Detecting workarounds in business processes — A deep learning method for analyzing event logs
Weinzierl S, Wolf V, Pauli T, Beverungen D, Matzner M (2020)
Publication Type: Conference contribution, Conference Contribution
Publication year: 2020
Publisher: AISeL
Pages Range: 1-16
Conference Proceedings Title: Proceedings of the 28th European Conference on Information Systems
Event location: Marrakesch
Abstract
Business processes performed in organizations often deviate from the
abstract process models issued by designers. Workarounds that are
carried out by process participants to increase the effectiveness or
efficiency of their tasks are often viewed as negative deviations from
prescribed business processes, interfering with their efficiency and
quality requirements. But workarounds might also play an important role
in identifying and re-structuring inefficient, dysfunctional, or
obsolete processes. While ethnography or critical incident techniques
can serve to identify how and why workarounds emerge, we need automated
methods to detect workarounds in large data sets. We set out to design a
method that implements a deep-learning-based approach for detecting
workarounds in event logs. An evaluation with three public real-life
event logs exhibits that the method can identify workarounds best in
standardized business processes that contain fewer variations and a
higher number of different activities. Our method is one of the first IT
artifacts to bridge boundaries between the complementing research
disciplines of organizational routines and business processes
management.
Authors with CRIS profile
Sven Weinzierl
Lehrstuhl für Digital Industrial Service Systems
Tobias Pauli
Lehrstuhl für Digital Industrial Service Systems
Martin Matzner
Lehrstuhl für Digital Industrial Service Systems
Related research project(s)
How to cite
APA:
Weinzierl, S., Wolf, V., Pauli, T., Beverungen, D., & Matzner, M. (2020). Detecting workarounds in business processes — A deep learning method for analyzing event logs. In Proceedings of the 28th European Conference on Information Systems (pp. 1-16). Marrakesch, MA: AISeL.
MLA:
Weinzierl, Sven, et al. "Detecting workarounds in business processes — A deep learning method for analyzing event logs." Proceedings of the European Conference on Information Systems, Marrakesch AISeL, 2020. 1-16.
BibTeX: Download