Publication type: Article in scientific journal
Type of review: Peer review (publication)
Title: Facilitating enhanced decision support using a social norms approach
Authors: Keller, Thomas
Savarimuthu, Bastin Tony Roy
DOI: 10.4018/JECO.2017040101
Published in: Journal of Electronic Commerce in Organizations
Volume(Issue): 15
Issue: 2
Issue Date: 2017
Publisher / Ed. Institution: IGI Global
ISSN: 1539-2937
Language: English
Subjects: Decision support; Human interaction; Norm inference; Process automation; Process mining
Subject (DDC): 658.5: Production management
Abstract: Social norms constrain behavior of individuals either through obligating or prohibiting certain types of behavior. Norm-based mechanisms have only recently found applications in enhancing decisions of knowledge workers in an automated business process management context. The norms inferred in the context of business process executions are then recommended to users so as to enable them to make informed decisions. The previous work on prohibition norm inference focused on identifying failure cases, which is now complemented by first inferring norms from the successful process execution cases and then inferring prohibition norms. This approach based on considering social feedback (i.e. inferring what is obliged and prohibited from history logs of process execution) shows encouraging results under uncertain business environments. Using simulation results the paper demonstrates that using the norm based mechanism results in reduced failure rates in the decision making of a knowledge worker while still providing maximum flexibility for the user to choose from a range of actions to execute.
Fulltext version: Published version
License (according to publishing contract): Licence according to publishing contract
Departement: School of Management and Law
Organisational Unit: Institute of Business Information Technology (IWI)
Appears in collections:Publikationen School of Management and Law

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.