IT Service Desk Ticket Classifier

A DistilBERT-based model for classifying IT support tickets into 12 categories.

Model Description

This model classifies IT service desk tickets into the following categories:

Category Description
Access Management Login, permissions, MFA issues
Backup Backup and restore operations
Database SQL, database connectivity
Email Outlook, calendar, mailbox
General Inquiry How-to questions
Hardware Physical device issues
Network WiFi, VPN, connectivity
Other Miscellaneous
Printing Printer and scanning
Security Threats, breaches, security
Software Application issues
Storage OneDrive, SharePoint, drives

Training Details

  • Base Model: DistilBERT (distilbert-base-uncased)
  • Training Data: 5,760 IT support tickets
  • Loss Function: Focal Loss (for class imbalance)
  • Framework: PyTorch + Transformers

Usage

from huggingface_hub import hf_hub_download
import torch

# Download model
model_path = hf_hub_download(
    repo_id="YOUR_USERNAME/ticket-classifier",
    filename="ticket_classifier.pt"
)

# Load model
checkpoint = torch.load(model_path, map_location="cpu")

Performance

Achieves 85%+ macro F1 score across 12 categories.

License

MIT

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Space using TuShar2309/ticket-classifier 1