This project implements a Credit Card Fraud Detection system using both supervised and unsupervised machine learning models. It demonstrates data preprocessing, exploratory data analysis, model training, evaluation, and real-time fraud detection simulation.

• Data preprocessing with scaling and feature selection.
• Exploratory Data Analysis (EDA) to understand fraud vs normal transaction distribution.
• Supervised learning using Random Forest Classifier.
• Unsupervised anomaly detection using Isolation Forest.
• Real-time transaction risk simulation.
• Visualization of predicted fraudulent transactions.

• The project uses the creditcard.csv dataset, which contains anonymized credit card transactions.
• Features include numerical PCA components (V1–V28), Amount, Time, and the target class (Class: 0 = Normal, 1 = Fraud).

1. Clone the repository:

git clone <repository-url>