NLP analysis of consumer complaints narratives in the financial industry
-
Updated
Oct 16, 2025 - Jupyter Notebook
NLP analysis of consumer complaints narratives in the financial industry
This project benchmarks vision (MobileNet, ResNet20) and NLP (DistilBERT) models via server inferencing APIs, built on a FastAPI backend. Clients access these APIs for model inference. The work is dedicated to fulfilling the Master’s thesis in AI & ML.
Production-ready ML inference service with Kubernetes, CI/CD, monitoring, and orchestration
Sentiment analysis of Google reviews from 12 Streatham restaurants using NLP (VADER & DistilBERT) to uncover insights hidden beyond star ratings — from service quality to wait times and customer emotion trends.
This project benchmarks vision (MobileNet, ResNet20) and NLP (DistilBERT) models across server vs. client inference, using backend servers and ONNX-converted local models. It evaluates latency, UX, accuracy, and performance, dedicated to fulfilling the Master’s thesis in AI & ML.
🚀 Build a production-grade ML inference service with a robust MLOps pipeline for seamless deployment and management.
Add a description, image, and links to the distillbert topic page so that developers can more easily learn about it.
To associate your repository with the distillbert topic, visit your repo's landing page and select "manage topics."