Abstract: The technological advancement of the financial industry has been vital in ensuring that it is more accessible to consumers. Still, it has also brought up complicated security issues, such as financial fraud. Conventional rule-based fraud detection methods consistently have challenges in staying up with the speed at which cyber threats evolve. To solve these issues, this systematic study examines how real-time analytics and artificial intelligence (AI) frameworks might improve the detection of fraud capabilities. Prior research has concentrated on discrete AI models but has frequently needed more thorough integration with real-time data. This review addresses the gaps in previous research by analyzing various AI models, including neural networks, support vector machines, and graph-learning algorithms in the context of identifying fraudulent behavior. The paper assesses experimental settings and real-world applications, offering insights into various frameworks' efficacy, scalability, and adaptability in real-time financial situations. This research also contributes to financial fraud detection systems continuous growth by investigating how AI-powered techniques might improve fraud detection accuracy, precision, and reaction times. Additionally, combining AI with real-time analytics is a viable way to combat the growing complexity of criminal activities related to financial crime.
Keywords: Real-Time Analytics, Artificial Intelligence, Financial Fraud Detection, Machine Learning, Fraudulent Transactions, Supervised Learning, Unsupervised Learning, Data Mining, Graph, Learning Algorithms, Explainable AI (XAI)
|
DOI:
10.17148/IJARCCE.2024.13920
