SMART-FMD: Rule-Driven Financial Fraud Monitoring and Risk Detection System for Indian Banking Transactions

The rapid expansion of digital banking platforms such as Unified Payments Interface (UPI), Immediate Payment Service (IMPS), and National Electronic Funds Transfer (NEFT) has significantly increased the number of online financial transactions.However, the growth of digital banking has also resulted in an increase in fraudulent activities, including unauthorized transactions, suspicious account behavior, and financial cybercrimes.Traditional fraud detection systems rely mainly on manual verification and static rule-based monitoring, which are often unable to detect complex and evolving fraud patterns in real time.This paper presents SMART-FMD, a rule-driven financial fraud monitoring and risk detection system designed to identify suspicious banking activities through automated transaction analysis.The proposed system integrates rule-based fraud detection techniques with a machine learning approach using the Random Forest algorithm to evaluate transaction behavior and generate fraud risk scores.The system is implemented using the Django framework and provides features such as transaction monitoring, risk score evaluation, fraud alerts, and a real-time fraud monitoring dashboard.The system also supports analytical visualization and compliance reporting to assist financial institutions in identifying high-risk accounts and suspicious transactions.The experimental implementation demonstrates that the proposed system can effectively detect anomalous transaction patterns and improve fraud monitoring capabilities in digital banking environments.