Automatic text summarization with a pre-trained encoder and a transformer decoder (BERT). Provides a web interface for the models using Django

ML Python - Logistic Regression (GLM)

Production-ready customer churn prediction API built with FastAPI, scikit-learn, and Docker.

An ML API to compute similarity scores between meta information about sentence examples.

An ML API to compute similarity scores between shingled sentence examples.

Production-style ML inference API for credit card fraud detection using FastAPI and XGBoost

Production‑ready MLOps pipeline: Kafka, ClickHouse, FastAPI, Streamlit, Prometheus, Grafana, CI/CD

ML-API Built using FastAPI for predicting food images and recommending food based on user dietary preferences

Production-ready FastAPI backend for NABTA smart agriculture platform with ML inference, WeatherAPI integration, Docker support, and interactive Swagger documentation.

🚀 A multi-container app using Docker Compose with a MySQL DB and a Python-based ML API. Accepts user input, returns predictions, and logs results with response time into the database.

Loan approval prediction using machine learning with data preprocessing, exploratory data analysis, model comparison, and performance evaluation.

Fraud Detection REST API project built with FastAPI and LightGBM Binary Classifier.

Cost-sensitive fraud detection REST API using XGBoost and FastAPI, optimized for financial loss minimization and deployed on Render.

SkinGlance is a smart Android application designed to detect skin cancer in real-time using deep learning. By capturing or selecting an image of a skin lesion, the app connects to a cloud-based AI backend to provide instant predictions with high accuracy.

FastAPI + Docker ML API for loan default risk prediction with model versioning, tests, example requests, and reproducible training workflow.

A FastAPI and ML-powered heart disease classification engine comparing five leakage-safe scikit-learn pipelines with reproducible evaluation and live predictions.

Personal Knowledge Base RAG API – FastAPI-based RAG system for querying TXT/PDF documents using embeddings, vector search (FAISS/Qdrant), optional reranking, and Groq LLM inference.

Predicting Number of Bedrooms given some covariates

Real-time fraud detection system built with FastAPI, Streamlit, and scikit-learn, featuring phishing email classification, audio spoof detection, and multi-modal risk fusion.

ML model serving project built with FastAPI and Docker. The API exposes prediction, health check and model info endpoints, with configuration prepared for deployment on Google Cloud Run