Financial Risk Assessment using Machine Learning Engineering (FRAME): Scenario based Quantitative Analysis under Uncertainty

Abstract

Risk management functions, under uncertainty, in the Banking Industry have been changing and will continue to change with the recent advancements and innovations. Embracing uncertainty and working with measurable risk becomes critical, therefore quantitative risk severity assessment is critical for sustainable financial excellence. In this paper, the authors propose Financial Risk Assessment using Machine Learning Engineering (FRAME) based on artificial intelligence (AI) and machine learning (ML), which has two significant contributions. Firstly, adoption of machine learning models for banking towards risk quantification and secondly, granularity that emphases on customized logic via multi-factor analysis modeling at different levels of abstraction connecting machine learning models. These contributions will help Financial Institutions (Fis) that will gain the most benefits and opportunities. In a nutshell, the framework analysis presented in this paper is intended as a step towards building a framework of risk modeling from qualitative to quantitative, viewed at different levels of abstraction to access risk severity in the banking applications.