Downloads · 30 days
10
20% of all-time downloads
fraud-model-aura
KS-Vijay/fraud-model-aura
fraud-model-aura is a text classification model from KS-Vijay. Use it when you need a label for a piece of text. The card lists the license as apache-2.0.
This model uses DistilBERT to classify whether a given grievance or complaint text contains fraudulent intent or behavior. It is trained as part of an intelligent Grievance Redressal Platform to auto-detect fraud-rela…
All-time downloads
49
Public
Parameters
67M
268 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors268 MB · 100%
At a glance
- Task
- Text Classification
- License
- apache-2.0
- Model type
- distilbert
- Access
- Public
- Created
- Apr 7, 2025
- Updated
- Apr 7, 2025
- SHA
- fdb86c2d
Try a prompt
Base models
Model card
From the Hugging Face model README
🕵️♂️ Fraud Model Aura (KS-Vijay)
This model uses DistilBERT to classify whether a given grievance or complaint text contains fraudulent intent or behavior. It is trained as part of an intelligent Grievance Redressal Platform to auto-detect fraud-related issues in startup complaints.
🧠 Use Case
Detects if the complaint relates to fraud:
FraudLegitimate
This helps startups or service providers to flag, escalate, or triage suspicious reports quickly.
🔍 Model Summary
- Model Type: Text Classification
- Architecture: DistilBERT (uncased)
- Output Labels:
Fraud,Legitimate - Weights Format:
safetensors - Dataset: Custom (based on complaints.csv)
- Training Framework: PyTorch using 🤗
transformers
📥 Example Input
"I think someone is misusing our company’s KYC information to open fake accounts."
- Task
- Text Classification
- Type
- distilbert
- License
- apache-2.0
- Languages
- en
- Created
- Apr 7, 2025
- Updated
- Apr 7, 2025