Open Source Intelligence: Classification and Mitigation of Risks and Fraud Within Financial Institutions

Abstract - The high volume of data that travels in open communications is a growing reality. Therefore, it is necessary to improve the capture, analysis and shielding of information through Open-Source Intelligence - OSINT. The objective of this study is to uncover the benefits of using OSINT by financial institutions and how the mechanisms of the current Open Finance and LGPD can contribute to best classify customer scores, aiming to mitigate risks and fraud, and increase efficiency in decision-making. As preliminary results of the adopted outline, a macro model was proposed to help financial institutions validate their respective models. The selected case has an average daily volume of €100,000.00 (one hundred thousand euros). Thus, it is justified that the referred proposal will allow independence to the institutions, which will have control of the information used in the universal classification, in addition to the results of other information searched in secure bases.