Update v2 model card

README.md

@@ -1,49 +1,50 @@
 ---
 library_name: sklearn
 tags:
+  - fairrelay
   - logistics
   - xgboost
   - sklearn
   - tabular-regression
-  - eta-prediction
   - delivery-time
-  - fairrelay
+  - eta-prediction
 datasets:
   - Cainiao-AI/LaDe-D
-  - electricsheepafrica/africa-synth-retail-and-ecommerce-last-mile-delivery-data-nigeria
 license: mit
 ---
 
-# FairRelay — Delivery Time Estimation Model
+# FairRelay — Delivery Time Estimation Model (v2)
 
 Part of the **[FairRelay](https://github.com/MUTHUKUMARAN-K-1/FairRelay)** AI logistics platform.
 
 ## Model Description
 
-Delivery Time Estimation Model
+Predicts total delivery time (in minutes) for a courier's daily route based on package count, stops, distance, and temporal features. Trained on real last-mile delivery data from **Cainiao-AI/LaDe-D** (KDD 2023, Shanghai + Hangzhou, ~70K courier-days) combined with physics-informed synthetic data calibrated to FairRelay's `estimate_route_time()` formula.
 
-**Type**: XGBRegressor Pipeline  
-**Framework**: scikit-learn Pipeline + XGBoost  
-**Task**: Regression
+**Type**: XGBRegressor Pipeline (StandardScaler + XGBoost)
+**Task**: Regression (delivery time in minutes)
 
 ## Performance
 
-- **R²**: 0.0785
-- **MAE**: 169.16 minutes
-- **RMSE**: 199.50 minutes
-- **CV R² (5-fold)**: -0.0300 ± 0.0507
-
+- **R²**: 0.6206
+- **MAE**: 73.01 minutes
+- **RMSE**: 105.68 minutes
+- **Median AE**: 46.03 minutes
+- **MAPE**: 33.4%
+- **CV R² (5-fold)**: 0.5580 ± 0.2773
 
 ## Input Features
 
 | Feature | Importance |
 |---------|-----------|
-| `distance_km` | 0.0974 |
-| `hour_of_day` | 0.2686 |
-| `day_of_week` | 0.1451 |
-| `is_weekend` | 0.0534 |
-| `num_packages` | 0.1910 |
-| `num_stops` | 0.2445 |
+| `num_packages` | 0.1579 |
+| `num_stops` | 0.2307 |
+| `total_distance_km` | 0.1216 |
+| `avg_distance_km` | 0.0709 |
+| `spatial_spread_km` | 0.1569 |
+| `start_hour` | 0.0713 |
+| `active_hours` | 0.0852 |
+| `packages_per_stop` | 0.1055 |
 
 
 ## Usage
@@ -51,23 +52,24 @@ Delivery Time Estimation Model
 ```python
 from skops import io as sio
 from huggingface_hub import hf_hub_download
+import numpy as np
 
 # Download and load
 model_path = hf_hub_download(repo_id="muthuk1/fairrelay-delivery-time", filename="model.skops")
 untrusted = sio.get_untrusted_types(file=model_path)
 model = sio.load(model_path, trusted=untrusted)
 
-# Predict
-import numpy as np
-features = np.array([[0.0, 0.0, 0.0, 0.0, 0.0, 0.0]])
-prediction = model.predict(features)
+# Predict: [num_packages, num_stops, total_distance_km, avg_distance_km,
+#            spatial_spread_km, start_hour, active_hours, packages_per_stop]
+features = np.array([[25, 15, 12.5, 0.83, 5.2, 9, 6, 1.67]])
+predicted_minutes = model.predict(features)
+print(f"Estimated delivery time: {predicted_minutes[0]:.0f} minutes")
 ```
 
 ## Training Data
 
-- **Cainiao-AI/LaDe-D**: Real last-mile delivery data from Shanghai (KDD 2023)
-- **Africa Synth Last-Mile**: Synthetic Nigerian delivery data
-- **FairRelay Synthetic**: Physics-informed synthetic data calibrated to FairRelay's deterministic formulas
+- **Cainiao-AI/LaDe-D**: Real last-mile delivery data (Shanghai + Hangzhou splits, ~70K courier-days from 1.5M+ individual deliveries)
+- **FairRelay Synthetic**: 20K samples with physics-informed noise, calibrated to `estimate_route_time()` formula
 
 ## Part of FairRelay