Predicting supply chain risks using machine learning : The trade-off between performance and interpretability
- Submitting institution
-
The University of Huddersfield
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 55
- Type
- D - Journal article
- DOI
-
10.1016/j.future.2019.07.059
- Title of journal
- Future Generation Computer Systems
- Article number
- -
- First page
- 993
- Volume
- 101
- Issue
- -
- ISSN
- 0167-739X
- Open access status
- Compliant
- Month of publication
- July
- Year of publication
- 2019
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- Yes
- Number of additional authors
-
2
- Research group(s)
-
-
- Citation count
- 6
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Published in the ERA2010 A-ranked journal Future Generation Computer Systems, ranked Q1 for Software in Scimago, the paper presents interdisciplinary research on utilising machine learning algorithms for the prediction of risks in global supply chains. The presented framework is the first attempt to detail the required synergies between experts from different disciplines (supply chains and AI) to deliver performant predictive models, while also stressing the significance of interpretability in the particular context. The presented research has already been recognised by Vishnu et al. (2019) (https://www.emerald.com/insight/content/doi/10.1108/JAMR-04-2019-0061/full/html) as a roadmap for research at the confluence of AI and supply chain risk management.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -