Demand Forecasting Method of Moving Average considering Variable Selection by Multiple Comparison Procedure
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
To help achieve Goal 12 of the SDGs, “Ensure sustainable consumption and production patterns,” food loss must be reduced. Therefore, a case study based on industry-academia collaboration with a processed food manufacturer was conducted. The manufacturer has a single production site in Koga City, Ibaraki Prefecture, and it ships products nationwide. The company handles milk, dairy products, various beverages, desserts, and other daily delivery products. All of these products are susceptible to obsolescence and have a short shelf life; consequently, excess inventory can easily lead directly to food loss. Aiming to reduce food loss, we analyzed the current situation and factors according to a problem-solving QC (Quality Control) story, and low accuracy in demand forecasting was found to be the main cause of food loss. As a result of studying countermeasures from the perspective of the 4Ms (Man, Machine, Material, Method) of production factors in quality control, we developed and introduced a demand forecasting method suitable for the characteristics of day-of-week-dependent demand as a countermeasure. By examining the formula for demand forecasting, we proposed a method that applies the multiple comparison procedure used in pharmaceutical development to demand forecasting in this case study. The demand forecasting formula is simple, and its practical use is emphasized in this case study. We compared and verified the accuracy of demand forecasting between the proposed method and existing methods using the absolute percentage error as an evaluation index and confirmed the superiority of the proposed method. This proposed method has practical value not only in terms of demand forecasting accuracy but also in terms of the standardization of operations.
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.
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 | 0.057 | 0.038 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.004 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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 it