This repository contains a machine learning-based system for detecting fraudulent credit card transactions using Isolation Forest and One-Class SVM algorithms. The project includes data preprocessing, exploratory data analysis (EDA), model training, evaluation, and real-time fraud prediction via a Streamlit web interface.

Deep learning fraud detection system using MLP, Autoencoder, and VAE for imbalanced credit card data. Built with PyTorch, it includes SMOTE, RobustScaler preprocessing, FastAPI REST API for real-time predictions, and an interactive dashboard. Features EDA, ROC-AUC/PR-AUC evaluation, and unit tests.

The online payment fraud analysis project follows several step approach from data preprocessing through model evaluation, result comparison and final model selection, using transaction patterns to identify fraud indicators including account draining, suspicious transfers, and balance inconsistencies.