fraud-detection-using-machine-learning

Bank card fraud detection using machine learning. Web application using Streamlit framework

A data science project focused on identifying fraudulent transactions in highly imbalanced datasets using Python and Scikit-Learn.

Hybrid deep learning fraud detection system using CNN, BiLSTM, and Attention mechanisms for UPI transaction classification.

A full-stack phishing and fraud risk analysis system with FastAPI endpoints for scanning URLs, emails, social text, QR codes, bulk URLs, and transactions. It returns explainable outputs including risk score, label, indicators, and educational guidance. The scoring engine combines heuristic indicators with model probabilities.

This project demonstrates the use of a Self-Organizing Map (SOM) for fraud detection in a dataset. The dataset contains transaction records, and the goal is to identify potential fraudulent transactions using unsupervised learning techniques.

ML project to detect fraudulent job postings using NLP & Scikit-learn

A machine learning pipeline that detects fraudulent transactions using a Random Forest Classifier on synthetic data.

Modular fintech intelligence system with authentication, ML-based risk detection, anomaly analysis, live NSE/BSE tracking, and stock price prediction.

Graph neural network system that detects money laundering, fraud patterns, and security threats in blockchain transactions and smart contracts.

End-to-end payment fraud detection pipeline using Spark (Batch/Streaming), Airflow, Kafka, and MariaDB. Implements a Medallion Architecture with real-time rule-based anomaly detection.

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

This is a fraud detection algorithm that is designed to detect fraudulent activity in online in-game markets using a combination of unsupervised learning and a rule based approach.

Detecting fraudulent credit card transactions using machine learning techniques, with a focus on handling imbalanced datasets.

AI-powered system to detect and flag suspicious financial transactions in real time using Python, Excel, and SQL Server. Includes automated form validation, unsupervised anomaly detection (Isolation Forest), and live dashboard integration.

Unsupervised anomaly detection to identify low-credibility reviewers on the Yelp dataset (2M users) using behavioral clustering and DuckDB.

ENSAE-ENSAI Formation Continue (Cepe)/OpenClassrooms Data Analyst 2022-2023 - Projet 10

End-to-end fraud detection system with time-aware validation, advanced feature engineering, LightGBM/XGBoost/CatBoost ensemble, FastAPI prediction service, and Streamlit frontend.

Advanced anomaly detection system using graph neural networks and time series analysis to identify fraudulent transactions, money laundering patterns, and market manipulation in real-time financial data streams.

An AI-powered system that detects water tanker fraud in real-time using machine learning, FastAPI backend, and a live monitoring dashboard.

Analyseur de flux financier, inspiré de FraudModelValidator - ML Boosted