Demand Forecasting in Retail Business Using the Ensemble Machine Learning Framework - A Stacking Approach
Bibliographic record
Abstract
Demand forecasting is an integral component of organizational and supply chain operations. Its primary objective is to anticipate the future demand for products, thereby informing and refining strategic decisions related to inventory management. Despite the inherent complexities in achieving precise demand forecasts, many methodologies have been proposed for the establishment of efficient forecasting systems. Such methodologies encompass traditional statistical approaches, hybrid techniques, and advanced methodologies rooted in machine learning and deep learning. Scholarly investigations within demand forecasting indicate a growing preference for deep learning paradigms, especially when confronted with data characterized by multivariate attributes, high dimensionality, and unpredictable demand fluctuations. Given the research emphasis on the retail domain, a sector inherently marked by data that is both multivariate and possesses volatile demand characteristics, this study devised a Stacking Ensemble learner. A comparative assessment was subsequently conducted, evaluating this ensemble against a trained Multilayer Perceptron , a deep learning archetype. The evaluation utilized a historical sales dataset sourced from ten Walmart outlets across Texas, California, and Wisconsin. Evaluative metrics were employed to discern the forecasting proficiencies of the respective frameworks. The evaluation determined that the Stacking Ensemble model outperformed the Multilayer Perceptron in terms of accurate predictions.
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 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".