Abstract:
Problem: The increasing amount of online financial transactions has significantly raised the risk of fraud. Existing fraud detection systems either prioritize speed or accuracy but rarely achieve both, leaving financial institutions vulnerable to new types of fraud. This project focuses on addressing this issue by developing a real-time fraud detection model that balances both high-speed processing and accuracy.
Methodology: A hybrid machine learning model was developed combining decision trees and neural networks to improve detection rates. The system processes large datasets of transactional records using pre-processing techniques like feature scaling and outlier detection. The model is then trained and tested using supervised learning techniques to optimize detection accuracy.
Initial Results: Initial evaluation of the prototype achieved a 96% accuracy rate, with an AUC-ROC of 0.93 and a confusion matrix revealing a 2% false-positive rate. The model's real-time processing capability allows it to handle up to 1,000 transactions per second.
