https://github.com/greatwoman23/my-paypal-project
The project is to build a fraud detection model using the dataset that has been provided and in doing so, increase revenue from transaction fees.
https://github.com/greatwoman23/my-paypal-project
credit-card credit-card-fraud data-science dataset finance machine-learning python
Last synced: 2 months ago
JSON representation
The project is to build a fraud detection model using the dataset that has been provided and in doing so, increase revenue from transaction fees.
- Host: GitHub
- URL: https://github.com/greatwoman23/my-paypal-project
- Owner: Greatwoman23
- Created: 2024-03-19T20:15:31.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2024-03-20T10:52:48.000Z (about 1 year ago)
- Last Synced: 2025-01-12T09:30:30.841Z (4 months ago)
- Topics: credit-card, credit-card-fraud, data-science, dataset, finance, machine-learning, python
- Language: Jupyter Notebook
- Homepage: https://medium.com/@chemistry8526/enhancing-financial-security-a-machine-learning-approach-to-credit-card-fraud-detection-a6c0932aff69
- Size: 1.1 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# My-PayPal-Project
The project is to build a fraud detection model using the dataset that has been provided and in doing so, increase revenue from transaction fees.
## Task
The task at hand is to develop a robust fraud detection system for FriendPay, a credit card company facing challenges in accurately identifying fraudulent transactions.
The dataset, sourced from real credit card transactions, presents a class imbalance, making it a challenging problem in machine learning.
## Description
This project focuses on building a fraud detection model using a machine learning approach.
The workflow involves detailed data analysis, preprocessing, and the implementation of various machine learning models, including Logistic Regression, Random Forest, XGBoost, and K-Nearest Neighbors (KNN).
The dataset is highly imbalanced, and we address this by exploring techniques such as synthetic data generation.
## Installation
we installed various libaries such as matplotlib, xgboost, seaborn, scikit-learn
## Acknowledgments
We would like to express our gratitude to Andrea Dal Pozzolo, Olivier Caelen, Reid A. Johnson, and Gianluca Bontempi for providing the dataset used in this project.
Their work in credit card fraud detection has significantly contributed to the field.