nzgl21 commited on
Commit
80920d1
ยท
verified ยท
1 Parent(s): 89830e4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +43 -9
README.md CHANGED
@@ -22,18 +22,52 @@ widget:
22
  base_model:
23
  - distilbert/distilbert-base-uncased
24
  ---
 
25
  # ๐ŸŽฏ Customer Ticket Routing & Intent Classifier (DistilBERT)
 
26
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) for **intent classification and automated customer ticket routing** across **77 banking categories** on the [Banking77](https://huggingface.co/datasets/PolyAI/banking77) dataset.
 
27
  It is designed for production microservices to automatically route incoming customer support requests to appropriate departments.
28
- * ๐Ÿ”— **Full Service & Microservice Code:** [GitHub Repository (FastAPI + ONNX + Docker)](https://github.com/your-username/ticket-routing-service)
29
  ---
 
30
  ## ๐Ÿ“Š Benchmark & Evaluation Results
31
- Evaluated on the official `Banking77` test set (3,080 samples):
 
 
32
  | Metric | Score |
33
- | :--- | :---: |
34
- | **Test Macro $F_1$** | **0.9175** |
35
- | **Test Accuracy** | **0.9175** |
36
- | **Test Precision (Macro)** | **0.9209** |
37
- | **Test Recall (Macro)** | **0.9175** |
38
- | **Test Loss** | **0.3478** |
39
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
  base_model:
23
  - distilbert/distilbert-base-uncased
24
  ---
25
+
26
  # ๐ŸŽฏ Customer Ticket Routing & Intent Classifier (DistilBERT)
27
+
28
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) for **intent classification and automated customer ticket routing** across **77 banking categories** on the [Banking77](https://huggingface.co/datasets/PolyAI/banking77) dataset.
29
+
30
  It is designed for production microservices to automatically route incoming customer support requests to appropriate departments.
31
+
32
  ---
33
+
34
  ## ๐Ÿ“Š Benchmark & Evaluation Results
35
+
36
+ Evaluated on the official Banking77 test set (3,080 samples):
37
+
38
  | Metric | Score |
39
+ | :--- | :--- |
40
+ | Test Macro F1 | 0.9175 |
41
+ | Test Accuracy | 0.9175 |
42
+ | Test Precision (Macro) | 0.9209 |
43
+ | Test Recall (Macro) | 0.9175 |
44
+ | Test Loss | 0.3478 |
45
+
46
+ ### Comparison with Baselines
47
+
48
+ | Approach | Trainable Params | Test Macro F1 | Test Accuracy | Test Loss |
49
+ | :--- | :--- | :--- | :--- | :--- |
50
+ | Baseline (TF-IDF + LogReg + Bayes) | - | 0.8901 | - | - |
51
+ | DistilBERT + LoRA (r=32) | ~2.6% (~1.8M) | 0.9132 | 0.9133 | 0.3189 |
52
+ | DistilBERT (Full Fine-Tuning) | 100% (66.9M) | 0.9175 | 0.9175 | 0.3478 |
53
+
54
+ ---
55
+
56
+ ## ๐Ÿš€ How to Use
57
+
58
+ ### 1. Using transformers pipeline (Quickest)
59
+
60
+ ```python
61
+ from transformers import pipeline
62
+
63
+ classifier = pipeline(
64
+ "text-classification",
65
+ model="nzgl21/ticket-routing-distilbert"
66
+ )
67
+
68
+ # Example ticket
69
+ ticket = "I noticed an unknown fee charged on my credit card statement."
70
+ prediction = classifier(ticket)
71
+
72
+ print(prediction)
73
+ # Output: [{'label': 'card_payment_fee_charged', 'score': 0.964}]