https://github.com/quantumcoderrr/credit-card-fraud-detection

💴 A machine learning project that detects fraudulent credit card transactions using classification algorithms. Includes data preprocessing, EDA, model training & evaluation with techniques like Random Forest, Logistic Regression, and SMOTE for class imbalance. Built for secure financial insights and real-world fraud detection use cases.
https://github.com/quantumcoderrr/credit-card-fraud-detection

classification credit-card data-science financial-security fraud-detection imbalanced-data logistic-regression machine-learning

Last synced: about 1 month ago
JSON representation

💴 A machine learning project that detects fraudulent credit card transactions using classification algorithms. Includes data preprocessing, EDA, model training & evaluation with techniques like Random Forest, Logistic Regression, and SMOTE for class imbalance. Built for secure financial insights and real-world fraud detection use cases.

• Host: GitHub
• URL: https://github.com/quantumcoderrr/credit-card-fraud-detection
• Owner: QuantumCoderrr
• License: mit
• Created: 2024-12-14T15:54:03.000Z (10 months ago)
• Default Branch: main
• Last Pushed: 2024-12-14T17:00:49.000Z (10 months ago)
• Last Synced: 2025-07-05T23:11:28.256Z (3 months ago)
• Topics: classification, credit-card, data-science, financial-security, fraud-detection, imbalanced-data, logistic-regression, machine-learning
• Language: Jupyter Notebook
• Homepage: https://quantumcoderrr.github.io/Credit-Card-Fraud-Detection/
• Size: 110 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE
  • Code of conduct: CODE_OF_CONDUCT.md

Awesome Lists containing this project

README

          
# Credit Card Fraud Detection 🚨💳

This project focuses on detecting fraudulent credit card transactions using machine learning techniques. It uses a dataset containing credit card transactions, where each transaction is labeled as either 'Fraud' or 'Not Fraud'. The goal is to train a model to predict fraud based on transaction features.

## Table of Contents

- [Overview](#overview)

- [Requirements](#requirements)

- [Getting Started](#getting-started)

- [Installation](#installation)

- [Results](#results)

- [Contributing](#contributing)

- [License](#license)

## Overview

In this project, we use a **Random Forest Classifier** to classify credit card transactions as fraudulent or not. The project includes steps like:

- Data Preprocessing

- Model Training

- Evaluation (Confusion Matrix, Classification Report, ROC-AUC)

- Feature Importance Analysis

## Requirements 📦

The following libraries are required to run this project:

- pandas

- numpy

- matplotlib

- seaborn

- scikit-learn

## Getting Started 🚀

### Prerequisites

- Python 3.8 or higher

- Required libraries installed (`pip install -r requirements.txt`)

### Installation

1. Clone the repository:

   ```bash

   git clone https://github.com/QuantumCoderrr/CreditCardFraudDetection.git

   cd CreditCardFraudDetection

2. Install dependencies:

   ```bash

   pip install -r requirements.txt

   

## Results 📊

Below are the visuals showing the **Confusion Matrix** and **Feature Importance**.

### Confusion Matrix

The confusion matrix visualizes the performance of the classification model, showing the true positives, true negatives, false positives, and false negatives.

![Confusion Matrix](images/confusion_matrix.png)

### Feature Importance

Feature importance indicates the relative importance of each feature in the model's decision-making process. Higher values indicate features that play a greater role in determining the prediction.

![Feature Importance](images/feature_importance.png)

## Dataset 📂

The dataset used for this project can be accessed via the following Google Drive link:  

[Credit Card Fraud Detection Dataset](https://drive.google.com/file/d/15ky1Zn1BTtSR2GCHJCPSVEMtmIO4wXPl/view?usp=drive_link)

## Contributing 🤝

We welcome contributions! Please follow the [contributing guidelines](CONTRIBUTING.md) to submit changes.

## License 📝

This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.

---

Thanks for checking out the project! Let's work together to make fraud detection more efficient! 🚀