https://github.com/aravindnathan02/credit-card-fraud-detection

This is a Machine Learning project on classifying fraudulent credit card transactions.
https://github.com/aravindnathan02/credit-card-fraud-detection

classification-model fraud-detection logistic-regression machine-learning python random-forest scikit-learn

Last synced: 13 days ago
JSON representation

This is a Machine Learning project on classifying fraudulent credit card transactions.

• Host: GitHub
• URL: https://github.com/aravindnathan02/credit-card-fraud-detection
• Owner: aravindnathan02
• Created: 2025-01-25T05:57:02.000Z (13 days ago)
• Default Branch: main
• Last Pushed: 2025-01-25T06:00:14.000Z (13 days ago)
• Last Synced: 2025-01-25T06:24:55.705Z (13 days ago)
• Topics: classification-model, fraud-detection, logistic-regression, machine-learning, python, random-forest, scikit-learn
• Language: Jupyter Notebook
• Homepage:
• Size: 0 Bytes
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Credit Card Fraud Detection System

**Link to Dataset:** [Kaggle](https://www.kaggle.com/datasets/mlg-ulb/creditcardfraud)

### Situation

> Financial institutions face significant losses from credit card fraud. \

> Traditional detection methods were insufficient. \

> Large volume of transactions (280K+) needed real-time analysis.

### Task

> Build a machine learning system to detect fraudulent transactions. \

> Improve detection accuracy while minimizing false positives. \

> Handle imbalanced dataset where fraud cases are rare.

### Action

> Conducted extensive data preprocessing and feature engineering. \

> Implemented Logistic Regression and Random Forest models. \

> Applied sampling techniques to address class imbalance. \

> Performed hyperparameter tuning using cross-validation. \

> Optimized models for real-world application.

### Result

> Achieved 0.99 AUPRC score in fraud detection. \

> Improved Recall by 2%. \

> Reached 94% fraud detection accuracy. \

> Reduced financial losses through better detection. \

> Created a scalable solution for ongoing fraud detection.