← Back to portfolio
🎓 Graduation Project
NLP Text Classification System
Multi-class text classification with BERT + LSTM, deployed as a real-time Flask API.
Problem
Manually sorting large volumes of text — support tickets, documents, reviews — doesn't scale. Teams need automated classification that's both accurate and fast enough to run in production.
Approach
Designed and trained a deep learning NLP pipeline combining BERT and LSTM architectures for multi-class text classification, then wrapped the trained model in a production-ready Flask REST API for real-time inference.
Results
- 96% accuracy on the test set
- Real-time inference via a deployed Flask REST API
Want the full picture, or think this kind of work fits a role you're hiring for?