Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: en
|
| 3 |
+
library_name: joblib
|
| 4 |
+
tags:
|
| 5 |
+
- text-classification
|
| 6 |
+
- embeddings
|
| 7 |
+
- business
|
| 8 |
+
- data-engineering
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Business Issue Allocation Classifier
|
| 12 |
+
|
| 13 |
+
A text classifier that maps a natural language business problem description to the most likely data engineering solution category.
|
| 14 |
+
|
| 15 |
+
## Model Details
|
| 16 |
+
|
| 17 |
+
- **Classifier:** SVM (Support Vector Machine)
|
| 18 |
+
- **Embedding model:** `sentence-transformers/all-mpnet-base-v2`
|
| 19 |
+
- **Classes:** 9 (stream_processing, etl_pipeline, data_warehouse, data_lake, api_integration, ml_feature_store, data_caching, data_governance, data_quality)
|
| 20 |
+
- **Accuracy:** 88.2%
|
| 21 |
+
- **Macro F1:** 88.4%
|
| 22 |
+
|
| 23 |
+
## How to Use
|
| 24 |
+
|
| 25 |
+
Clone the full project from GitHub and run:
|
| 26 |
+
|
| 27 |
+
```python
|
| 28 |
+
from src.inference import Predictor
|
| 29 |
+
predictor = Predictor()
|
| 30 |
+
result = predictor.predict("We need to detect fraud before transactions are approved.")
|
| 31 |
+
print(result["predicted_label"])
|
| 32 |
+
```
|
| 33 |
+
|
| 34 |
+
## Dataset
|
| 35 |
+
|
| 36 |
+
[dianamikova/business-issue-allocation](https://huggingface.co/datasets/dianamikova/business-issue-allocation)
|
| 37 |
+
|
| 38 |
+
## GitHub
|
| 39 |
+
|
| 40 |
+
[github.com/dianamikova/business-issue-allocation](https://github.com/dianamikova/business-issue-allocation)
|