A Machine Learning-Based System for Predicting Service-Level Failures in Supply Chains

Gabrielle Gauthier Melançon (), Philippe Grangier (), Eric Prescott-Gagnon (), Emmanuel Sabourin () and Louis-Martin Rousseau ()
Additional contact information
Gabrielle Gauthier Melançon: Polytechnique Montréal, Montréal, Québec H3T 1J4, Canada; Element AI, Montréal, Québec H2S 3G9, Canada
Philippe Grangier: IVADO Labs, Montréal, Québec H2S 2J9, Canada
Eric Prescott-Gagnon: Element AI, Montréal, Québec H2S 3G9, Canada
Emmanuel Sabourin: Element AI, Montréal, Québec H2S 3G9, Canada
Louis-Martin Rousseau: Polytechnique Montréal, Montréal, Québec H3T 1J4, Canada

Interfaces, 2021, vol. 51, issue 3, 200-212

Abstract: Despite advanced supply chain planning and execution systems, manufacturers and distributors tend to observe service levels below their targets, owing to different sources of uncertainty and risks. These risks, such as drastic changes in demand, machine failures, or systems not properly configured, can lead to planning or execution issues in the supply chain. It is too expensive to have planners continually track all situations at a granular level to ensure that no deviations or configuration problems occur. We present a machine learning system that predicts service-level failures a few weeks in advance and alerts the planners. The system includes a user interface that explains the alerts and helps to identify failure fixes. We conducted this research in cooperation with Michelin. Through experiments carried out over the course of four phases, we confirmed that machine learning can help predict service-level failures. In our last experiment, planners were able to use these predictions to make adjustments on tires for which failures were predicted, resulting in an improvement in the service level of 10 percentage points. Additionally, the system enabled planners to identify recurrent issues in their supply chain, such as safety-stock computation problems, impacting the overall supply chain efficiency. The proposed system showcases the importance of reducing the silos in supply chain management.

Keywords: supply chain management; manufacturing; machine learning; human–computer interface; explainable AI (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
http://dx.doi.org/10.1287/inte.2020.1055 (application/pdf)

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:inm:orinte:v:51:y:2021:i:3:p:200-212

Access Statistics for this article

More articles in Interfaces from INFORMS Contact information at EDIRC.
Bibliographic data for series maintained by Chris Asher ().