Structural Similarity Measurement of Business Process Model to Compare Heuristic and Inductive Miner Algorithms Performance in Dealing with Noise

Ifrina Nuritha*, E. R. Mahendrawathi

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

9 Citations (Scopus)

Abstract

Heuristic and Inductive Miner algorithms have different characteristics, properties, specializations, and performances in modeling business process. This research adopts three modules from Wang framework i.e. log generation, process mining, and similarity calculation to compare process mining algorithms performance in dealing with noise. The similarity calculation module measures structural similarity between reference model generated from standard event log, with mined model generated from noisy event log obtained with Heuristic and Inductive Miner algorithms. Noisy event log is obtained by adding 1% noise to the standard event log. Results from stuctural similarity measurement show that Inductive Miner algorithm obtain better performance in dealing with noise, especially related to material procurement process model of Cement Manufacturing and production in Pharmaceutical Industry.

Original languageEnglish
Pages (from-to)255-263
Number of pages9
JournalProcedia Computer Science
Volume124
DOIs
Publication statusPublished - 2017
Event4th Information Systems International Conference 2017, ISICO 2017 - Bali, Indonesia
Duration: 6 Nov 20178 Nov 2017

Keywords

  • Heuristic Miner
  • Inductive Miner
  • Process Mining
  • Structural Similarity

Fingerprint

Dive into the research topics of 'Structural Similarity Measurement of Business Process Model to Compare Heuristic and Inductive Miner Algorithms Performance in Dealing with Noise'. Together they form a unique fingerprint.

Cite this