Heterogeneity in feature importance and prediction performance for sales at the market and store levels: the case of branded yogurt products in Quebec
Bibliographic record
Abstract
The supply and demand of fresh food products must be tightly integrated to mitigate food waste, economic losses, and expansion of the environmental footprint. In this study, we use a novel loyalty program dataset from a grocery retailer in Quebec, Canada to predict demand for yogurt products for 17 months from 2015 to 2016. Focusing our attention on 13 newly launched yogurt products from a local manufacturer, we build and test 18 different machine learning models capable of predicting demand for individual products at the aggregate market level, as well as for each store. Store-level data were matched to neighborhood demographic data from the 2016 Canadian census to enrich features. Overall, 330 features were engineered to provide information on the product, marketing and promotions, store, and neighborhood over time. Analyses were conducted using Python 3 in Google Collaboratory and open-source libraries. Results from the best market-level model (random forest) achieve an r-squared of 84.0% on test data, while the store-level model (light gradient boosting machine) only achieves 57%. The results show that ML tools can be useful in modeling demand for new products at aggregate levels but achieving accurate predictions at more granular levels remains a hurdle to overcome. Insights for the preparation and analysis of loyalty data are discussed.
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".