A case-based approach to business process monitoring

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The agile workflow technology deals with flexible workflow adaptation and overriding, in case of foreseen as well as unforeseen changes and problems in the operating business environment. One key issue that an agile workflow system should address is Business Process (BP) monitoring. This consists in properly highlighting and organizing non-compliances and adaptations with respect to the default process schema. Such an activity can be the starting point for other very critical tasks, such as quality assessment and process reengineering. In this paper, we introduce an automated support to BP monitoring, which exploits the Case-based Reasoning (CBR) methodology. CBR is particularly well suited for managing exceptional situations, and has been proposed in the literature for process change reuse and workflow adaptation support. Our work extends these functionalities by retrieving traces of process execution similar to the current one, which can then be automatically clustered. Retrieval and clustering results can provide support both to end users, in the process instance execution phase, and to process engineers, in (formal) process quality evaluation and long term process schema redefinition. Our approach in practice is illustrated by means of a case study in the field of stroke management.

Original languageEnglish
Title of host publicationArtificial Intelligence in Theory and Practice III - Third IFIP TC 12 International Conference on Artificial Intelligence, IFIP AI 2010, Held as Part of WCC 2010, Proceedings
EditorsMax Bramer
PublisherSpringer New York LLC
Pages101-110
Number of pages10
ISBN (Print)3642152856, 9783642152856
DOIs
Publication statusPublished - 2010

Publication series

NameIFIP Advances in Information and Communication Technology
Volume331 AICT
ISSN (Print)1868-4238

Fingerprint

Dive into the research topics of 'A case-based approach to business process monitoring'. Together they form a unique fingerprint.

Cite this