Kimberly-Clark Latin America Builds an Optimization-Based System for Machine Scheduling
Bibliographic record
Abstract
During a single planning period, Kimberly-Clark Latin America manufactures dozens of stock-keeping units (SKUs) in varying quantities using a few machines. The same SKU can be manufactured on multiple machines, some of which are more efficient than others. In addition, the setup time for an SKU is sequence dependent, and its demand is stochastic between planning periods. The stochastic demand necessitates changing production plans each planning period; given the large number of SKUs and small number of machines, this leads to inefficiencies. This paper describes the formulation and corresponding solution approach of an integrated inventory, production-planning, and detailed scheduling model to address the inefficiencies in lot sizing, production scheduling, and inventory management. The paper's key contribution is the solution approach, which solves the resultant industry-size NP-hard problem in minutes. The solution quality and its implementation have been tested extensively, and the model has been successfully deployed in five countries. A reduction in finished product inventories of up to 45 percent, an increase in yield and uptime of 2 percent, and improvements in service levels of 2.4 percent are directly attributable to the model and the solution approach highlighted in the paper.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.012 | 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".