j2damax commited on
Commit
e08d1df
·
verified ·
1 Parent(s): fd6ffd1

Version sync: sklearn 1.7.2 retrain + provenance

Browse files
Files changed (1) hide show
  1. README.md +11 -2
README.md CHANGED
@@ -30,7 +30,7 @@ model-index:
30
 
31
  Predicts probability that a hotel booking will be cancelled (Sri Lankan hospitality context). The champion model is **XGBoost**; threshold based decisions currently use **0.35000000000000003** (see `champion_meta.json`).
32
 
33
- _Last updated: 2025-10-05 16:16 UTC_
34
 
35
  ## Key Metrics (Holdout)
36
  | Metric | Value |
@@ -42,7 +42,16 @@ _Last updated: 2025-10-05 16:16 UTC_
42
  | Accuracy | 0.8613786749308987 |
43
 
44
  ## Top Features (SHAP importance)
45
- (Not available)
 
 
 
 
 
 
 
 
 
46
 
47
  ## Quickstart
48
  ```python
 
30
 
31
  Predicts probability that a hotel booking will be cancelled (Sri Lankan hospitality context). The champion model is **XGBoost**; threshold based decisions currently use **0.35000000000000003** (see `champion_meta.json`).
32
 
33
+ _Last updated: 2025-10-05 16:43 UTC_
34
 
35
  ## Key Metrics (Holdout)
36
  | Metric | Value |
 
42
  | Accuracy | 0.8613786749308987 |
43
 
44
  ## Top Features (SHAP importance)
45
+ - deposit_type
46
+ - country__te
47
+ - market_segment
48
+ - total_of_special_requests
49
+ - lead_time
50
+ - required_car_parking_spaces
51
+ - assigned_room_type
52
+ - customer_type_target_encoded
53
+ - reserved_room_type
54
+ - previous_cancellations
55
 
56
  ## Quickstart
57
  ```python