Machine Learning and AI for Risk Management

Abstract

We explore how machine learning and artificial intelligence (AI) solutions are transforming risk management. A non-technical overview is first given of the main machine learning and AI techniques of benefit to risk management. Then a review is provided, using current practice and empirical evidence, of the application of these techniques to the risk management fields of credit risk, market risk, operational risk, and compliance ('RegTech'). We conclude with some thoughts on current limitations and views on how the field is likely to develop in the short-to medium-term. Overall, we present an optimistic picture of the role of machine learning and AI in risk management, but note some practical limitations around suitable data management policies, transparency, and lack of necessary skillsets within firms.

Artificial Intelligence Based Commercial Risk Management Framework for SMEs

“…A survey of the top 1000 firms in the United States on AI implementation in their firms found that their biggest concern in the implementation of AI was the readiness and ability of staff to understand and work with these new solutions. Training a skilled cohort of staff is something that will take time [67]. World Economic Forum data show that by 2020, machines and algorithms will create 133 million job positions of new functions.…”

“…As Aziz and Dowling suggest, firms cannot simply 'apply' a machine learning risk management solution, but it is rather a continuous process requiring a constant evaluation of whether their particular machine learning solution is currently considered best practice. When it comes to AI, where there is some or full automation of processes, from data gathering to decision-making, the need for human oversight will become even more pressing [67].…”

“…However, there is now an increased interest by institutions in using AI and machine learning techniques to enhance credit risk management practices, partially due to evidence of incompleteness in traditional techniques. The evidence is that credit risk management capabilities can be significantly improved through leveraging AI and machine learning techniques due to its ability of semantic understanding of unstructured data [67]. However, the main problem lies not in the sophisticated credit score methods and their development.…”

“…ZestFinance (with permission) tapped into the huge volume of information on members held by Baidu such as their search or purchase histories to help Baidu decide whether to lend. They use thousands of data points per customer and are still able to make lending decisions on new applications in seconds [67].…”

“…It can also help in opting for an appropriate risk mitigation strategy and finding instruments that can facilitate shifting or trading risk. Thus, the use of AI techniques for risk management is now expanding to new areas involving the analysis of extensive document collections and the performance of repetitive processes, as well as the detection of money laundering that requires analysis of large datasets [67].…”