Section 2.1 provides an overview of risk management at banks, the key risk types and risk management tools and methodologies.
Section 2.2 gives a quick introduction to machine learning and its use.
Machine learning, identified as one of the technologies with important implications for risk management, can enable the building of more accurate risk models by identifying complex, nonlinear patterns within large datasets.
The predictive power of these models can grow with every bit of information added, thus enhancing predictive power over time.
To determine the risks specific to banks, as an alternate to leveraging on existing literature, this paper provides a taxonomy of risks that is developed based on a review of bank annual reports.
An analysis of the available literature was carried out to evaluate the areas of banking risk management where machine-learning techniques have been researched.Credit risk arises from the potential that a borrower or counterparty will fail to perform on an obligation.For most banks, loans are the largest and most obvious source of credit risk.The broadening and deepening of regulations, evolving customer expectations and the evolution of risk types are expected to drive the change within risk management.New products, services and risk management techniques are being enabled through the application of evolving technologies and advanced analytics.In tandem, there has been a growing influence of machine learning in business applications, with many solutions already implemented and many more being explored.Mc Kinsey & Co highlighted that risk functions in banks, by 2025, would need to be fundamentally different from what they are today.The paper seeks to study the extent to which machine learning, which has been highlighted as an emergent business enabler, has been researched in the context of risk management within the banking industry and, subsequently, to identify potential areas for further research.The aim of this review paper is to assess, analyse and evaluate machine-learning techniques that have been applied to banking risk management, and to identify areas or problems in risk management that have been inadequately explored and make suggestions for further research.Section 3 begins by providing an overview of the research methodology.The section further examines the existing research around the application of machine learning in the management of risk at banks.