Title: Identifying performance measures relationships in business processes based on data mining

Authors: Wiem Khlif; Lamin Karous; Nadia Bouassida; Faïez Gargouri

Addresses: MIRACL Laboratory, University of Sfax, Sfax, Tunisia ' University of Kairouan, Kairouan, Tunisia ' MIRACL Laboratory, University of Sfax, Sfax, Tunisia ' MIRACL Laboratory, University of Sfax, Sfax, Tunisia

Abstract: Establishing performance measures relationships is very important in order to make relevant decisions. Actually, these measures are calculated separately without establishing any relation with other elements having impact on the business process (BP). In fact, it is vital to identify all concepts in the BP and integrate domain knowledge. The enhancement of BP performance relies on data understanding and pertinent interpretation of results. So, we propose a new approach for identifying semantic relationships between performance measures related to BPMN elements/actors and belonging to the same or different category(ies), and, between performance measures and quality characteristics. The proposed approach first identifies a new ontology that allows creating semantic relationships between all terms. It uses data mining techniques, especially association rules, to extract information from annotated BP models to assist analysts during the BP performance improvement. The efficiency of the proposed approach is illustrated through performance measures. The illustration is made through a case study and the development of a tool that fully supports the proposed approach.

Keywords: business process; BP; ontology; performance measures relationships; data mining; quality characteristics; association rules.

DOI: 10.1504/IJBPIM.2025.144067

International Journal of Business Process Integration and Management, 2025 Vol.12 No.1, pp.25 - 45

Received: 04 Jan 2024
Accepted: 29 Apr 2024
Published online: 23 Jan 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article