This is an Online Transaction Fraud Detection System (FDS) to detect payment frauds. Made using Django.

This repository outlines various solutions using AWS Cloud's AIML services to detect fraud faster.

A machine learning-based fraud detection system that analyzes transaction patterns to identify potentially fraudulent activities. Features a Streamlit web interface for real-time predictions. Note: Model is currently in development with ongoing improvements planned.

Real-time AML transaction scoring pipeline on AWS: Lambda, S3, DynamoDB, SNS, IAM Roles and Terraform (IaC)

AI-powered behavioural fraud detection system for UPI transactions using FastAPI and Streamlit.

Fraud investigation tutorial across 9 phases — same 6 cases, progressively adding LangGraph, tools, HITL, multi-agent coordination, and LangSmith observability

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

End-to-end fraud detection — JAX neural nets from scratch, multi-objective Optuna (Pareto recall vs precision), custom Precision@K/Recall@K/Lift@K metrics, SHAP explainability, and GitHub Actions CI/CD. No ML framework shortcuts.

Real-time transaction risk monitoring system with rule-based fraud detection, REST API, and a React dashboard. Built with Node.js, Express, and SQLite.

data-engineering aws pyspark fraud-detection data-pipeline etl-pipeline aws-glue data-lake medallion-architecture banking-analytics

Full-stack Flask insurance workflow system with policy management, QR verification, Twilio SMS alerts, NLP sentiment analysis, and Decision Tree-based fraud detection (77% accuracy).

We address the 'Resilience Gap' in modern autonomous systems. As enterprises transition from AI tools to Agentic AI, the risk of operational drift and systemic capture increases exponentially. Our mission is to provide the Cohesion Layer necessary for secure, sovereign execution.

AI Deepfake and Fraud Detection

An open-source project for ROSP Lab based on Fraud Detection using ML

Credit Card Fraud Detection using SMOTE, XGBoost, and LightGBM.

Detect fraudulent transactions and accounts in a vast dataset

A ML-based web app that detects fraudulent e-commerce transactions in real time. Features SMOTE for class balancing, Logistic Regression & Random Forest models, and an interactive form UI for live predictions. Built with Python, scikit-learn, and Flask.

Probabilistic identity continuity for hostile browser environments. Drift-tolerant confidence scoring that tracks returning visitors across cookie deletion, VPNs, and anti-fingerprinting - without PII.