An Emerging Technology Of Fraudlent Detection For Enhancing Deep Learning Based Block Chain Innovation

Abstract

Recently, machine learning (ML) techniques have been highly effective in addressing the problem of payment-related fraud detection. These methods have the ability to evolve and uncover new, previously unseen fraud patterns. In this study, we apply multiple ML techniques, specifically Logistic Regression and Support Vector Machine (SVM), to detect payment fraud using a labeled dataset of transaction data. Our results demonstrate that these approaches can accurately identify fraudulent transactions while maintaining a low rate of false positives. ML, a branch of artificial intelligence (AI), allows systems to learn from data, recognize patterns, and make decisions with minimal human intervention. By leveraging algorithms that build predictive models from training data, ML enables automated decision-making without the need for explicit programming. Deep learning, a more advanced subset of ML, employs deep neural networks with multiple layers, which are particularly effective in processing large, complex datasets.