Modern Approaches to Risk Management in the Use of Big Data in the Financial Sector

Abstract

This study analyzes modern approaches to financial risk management using Big Data, artificial intelligence (AI/ML), and generative AI. A comprehensive literature review has been conducted, examining the advantages of traditional methods such as MCMC, as well as the potential of machine learning algorithms and generative models for data synthesis and stress testing. A scientific gap has been identified, highlighting the lack of integrated methodologies that combine statistical modeling, AI/ML, and generative AI into a unified risk management system. The objective of this study is to explore the specific features of contemporary approaches used in risk management processes involving Big Data in the financial sector. The study's scientific novelty lies in analyzing the feasibility of forming a unified integrative system capable of synthesizing synthetic data for extreme scenario modeling, as well as automating risk monitoring and analysis processes through cloud computing platforms and RegTech solutions. The findings presented in this study may be of interest to researchers, postgraduate students, and professionals in finance and risk management. Additionally, the data outlined in this research may be valuable for specialists seeking interdisciplinary synergy between financial engineering, information technology, and statistical methods to optimize managerial decision-making in the era of digital transformation.