Fraud Detection System

This project is a machine learning web application that predicts whether a financial transaction is fraudulent or legitimate based on transaction details.

The goal of this project is to demonstrate how machine learning models can be used to detect suspicious financial activity and assist in preventing fraud in digital payment systems.

---

Features

• Predict fraudulent transactions using a trained machine learning model
• Interactive web interface built with Streamlit
• Real-time prediction based on user input
• Machine learning pipeline implemented using scikit-learn

---

Technology Stack

• Python
• Pandas
• Scikit-learn
• Streamlit
• Joblib

---

Project Structure

fraud-detection-system
│
├── Streamlit_app.py               # Streamlit web application
├── fraud_detection_pipeline.pkl   # Trained machine learning pipeline
├── requirements.txt               # Project dependencies
├── README.md                      # Project documentation
└── data/                          # Dataset (not included due to size)

---

How to Run the Project

1. Clone the repository

git clone https://github.com/RoseJ02/fraud-detection-system.git

2. Navigate to the project directory

cd fraud-detection-system

3. Install dependencies

pip install -r requirements.txt

4. Run the Streamlit application

streamlit run Streamlit_app.py

The application will open in your web browser.

---

Input Features

The model uses the following transaction details as input:

• Transaction type
• Transaction amount
• Sender old balance
• Sender new balance
• Receiver old balance
• Receiver new balance

---

Output

The model predicts whether a transaction is:

• Fraudulent transaction
• Legitimate transaction

---

Dataset

The dataset used for training is not included in this repository due to its large size.

---