Downloads · 30 days
4
3% of all-time downloads
container-appt-ranker
rhlprj/container-appt-ranker
container-appt-ranker is a machine learning model from rhlprj. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Calibrated dual-head LightGBM model for ranking container appointment slots.
All-time downloads
124
Public
Repo size
66.7 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.txt7 MB · 99%
At a glance
- Model type
- lightgbm+isotonic
- Access
- Public
- Created
- Apr 30, 2026
- Updated
- Apr 30, 2026
- SHA
- 407be4c8
Model card
From the Hugging Face model README
Container Appointment Ranking
Calibrated dual-head LightGBM model for ranking container appointment slots.
Architecture: GBDT + Neural Blend (Option 3)
- LightGBM for tabular features + hash-bucket embeddings
- Dual-head: Head A (P_accept) + Head B (P_zero_rehandle)
- Isotonic calibration on realized val slots
- Combined score = 0.6 * P_accept + 0.4 * P_zero_rehandle
Metrics
| Baseline | Proposed | Target | |
|---|---|---|---|
| AUC Head A | 0.638 | 0.710 | ≥ 0.82 |
| Brier Head A | 0.186 | 0.174 | ≤ 0.18 |
| AUC Head B | 0.724 | 0.723 | ≥ 0.74 |
| NDCG@3 | 0.726 | 0.922 | ≥ 0.68 |
| Cold AUC | 0.639 | 0.688 | ≥ 0.72 |
Files
inference.py:predict(container_features, trucker_id, candidate_slots)data/synth.py: Synthetic data generator (seed=42)train.py/train_slots.py: Baseline + proposed trainingeval.ipynb: Reproduces all metricsmodel_card.md: Intended use, limitations, failure modes
- Type
- lightgbm+isotonic
- Created
- Apr 30, 2026
- Updated
- Apr 30, 2026