Research map / Time series / Causal and generative time series
Bayesian Intermittent Demand Forecasting for Large Inventories
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add feature vector (seasonality, holidays, price, out of stock) (ablation) | LS-pure · EC-sub P90 risk (0,56) | relative P90 risk: 1.07 -> 0.80 | Helped |
| add features (ablation) | LS-pure · EC-sub P90 risk (21,84) | relative P90 risk: 0.97 -> 0.73 | Helped |
| add features (ablation) | LS-pure · EC-sub P50 risk (0,56) | relative P50 risk: 0.99 -> 0.85 | Helped |
| add features (ablation) | LS-pure · EC-sub P50 wk(33) | relative P50 risk: 0.99 -> 0.94 | Helped |
| add features (ablation) | LS-pure · EC-all P90 risk (0,56) | relative P90 risk: 1.11 -> 0.95 | Helped |
| add features (ablation) | LS-pure · EC-all P50 wk(33) | relative P50 risk: 1.05 -> 0.98 | Helped |
| ignore out of stock signal vs treat as missing (ablation) | latent state forecaster · item partially out of stock | bias | Helped |
| LS-pure vs NegBin on Parts | LS-pure · Parts P90 (0,2) | relative P90 risk: 1.00 -> 1.08 | Hurt |
| LS-pure vs NegBin on EC-sub | LS-pure · EC-sub P90 wk(33) | relative P90 risk: 1.00 -> 0.99 | No clear effect |
| ETS vs NegBin on EC-sub | ETS · EC-sub P50 wk(33) | relative P50 risk: 1.00 -> 1.18 | Hurt |
| ETS vs NegBin on Parts | ETS · Parts P50 dy(8) | relative P50 risk: 1.00 -> 1.38 | Hurt |
| scale to EC-all | LS-feats · EC-all vs EC-sub P90 (21,84) | relative P90 risk: 0.73 -> 0.86 | Mixed |
Closest papers by meaning
- GMP-AR: Granularity Message Passing and Adaptive Reconciliation for Temporal Hierarchy Forecasting (AAAI 2024 · similarity 0.82)
- Treeffuser: probabilistic prediction via conditional diffusions with gradient-boosted trees (NeurIPS 2024 · similarity 0.81)
- GCF: Estimating Unobserved Demand Using Graph Causal Forecasting (AAAI 2025 · similarity 0.81)
- Pareto-Optimality, Smoothness, and Stochasticity in Learning-Augmented One-Max-Search (ICML 2025 · similarity 0.81)
- Adaptive Market Making with Inventory Constraints via Online Learning (AAAI 2025 · similarity 0.80)
- Contextual Online Pricing with (Biased) Offline Data (NeurIPS 2025 · similarity 0.80)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.