Update README.md

README.md

@@ -18,7 +18,7 @@ library_name: xgboost
 
 # Article Extraction Outcome Classifier
 
-A fast, lightweight classifier that categorizes web article extraction outcomes with 99.99% accuracy.
+A fast, lightweight classifier that categorizes web article extraction outcomes with 90% accuarcy
 
 ## Model Description
 
@@ -36,21 +36,19 @@ This model predicts whether HTML extraction succeeded, failed, or returned a non
 
 ## Performance
 
-**Test Set Results (13,852 samples):**
+~90% accuracy on a large, real-world test set, with strong performance on dominant classes
 
-```
-Overall Accuracy: 99.99%
-Macro F1: 0.7976
-
-                           precision    recall  f1-score   support
-   full_article_extracted     0.9985    1.0000    0.9992      1312
-partial_article_extracted     1.0000    0.9783    0.9890        92
-       api_provider_error     1.0000    1.0000    1.0000       627
-            other_failure     0.0000    0.0000    0.0000         0
-    full_page_not_article     1.0000    1.0000    1.0000     11821
-```
+| Class                     | Precision | Recall | F1-score | Support |
+| ------------------------- | --------- | ------ | -------- | ------- |
+| full_article_extracted    | 0.91      | 0.84   | 0.87     | 1,312   |
+| partial_article_extracted | 0.76      | 0.63   | 0.69     | 92      |
+| api_provider_error        | 0.95      | 0.93   | 0.94     | 627     |
+| other_failure             | 0.41      | 0.28   | 0.33     | 44      |
+| full_page_not_article     | 0.92      | 0.97   | 0.94     | 11,821  |
+| **Accuracy**              | —         | —      | **0.90** | 13,852  |
+| **Macro Avg**             | 0.79      | 0.73   | 0.72     | 13,852  |
+| **Weighted Avg**          | 0.90      | 0.90   | 0.90     | 13,852  |
 
-## Usage
 
 ```python
 import numpy as np