Estimating risks of option books using neural-SDE market models
This work addresses risk management for financial institutions by providing a more efficient and accurate simulation engine for option portfolios, though it is incremental as it builds on existing neural-SDE models.
The paper tackled the problem of estimating risks for option portfolios by using an arbitrage-free neural-SDE market model to generate realistic scenarios for multiple European options, resulting in more computationally efficient and accurate Value-at-Risk (VaR) evaluations with better coverage and less procyclicality than standard methods.
In this paper, we examine the capacity of an arbitrage-free neural-SDE market model to produce realistic scenarios for the joint dynamics of multiple European options on a single underlying. We subsequently demonstrate its use as a risk simulation engine for option portfolios. Through backtesting analysis, we show that our models are more computationally efficient and accurate for evaluating the Value-at-Risk (VaR) of option portfolios, with better coverage performance and less procyclicality than standard filtered historical simulation approaches.