Abstract :

With Thousands Of Transactions Happening Every Second In Todays Digital Banking Systems, Credit Card Fraud Is One Of The Biggest Risks. The Significant Imbalance Between Legal And Fraudulent Records And The Dynamic Nature Of Fraud Trends Make It Difficult To Identify Fraudulent Transactions In Real Time. The TabNet Model, Which Effectively Manages Large-scale, High-dimensional Tabular Transaction Data, Is Used In This Project To Construct A Deep Learning-based Fraud Detection System. Using Sequential Attention, The Model Learns To Concentrate On The Most Crucial Aspects Of Each Transaction, Attaining High Recall And Precision While Reducing False Alarms. Advanced Pre-processing, Balanced Data Handling, Model Training, Assessment, And Visualisation Are All Integrated Into The System. Lastly, An Interactive User Interface With Modules For Registration, Login, Real-time Prediction, And Visual Analytics Of Model Performance Is Developed Using A Flask-based Web Application. Compared To Conventional Methods, The Suggested System Provides Superior Accuracy, Quicker Inference, And Strong Fraud Detection Capabilities..

Published:

17-8-2026

Issue:

Vol. 26 No. 8 (2026)

Page Nos:

981 - 985

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite