Modelos de Arquitectura de Big Data para identificar riesgos financieros en los bancos: Una Revisión Sistemática de la Literatura

The financial sector faces difficulties in managing risks due to the increasing volume of structured and unstructured data, which complicates the identification of financial risks such as payment defaults. Traditional models are insufficient to address this problem, prompting the exploration of Big Data solutions. This study aims to review how Big Data architecture models can enhance the prediction and management of financial risks in banks. A systematic literature review was conducted, analyzing 32 relevant studies published between 2019 and 2023. The results indicate that various Big Data frameworks and architectures, such as those utilizing technologies like Apache Spark and Apache Storm, effectively process large data volumes in real-time. Additionally, data analysis techniques like machine learning were highlighted to improve accuracy in risk identification. This study concludes that implementing Big Data and advanced techniques can improve decision-making in financial risk management, although challenges remain in integrating these models into existing banking infrastructures.