Distributionally Robust Optimization for the Multi-Period Multi-Item Lot-Sizing Problems Under Yield Uncertainty
Bibliographic record
Abstract
Yield uncertainty is an important issue in various industries such as agriculture, food, and textile where the production output relies on uncontrollable factors and fluctuating raw material quality. To systematically leverage data to deal with uncertainty cost-effectively, distributionally robust optimization combines the strengths of stochastic programming and robust optimization by optimizing the expected costs against an ambiguity set that defines possible distributions. In this work, we leverage a data-driven robust optimization framework and formulate a mixed-integer distributionally robust multi-item lot-sizing model with uncertain production yield to determine a robust production plan. To this end, we use a scenario-wise formulation that partitions the available data into scenarios that define different patterns influencing the quality of the product and production process. In addition, we apply the proposed approach to real-world data of a case study to demonstrate the effectiveness of the proposed framework in dealing with yield uncertainty. Our experimental results show that distributionally robust plans lead to more effective cost-saving strategies and decreased risk of stock-outs. Additionally, our findings suggest that the proposed model exhibits lower sensitivity to variations in production yield realizations and it is more proficient in incorporating historical data into the decision-making process. This results in a more effective response to challenges encountered within the production system under yield uncertainty. Note to Practitioners–In a production context with various sources of uncertainty for which the mathematical estimation of the uncertain parameter can be complex or hard to perform, it would be better to use the proposed robust approach. Here, any information, accurate or not, new or historical, can be integrated into the system to improve the quality of the obtained production plan, yet still robust and mitigate nervousness. For the reduction of conservatism, the proposed approaches indicate how the manufacturer risk aversion could be integrated into the decision models to respond to the strategic need for robustness for production planning under uncertainty.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".