Skip to content

AkpanDaniel/-Fraud-Detection-System

Repository files navigation

Fraud Detection System

81.6% recall | 87.4% F1 | 284k transactions

Random Forest model that detects credit card fraud. End-to-end pipeline from data to deployment.

Results

Metric Score
Recall 81.6%
F1 87.4%

What I Built

  • Engineered 7 features (transaction hour, user velocity, amount patterns)
  • Trained a Random Forest model with 81.6% fraud catch rate
  • Pushed predictions to SQL Server with complex queries (window functions, CTEs)
  • Saved model with versioning for production
  • Built a PyTorch neural network (11 parameters) to show framework knowledge

Business Impact

  • Flag transactions > $106
  • Monitor 2-3 AM (peak fraud hour)
  • Approve users with >50 daily transactions faster (0.17% fraud rate)

Tech Stack

Python · pandas · scikit-learn · PyTorch · SQL Server · joblib

Reproducible

Fixed random seed (42) for exact replication

About

Built a fraud detection model on 284K transactions with feature engineering, SQL integration, and PyTorch demonstration. Achieved 81.6% fraud recall.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors