10.15480/882.2484
Diedrich, Katharina
Katharina
Diedrich
Klingebiel, Katja
Katja
Klingebiel
Smart risk analytics design for proactive early warning
epubli GmbH
2019
Supply chain risk management
Proactive early warning
Smart risk analytics
Machine learning
004: Informatik
330: Wirtschaft
380: Handel, Kommunikation, Verkehr
TUHH Universitätsbibliothek
TUHH Universitätsbibliothek
2019-11-13
2019-11-13
2019-09-26
en
Conference Paper
Hamburg International Conference of Logistics (HICL) 27: 559-585 (2019)
978-3-750249-47-9
http://hdl.handle.net/11420/3755
urn:nbn:de:gbv:830-882.054511
10.15480/882.2484
https://creativecommons.org/licenses/by-sa/4.0/
Purpose: Automobile manufacturers are highly dependent on supply chain performance which is endangered by risks. They are not yet able to proactively manage these risks, often requiring reactive bottleneck management. A proactive and digitalized early warning method is needed. Methodology: The publication provides methodological-empirical contribution to proactive early warning resulting in a smart risk management approach. The methodological approach is carried out according to the design science research approach. Findings: The developed smart risk management enables an automated, objective and real-time ex-ante-assessment of supply chain risks in to secure the supply of the automobile manufacturer. Smart risk analytics based on artificial intelligence is shown with its suitability for proactive early warning using the example of inaccurate demand planning. Originality: The analytical approach provides insights into the flexibility of supply chains under risk and the impact over time, which is applied in the proactive early warning design. Artificial intelligence is applied to predict and assess supply chain risk events.