AT-AI04 · Machine learning
Credit Card Fraud Detection
Flags fraudulent transactions in highly imbalanced data.
- Suits
- Sem 5–6
- Branches
- CSE, ISE, AIML
- Type
- Software
How it works
In real transaction data, fraud cases are a tiny fraction of the total, so a model can look accurate while missing every fraud. The project balances the training data so the model learns the fraud pattern properly, and judges it by precision and recall instead of plain accuracy. A test page lets you submit a transaction and see whether it is flagged.
What it does
- Imbalance handling
- Precision and recall report
- Live test page
Built with
Python, scikit-learn
What you get
- Working software with full source code
- Steps to install and run it on your laptop
- Rough report and explanation of the working
- Live demo on video call before the final payment
Good to know
- Features are as listed here. Anything extra is quoted separately.
- Runs on a normal laptop unless we tell you otherwise.
- Full reports and PPTs are not included.
Similar projects
- AT-AI01Student Performance PredictionPredicts final marks from attendance, study hours and past scores.
- AT-AI02House Price PredictionEstimates a house price from area, location and rooms using regression.
- AT-AI03Heart Disease PredictionEstimates heart disease risk from health readings using ensemble models.
- AT-AI05Customer Churn PredictionPredicts which customers are likely to leave, and why.