A Machine Learning-Based System for Predicting Service-Level Failures in Supply Chains
Bibliographic record
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".