Forecasting Supply Chain Demand Using Machine Learning Algorithms
Bibliographic record
Abstract
Managing supply chains in today’s complex, dynamic, and uncertain environment is one of the key challenges affecting the success of the businesses. One of the crucial determinants of effective supply chain management is the ability to recognize customer demand patterns and react accordingly to the changes in face of intense competition. Thus the ability to adequately predict demand by the participants in a supply chain is vital to the survival of businesses. Demand prediction is aggravated by the fact that communication patterns between participants that emerge in a supply chain tend to distort the original consumer’s demand and create high levels of noise. Distortion and noise negatively impact forecast quality of the participants. This work investigates the applicability of machine learning (ML) techniques and compares their performances with the more traditional methods in order to improve demand forecast accuracy in supply chains. To this end we used two data sets from particular companies (chocolate manufacturer and toner cartridge manufacturer), as well as data from the Statistics Canada manufacturing survey. A representative set of traditional and ML-based forecasting techniques have been applied to the demand data and the accuracy of the methods was compared. As a group, Machine Learning techniques outperformed traditional techniques in terms of overall average, but not in terms of overall ranking. We also found that a support vector machine (SVM) trained on multiple demand series produced the most accurate forecasts.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".