Investigation of financial fraud detection by using big data analytics

Abstract

The aim of this study is to examine the application of big data analytics in financial fraud detection, considering advancements in modern technology and the increasing complexity of financial crime schemes. The research is based on an extensive review of the scientific literature, data synthesis, and the application of empirical methods, including clustering analysis using the UMAP algorithm, graphical visualization techniques, and descriptive statistics, to systematically assess fraud detection mechanisms and their effectiveness. The findings reveal that advanced artificial intelligence techniques, such as deep neural networks and random forest models, enable the efficient detection of financial fraud in real time. Big data analytics not only facilitates the processing of vast financial transaction datasets but also allows for the integration of diverse data sources and the development of adaptive predictive models capable of adjusting to evolving fraud patterns. However, the study also highlights critical challenges, including data quality assurance, privacy protection, and the need for significant computational resources. The practical significance of this research lies in the development of more effective financial fraud prevention strategies, enhancing the resilience and trustworthiness of the financial sector. These insights are particularly valuable for banks, insurance companies, and other financial institutions seeking to mitigate fraud risks and safeguard clients from potential losses. The originality of the study is reflected in its systematic evaluation of the application of big data analytics in financial fraud prevention, grounded in the integration of theoretical and practical knowledge.