Research map / Probabilistic and scientific modeling / Molecules and proteins
Duration-of-Stay Storage Assignment under Uncertainty
Michael Lingzhi Li, Elliott Wolf, Daniel Wintz
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| use ParallelNet instead of CNN-LSTM | DoS distribution prediction · Testing Set | MSLE: 0.4812 -> 0.4419 | Improved |
| use ParallelNet instead of CNN-LSTM | DoS distribution prediction · Testing Set | MAPE: 41% -> 29% | Improved |
| use ParallelNet instead of CNN-LSTM | DoS distribution prediction · Extended Testing Set | MSLE: 0.9021 -> 0.7945 | Improved |
| use ParallelNet instead of CNN-LSTM | DoS distribution prediction · Extended Testing Set | MAPE: 80% -> 51% | Improved |
| add the final co-training output layer rather than averaging the CNN and GRU outputs | ParallelNet · Testing Set | MSLE: 0.5024 -> 0.4419 | Improved |
| add product group (ablation) | ParallelNet · Testing Set | MSLE: 0.6149 -> 0.4419 | Improved |
| add date of arrival (ablation) | ParallelNet · Testing Set | MSLE: 0.5723 -> 0.4419 | Improved |
| add customer type (ablation) | ParallelNet · Testing Set | MSLE: 0.5687 -> 0.4419 | Improved |
| add all nontextual features (ablation) | ParallelNet · Testing Set | MSLE: 0.8312 -> 0.4419 | Improved |
| add textual features (ablation) | ParallelNet · Testing Set | MSLE: 0.9213 -> 0.4419 | Improved |
| deploy DoS-based storage assignment | Facilities A and B · Live warehouses | average placement percentile: 51% -> 41%; 50% -> 39% | Improved |
Closest papers by meaning
- Robust Out-of-Order Retrieval for Grid-Based Storage at Maximum Capacity (AAAI 2026 · similarity 0.83)
- Online Allocation with Unknown Shared Supply (NeurIPS 2026 · similarity 0.80)
- Treeffuser: probabilistic prediction via conditional diffusions with gradient-boosted trees (NeurIPS 2024 · similarity 0.79)
- Learning Production Functions for Supply Chains with Graph Neural Networks (AAAI 2025 · similarity 0.78)
- Adaptive Multi-Faceted Service Capabilities Co-Prediction for Nationwide Terminal Stations in Logistics (AAAI 2025 · similarity 0.78)
- Procurement Auctions with Predictions: Improved Frugality for Facility Location (NeurIPS 2025 · similarity 0.78)
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.
