Performance-preserving event log sampling for predictive monitoring

Mohammadreza Fani Sani (Corresponding author), Mozhgan Vazifehdoostirani, Gyunam Park, Marco Pegoraro, S.J. (Bas) van Zelst, Wil M.P. van der Aalst

Research output: Contribution to journalArticleAcademicpeer-review

7 Citations (Scopus)
34 Downloads (Pure)

Abstract

Predictive process monitoring is a subfield of process mining that aims to estimate case or event features for running process instances. Such predictions are of significant interest to the process stakeholders. However, most of the state-of-the-art methods for predictive monitoring require the training of complex machine learning models, which is often inefficient. Moreover, most of these methods require a hyper-parameter optimization that requires several repetitions of the training process which is not feasible in many real-life applications. In this paper, we propose an instance selection procedure that allows sampling training process instances for prediction models. We show that our instance selection procedure allows for a significant increase of training speed for next activity and remaining time prediction methods while maintaining reliable levels of prediction accuracy.
Original languageEnglish
Pages (from-to)53-82
Number of pages30
JournalJournal of Intelligent Information Systems
Volume61
Issue number1
Early online date6 Mar 2023
DOIs
Publication statusPublished - Aug 2023

Keywords

  • Predictive monitoring
  • Machine learning
  • Sampling
  • Process mining
  • Deep learning
  • Instance selection

Fingerprint

Dive into the research topics of 'Performance-preserving event log sampling for predictive monitoring'. Together they form a unique fingerprint.

Cite this