Fraud Transaction Detection

Overview

This project focuses on the development of a machine learning model aimed at detecting fraudulent transactions based on transaction details. The model is designed to analyze various features of a transaction and determine whether it is normal or fraudulent.

Features

• Utilizes transaction details as inputs for fraud detection.
• Performs meticulous data preparation on a dataset with 154 features.
• Includes processes such as:
  • Correlation analysis
  • Incorporation of domain-specific data
  • Handling null values
  • Creation of new features through feature engineering

Methodology

• Developed and fine-tuned a machine learning model to achieve nearly 94% accuracy.
• Employed various machine learning algorithms and compared their performance to identify the most effective approach.

Repository Structure

• Online_fraud_detection_practice.ipynb: Jupyter Notebook containing data preparation processes, training and evaluating machine learning models.
• requirements.txt: List of dependencies required to run the project.
• README.md: Overview of the project and instructions for usage.

Usage

1. Clone the repository:

   git clone https://github.com/revant-kumar/Fraud-Detection-Model.git

2. Install dependencies:

   pip install -r requirements.txt

3. Run the Jupyter Notebook (Online_fraud_detection_practice.ipynb) to execute the data preparation and model training processes.

Contributing

Contributions are welcome! Feel free to open issues or submit pull requests with suggestions, improvements, or bug fixes.