenfound in trace clustering, namely a set of techniques whichautomatically group similar traces according to specifiedcriteria, allowing for better understandability and decreasedcomplexity of the analysis. However, all available clusteringtechniques are designed exclusively with procedural processmodels. For those techniques the key aspect for trace similarityis the precise sequence of execution of events, as they consideronly events that immediately follow or precede one another.Yet, the properties and relations of events in a process mayfall outside such a narrow scope.In our research, we want to explore the opportunity ofemploying declarative process mining for trace clustering. Webelieve that the characteristics of declarative specifications canlead to novel results given the focus on different relations of theevents in the event log. Indeed, a declarative rule describes adesired property of the process, not a specific execution. Thus,grouping around them suggests clusters centred on flexible,complex, and yet specific behaviours of the process instead ofstrict events sequence similarity.Any clustering technique is based on similarity (or distance)concepts describing how close or distant objects are. Never-theless, the current declarative rules evaluation methods arelimited to devise a comprehensive similarity concept for tracesbased on rules. To fill this gap it is required an extensivemeasurement system for declarative specifications.
Original languageEnglish
Title of host publicationProceedings of the ICPM Doctoral Consortium and Tool Demonstration Track 2020 co-located with the 2nd International Conference on Process Mining (ICPM 2020)
Editors Claudio Di Ciccio, Benoit Depaire, Jochen De Weerdt, Chiara Di Francescomarino, and Jorge Munoz-Gama
Place of PublicationPadua, Italy
PublisherCEUR Workshop Proceedings
Pages11 - 12
Publication statusPublished - 2020

Cite this