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

Credit Card Fraud Detection using machine learning to distinguish fraudulent transactions from legitimate ones. This project includes data analysis, model training, and evaluation to achieve high accuracy and recall, minimizing false negatives for better fraud detection
https://github.com/medicharlakarthik/credit-card-fraud-detection

machine-learning python random-forest-classifier scikit-learn

Last synced: 4 days ago
JSON representation

Credit Card Fraud Detection using machine learning to distinguish fraudulent transactions from legitimate ones. This project includes data analysis, model training, and evaluation to achieve high accuracy and recall, minimizing false negatives for better fraud detection

• Host: GitHub
• URL: https://github.com/medicharlakarthik/credit-card-fraud-detection
• Owner: MedicharlaKarthik
• Created: 2024-11-03T14:05:22.000Z (2 months ago)
• Default Branch: main
• Last Pushed: 2024-11-03T14:21:18.000Z (2 months ago)
• Last Synced: 2024-11-13T02:09:47.320Z (2 months ago)
• Topics: machine-learning, python, random-forest-classifier, scikit-learn
• Language: Jupyter Notebook
• Homepage:
• Size: 207 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Credit-Card-Fraud-Detection

Credit Card Fraud Detection using machine learning to distinguish fraudulent transactions from legitimate ones. 

The dataset used in this project is a credit card transaction dataset available on Kaggle. The dataset contains transactions labeled as either fraudulent or legitimate, with 30 anonymized features (V1, V2, ..., V28) generated through Principal Component Analysis (PCA), along with the Time and Amount features.

The dataset is highly imbalanced, with only 0.17% of transactions labeled as fraudulent. Therefore, the challenge lies in accurately identifying fraudulent transactions amidst a large volume of legitimate transactions.

This project includes data analysis, model training, and evaluation to achieve high accuracy and recall, minimizing false negatives for better fraud detection

Data Analysis: Understanding the distribution and characteristics of transactions.

Modeling: Training a Random Forest classifier to differentiate between fraud and legitimate transactions.

Evaluation: High focus on recall to reduce false negatives and improve fraud detection.