https://github.com/mukeshthenraj/fraud-detection-model

Logistic Regression, Grid Search, and ROC-PR curve evaluation on fraud detection dataset
https://github.com/mukeshthenraj/fraud-detection-model

classification fraud-detection machine-learning numpy pandas scikit-learn

Last synced: about 2 months ago
JSON representation

Logistic Regression, Grid Search, and ROC-PR curve evaluation on fraud detection dataset

• Host: GitHub
• URL: https://github.com/mukeshthenraj/fraud-detection-model
• Owner: Mukeshthenraj
• License: mit
• Created: 2025-06-16T19:45:08.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2025-06-16T20:38:35.000Z (about 1 year ago)
• Last Synced: 2025-06-16T20:42:26.203Z (about 1 year ago)
• Topics: classification, fraud-detection, machine-learning, numpy, pandas, scikit-learn
• Language: Python
• Homepage:
• Size: 0 Bytes
• Stars: 0
• Watchers: 0
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          

# 🕵️‍♂️ Fraud Detection Model

![Python](https://img.shields.io/badge/Python-3.9+-blue?logo=python)

![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)

![Status](https://img.shields.io/badge/Status-Completed-brightgreen)

This project uses machine learning to detect fraud in a labeled dataset. It covers data preprocessing, model training, evaluation, and visualization of fraud prediction.

---

## 📂 Project Structure

```

Fraud-Detection-Model/

├── data/

│   └── fraud_data.csv              # Dataset (CSV file)

├── images/

│   └── gridsearch_heatmap.png     # Heatmap of hyperparameter tuning

├── notebooks/

│   └── fraud_assignment.ipynb     # Jupyter notebook (main assignment)

├── fraud_assignment.py            # Converted Python script version

├── requirements.txt               # Project dependencies

├── README.md                      # Project overview (this file)

└── LICENSE                        # MIT License

```

## 📊 Dataset

The dataset (`fraud_data.csv`) contains observations labeled as fraudulent or not. The goal is to predict fraud using classification models.

---

## 🌟 Features

- Load and explore the dataset

- Train/test split

- Use of `DummyClassifier` as baseline

- Train classifiers like:

  - Logistic Regression

  - Support Vector Machines

  - Decision Trees

- Evaluate using:

  - Accuracy

  - Recall

  - Precision

  - Confusion Matrix

- Visualization using seaborn/matplotlib

- GridSearchCV for hyperparameter tuning

---

## 🛠️ Installation

Install dependencies:

```bash

pip install -r requirements.txt

```

Run the notebook:

```bash

jupyter notebook notebooks/fraud_assignment.py

```

Or run the Python script in PyCharm or terminal:

```bash

python fraud_assignment.py

```

---

## 📊 Sample Visuals

### 🔥 Grid Search Heatmap

![Grid Search Heatmap](images/gridsearch_heatmap.png)

---

## 📌 Requirements

```

- Python 3.7+

- scikit-learn

- pandas

- numpy

- matplotlib

- seaborn

```

---

## 📄 License

This project is licensed under the [MIT License](LICENSE).

---

## 👤 Author

[Mukesh Thenraj](https://www.linkedin.com/in/mukesh-thenraj)  

📧 mukeshthenraj@gmail.com