divyansh10100/credit-card-fraud-using-SMOTE

Credit card frauds cost a lot to the banks as well as the customers. Here we compare various machine learning algorithms to find the best one in detecting credit card frauds. The dataset is highly imbalanced, therefore we use a technique known as SMOTE to generate synthetic data

20
/ 100
Experimental

This project helps financial institutions and fraud detection teams improve their ability to spot fraudulent credit card transactions. It takes raw credit card transaction data and applies advanced techniques to identify patterns, ultimately providing a predictive model that flags suspicious activities. The output is a robust system that helps fraud analysts and risk managers quickly identify and prevent financial losses.

No commits in the last 6 months.

Use this if you are a fraud analyst or risk manager looking for a way to more accurately detect credit card fraud, especially when dealing with a high number of legitimate transactions compared to fraudulent ones.

Not ideal if you need to detect fraud in real-time streaming data with extremely low latency, as this focuses on model building and comparison for batch processing.

credit-card-fraud financial-crime risk-management transaction-monitoring fraud-detection
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 8 / 25
Community 8 / 25

How are scores calculated?

Stars

8

Forks

1

Language

Jupyter Notebook

License

Last pushed

Feb 28, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/divyansh10100/credit-card-fraud-using-SMOTE"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.