Machine Learning in Business Process Monitoring: A Comparison of Deep Learning and Classical Approaches Used for Outcome Prediction

Wolfgang Kratsch, Jonas Manderscheid, Maximilian Röglinger () and Johannes Seyfried
Additional contact information
Wolfgang Kratsch: University of Bayreuth, Project Group Business and Information Systems Engineering of the Fraunhofer FIT
Jonas Manderscheid: University of Augsburg
Maximilian Röglinger: University of Bayreuth, Project Group Business and Information Systems Engineering of the Fraunhofer FIT
Johannes Seyfried: University of Augsburg

Business & Information Systems Engineering: The International Journal of WIRTSCHAFTSINFORMATIK, 2021, vol. 63, issue 3, No 5, 276 pages

Abstract: Abstract Predictive process monitoring aims at forecasting the behavior, performance, and outcomes of business processes at runtime. It helps identify problems before they occur and re-allocate resources before they are wasted. Although deep learning (DL) has yielded breakthroughs, most existing approaches build on classical machine learning (ML) techniques, particularly when it comes to outcome-oriented predictive process monitoring. This circumstance reflects a lack of understanding about which event log properties facilitate the use of DL techniques. To address this gap, the authors compared the performance of DL (i.e., simple feedforward deep neural networks and long short term memory networks) and ML techniques (i.e., random forests and support vector machines) based on five publicly available event logs. It could be observed that DL generally outperforms classical ML techniques. Moreover, three specific propositions could be inferred from further observations: First, the outperformance of DL techniques is particularly strong for logs with a high variant-to-instance ratio (i.e., many non-standard cases). Second, DL techniques perform more stably in case of imbalanced target variables, especially for logs with a high event-to-activity ratio (i.e., many loops in the control flow). Third, logs with a high activity-to-instance payload ratio (i.e., input data is predominantly generated at runtime) call for the application of long short term memory networks. Due to the purposive sampling of event logs and techniques, these findings also hold for logs outside this study.

Keywords: Predictive process monitoring; Business process management; Outcome prediction; Deep learning; Machine learning (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://link.springer.com/10.1007/s12599-020-00645-0 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:binfse:v:63:y:2021:i:3:d:10.1007_s12599-020-00645-0

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/12599

DOI: 10.1007/s12599-020-00645-0

Access Statistics for this article

Business & Information Systems Engineering: The International Journal of WIRTSCHAFTSINFORMATIK is currently edited by Martin Bichler

More articles in Business & Information Systems Engineering: The International Journal of WIRTSCHAFTSINFORMATIK from Springer, Gesellschaft für Informatik e.V. (GI)
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().