FRAUD TRANSCATION DETECTION

Vist webpage: Streamlit App

Abstract

The idea aims to develop a fraud detection system for financial transactions that can accurately identify fraudulent activities and prevent potential losses. By leveraging machine learning algorithms and advanced data analytics techniques, aim to create a robust and effective solution that enhances security and trust in financial transactions.

Features

• EDA on transaction data: Detailed visualizations on banking transcation trends.
• Web deployment for induviduals: Check if your transcations are fraudulant or not in webpage.
• Analyze bulk transactions: Upload a transactions data CSV in required format to analyze bulk data (suitable for banks).

Technologies Used

• Backend: Python (Flask), Streamlit
• Frontend: HTML, CSS
• Data Visualization: Matplotlib, Seaborn
• Database: CSV
• Other Libraries: Pandas, NumPy, Sklearn, Imblearn

Setup Instructions (for Flask)

Follow the steps below to set up and run the project locally.

1. Clone the Repository:

   git clone https://github.com/Anja-c1511/Fraud_Transaction_Detection.git

2. Set up a Python Virtual Environment:

   python -m venv env
   source env/bin/activate  # For Linux/macOS
   env\Scripts\activate     # For Windows

3. Install Dependencies:

   pip install -r requirements.txt

4. Run the Flask App:

   Flask --app flask/app run

5. Open in Browser: Navigate in your web browser.

Usage

1. Enter your inputs in required columns.
2. Enter Submit button