Inventory and Pricing with AI Forecasting: Robust vs. Adaptive Policies
Bibliographic record
Abstract
Background: AI-driven demand forecasting expands the signal space for inventory and pricing decisions, enabling faster reactions to market changes. However, forecast error, non-stationarity, and distribution shifts raise a governance question: should decisions be designed to be robust to uncertainty, or adaptive to feedback?Methods: This review integrates inventory control, probabilistic demand forecasting, dynamic pricing, and robust optimization into a unified decision architecture. We organize prior findings around a closed-loop cycle: data ingestion, forecasting (point and distribution), policy selection (robust/adaptive/hybrid), execution, monitoring, and recalibration.Results: Robust policies protect against tail risk by optimizing over uncertainty sets and worst-case scenarios, but may be conservative and costly in stable environments. Adaptive policies leverage frequent feedback to improve average performance, yet can become unstable under regime changes, delayed signals, or strategic customer responses. The synthesis supports a hybrid design: adaptive learning within robust guardrails (service constraints, pricing move limits, and inventory safety floors).Conclusions: The practical frontier is not “robust versus adaptive” as a binary choice. Best practice is layered: robust feasibility and risk limits at the outer layer, with adaptive learning tuned inside auditable constraints. Future research should prioritize regime-switching demand, decision-focused learning, and explainable pricing and replenishment rules.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.002 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| 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 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".