What if process predictions are not followed by good recommendations?

Marcus Dees, Massimiliano de Leoni, Wil M.P. van der Aalst, Hajo A. Reijers

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

3 Citations (Scopus)
78 Downloads (Pure)

Abstract

Process-aware Recommender systems (PAR systems) are information systems that aim to monitor process executions, predict their outcome, and recommend effective interventions to reduce the risk of failure. This paper discusses monitoring, predicting, and recommending using a PAR system within a financial institute in the Netherlands to avoid faulty executions. Although predictions were based on the analysis of historical data, the most opportune intervention was selected on the basis of human judgment and subjective opinions. The results showed that, although the predictions of risky cases were relatively accurate, no reduction was observed in the number of faulty executions. We believe that this was caused by incorrect choices of interventions. Although a large body of research exists on monitoring and predicting based on facts recorded in historical data, research on fact-based interventions is relatively limited. This paper reports on lessons learned from the case study in finance and identifies the need to develop interventions based on insights from factual, historical data.

Original languageEnglish
Title of host publication17th International Conference on Business Process Management 2019 Industry Forum
Subtitle of host publicationProceedings of the Industry Forum at BPM 2019 co-located with 17th International Conference on Business Process Management (BPM 2019)
EditorsJan vom Brocke , Jan Mendling, Michael Rosemann
PublisherCEUR-WS.org
Pages61-72
Number of pages12
Publication statusPublished - 1 Jan 2019
Event17th International Conference on Business Process Management (BPM 2019) - Austria, Vienna, Austria
Duration: 1 Sep 20196 Sep 2019
Conference number: 17
https://bpm2019.ai.wu.ac.at/

Publication series

NameCEUR Workshop Proceedings
Volume2428
ISSN (Print)1613-0073

Conference

Conference17th International Conference on Business Process Management (BPM 2019)
Abbreviated titleBPM 2019
Country/TerritoryAustria
CityVienna
Period1/09/196/09/19
Internet address

Keywords

  • A/B Test
  • Intervention
  • Prediction
  • Process Mining
  • Recommender Systems

Fingerprint

Dive into the research topics of 'What if process predictions are not followed by good recommendations?'. Together they form a unique fingerprint.

Cite this