Black-box model risk in finance

TL;DR

This paper discusses the risks associated with using machine learning models in finance, especially in option pricing and hedging, emphasizing the importance of understanding, quantifying, and managing these risks.

Contribution

It highlights the sources of risk introduced by machine learning in financial applications and reviews strategies for risk mitigation and management.

Findings

Identifies key risks in ML-based financial models

Analyzes how ML affects risk emphasis in option pricing

Suggests strategies for risk mitigation in finance

Abstract

Machine learning models are increasingly used in a wide variety of financial settings. The difficulty of understanding the inner workings of these systems, combined with their wide applicability, has the potential to lead to significant new risks for users; these risks need to be understood and quantified. In this sub-chapter, we will focus on a well studied application of machine learning techniques, to pricing and hedging of financial options. Our aim will be to highlight the various sources of risk that the introduction of machine learning emphasises or de-emphasises, and the possible risk mitigation and management strategies that are available.