Sztuczna inteligencja w problematyce modeli oceny ryzyka w instytucjach finansowych z perspektywy prawno-regulacyjnej

Abstrakt

Purpose of the article / hypothesis: This article aims to verify the need to introduce additional legal and regulatory requirements in relation to the models used in banks, including, in particular, risk assessment models. At the same time, the article analyzes the need for possible introduction of sector-specific guidelines, or the need to include the above-mentioned models in the classification of high-risk artificial intelligence systems, referred to in the draft EU regulation on artificial intelligence.

Methodology: The article is based on an analysis of the available literature on the subject, legal acts as well as regulations and standards developed both at the local and international level.

Research results / results: The issue of the application of models in the financial sector, mainly banking, is of significant importance from the perspective of the regulator and supervisor. Quality, compliance with the regulations, but also efficiency and effective supervision may constitute the (instability) of a given financial institution, the instability of which may be a component – at least potentially – of systemic risk. Banks commonly use internal models that generally allow the calculation of capital requirements to cover specific risks in a bank’s business, such as credit risk or market risk. Internal models have been evolving for years and are undoubtedly becoming more and more accurate (they predict with a greater probability the occurrence of certain events), although they are still only certain assumptions that reality can verify, as evidenced by financial crises that have already occurred in the past as well as failures of banks considered to be stable. At the same time, the development of new technologies, in particular the so-called artificial intelligence makes institutions more and more willing to use various models, e.g. machine learning, to support these models and obtain theoretically better results. The European Union, but also other jurisdictions are considering or already introducing specific legal and regulatory solutions that are to introduce clear rules related to the use of certain artificial intelligence systems, including those used by financial institutions. As a result, institutions – already burdened with significant regulatory requirements, may soon be obliged to go through another "health path" of a legal and regulatory compliance nature.