Title: An integrated fuzzy Delphi-DEMATEL and analytic network process for sustainable operations and evaluations in process mining

Authors: Mohammad Salehi; Raouf Khayami; Mirpouya Mirmozaffari

Addresses: Shiraz University of Technology, Shiraz, Iran ' Shiraz University of Technology, Shiraz, Iran ' Department of Industrial Engineering, Dalhousie University, 5269 Morris Street, Halifax, NS B3H 4R2, Canada

Abstract: This study examines the evolving role of process mining in monitoring real-world processes through advanced discovery algorithms like alpha, PSO miner, and genetic miner. Traditionally, these algorithms have been evaluated using precision, consistency, simplicity, and generalisation. However, the IEEE task force on process mining called for new dimensions and refined priorities. Using the fuzzy Delphi method, the study evaluated 12 dimensions and 20 criteria, narrowing them to 6 dimensions and 10 key criteria. The decision-making trial and evaluation laboratory (DEMATEL)-based analytic network process (DANP) method was applied to prioritise and weigh these factors. Key additions include the new dimensions of explainability and robustness. The study identifies consistency, cyclomatic complexity, and density as major performance influencers, with simplicity receiving the highest weight (0.175) and consistency the lowest (0.153). These findings aim to enhance process discovery algorithms by addressing both traditional and newly identified dimensions.

Keywords: sustainable discovery algorithm; process mining; multi-criteria decision-making; MCDM; DEMATEL-based analytic network process; DANP; fuzzy Delphi; discovery algorithm's performance dimensions.

DOI: 10.1504/IJMDM.2025.149569

International Journal of Management and Decision Making, 2025 Vol.24 No.6, pp.583 - 613

Received: 18 Oct 2024
Accepted: 21 Nov 2024
Published online: 07 Nov 2025 *

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