Open source AML and Fraud Detection using Machine Learning for Real-Time Transaction Monitoring

Welcome to an open-source transaction monitoring engine! This product is designed to simplify the definition and management of business rules while also offering a scalable infrastructure for rule execution and backtesting.

Blnk Watch is a domain-specific language (DSL) for creating real-time transaction monitoring rules. It enables you to define conditions and automated actions for detecting fraud, enforcing limits, and staying compliant. A Watch script is declarative: you describe what to detect and what action to take—the engine handles evaluation at runtime.

Name Matching ML model for entity resolution and transaction monitoring

⚡ Real-time fraud & anomaly detection system for streaming transactions. Built with Kafka Streams + Isolation Forest ML. Low-latency processing, online learning, and scalable architecture for detecting fraud patterns in transaction data. 🚨🔍

End-to-end KYC/AML compliance data analysis using mock datasets. Includes customer risk scoring, suspicious transaction flagging, and compliance reporting in Python (Pandas, Matplotlib).

Enterprise-grade fraud & AML detection with ML and deep learning (XGBoost, LightGBM, Autoencoder, LSTM, Transformer). Real-time API, explainability (SHAP), BI export, Streamlit dashboard. PaySim-compatible.

This project is a cryptocurrency automation tool designed to interact with blockchain data and exchanges for analytical and operational purposes. The bot helps automate routine tasks, monitor transactions, and process market-related information in real time.

Analyse alert-to-SAR conversion rates and recommend threshold adjustments for transaction monitoring rule engines.

Full-stack digital payments compliance engine—UPI/RTGS simulator, AML rule engine, ML-based STR detection, SHAP explainability, and audit-ready dashboards.

A simple CLI tool to monitor and log Solana wallet payment transactions in real-time

False-Positive Reduction Lab : rule-based transaction monitoring with threshold tuning and cost trade-offs. Demonstrates how adjusting detection rules reduces noise, lowers investigation cost, and improves fraud catch.

Practical repository for transaction monitoring scenarios, red flags, suspicious activity indicators, and AML-focused analytical review.

An AI-powered fraud detection system that uses machine learning to detect suspicious financial transactions in real time. Features include interactive dashboards, secure authentication, and comprehensive reporting for fintech risk analysis.

Multi-agent fraud detection pipeline for the Reply AI Challenge, combining deterministic transaction features, communications analysis, and a LangGraph supervisor to detect suspicious transactions with Langfuse tracing and OpenRouter-powered LLM reasoning.

Professional toolkit for crypto investigations, AML/CTF intelligence, blockchain risk analysis, and compliance research.

USDT TRC-20 payment processor with wallet pool management. Extracted from production gambling platform. FastAPI + PostgreSQL + TronGrid API integration.

SQL-based AML transaction monitoring engine simulating rule-based detection and alert generation.

High-performance blockchain monitoring service supporting Ethereum, BSC, and Bitcoin with real-time wallet tracking and multi-chain architecture

A full-stack fintech case resolution system with multi-agent automation for fraud detection, dispute management, and automated actions with explainable traces and observability.