Credit Card Fraud Detection

Project developed at the University of Camerino

Table of Contents

• Project Overview
• Setup
• Dataset
• Group Components

Project Overview

This project focuses on developing a robust credit card fraud detection system using advanced machine learning techniques. By leveraging a dataset of over 550,000 credit card transactions, we implemented various algorithms, including logistic regression, decision trees, and random forests, integrated through a stacking ensemble method to achieve high accuracy in detecting fraudulent transactions. This work is developed at the University of Camerino by Damiano Pasquini, Nicol Buratti, and Mathukiya Vaibhav Jagdish, for the Research Methodologies 2023/24 course under the supervision of Andrea Morichetta and Romeo Pruno.

Setup

Libraries

To replicate our results, you need to install the following Python libraries:

• pandas (Version 2.2.2)
• numpy (Version 1.26.4)
• scikit-learn (Version 1.5.0)
• matplotlib (Version 3.9.0)
• seaborn (Version 0.13.2)
• jupyter (1.0.0)

You can install these libraries using pip:

pip install pandas==2.2.2 numpy==1.26.4 scikit-learn==1.5.0 matplotlib==3.9.0 seaborn==0.13.2 jupyter==1.0.0

Hardware Requirements

To efficiently run the analysis and model training, the following hardware specifications are recommended:

• CPU: Multi-core processor (Quad-core or higher)
• RAM: Minimum 16 GB
• GPU: Optional

Dataset

The dataset used in this study is the "Credit Card Fraud Detection Dataset 2023," which is publicly available on Kaggle

Group Components

• @damiano00
• @uninicol
• @VaibhavMathukiyaa