HMLM: An Intelligent Artificial Intelligence Assisted Strategy to Identify UPI Frauds Based on Hybrid Markov Learning Methodology

The proliferation of Unified Payments Interface (UPI) transactions in the digital age has considerably improved financial inclusion, but it has also increased the vulnerability to fraud. This manuscript introduces a novel approach that employs Artificial Intelligence (AI) to detect UPI frauds. The approach is based on deep learning and is referred to as the Hybrid Markov Learning Methodology (HMLM). To evaluate the suggested system, it is cross-checked against the traditional Hidden Markov Model (HMM). Our approach combines the benefits of modern artificial intelligence methods with Markov models to improve the accuracy of fraud detection. Combining deep learning algorithms with probabilistic state transitions allows the hybrid Markov Learning Methodology to dynamically analyze transaction patterns and behaviors. By modeling both historical and real-time transaction data, our approach improves the identification of unusual activity and fraud patterns that conventional algorithms may ignore. From experimental data, we prove our approach minimizes false positives and improves the rate for fraud detection against the current options available. Our work advances the current state of fraud detection systems using more flexible and robust fraud detection systems, thus enabling security and confidence in UPI transactions.