Scenario generation for market risk models using generative neural networks

TL;DR

This paper demonstrates how generative adversarial networks can be used to create comprehensive market risk scenarios for insurance companies, matching regulatory standards and offering a data-driven modeling alternative.

Contribution

It extends GAN-based scenario generation from simple models to full internal market risk models with numerous risk factors for a one-year horizon.

Findings

GAN-based models produce results similar to approved internal models

The approach covers a wide range of investment risk factors

GANs offer a viable data-driven alternative for market risk modeling

Abstract

In this research, we show how to expand existing approaches of using generative adversarial networks (GANs) as economic scenario generators (ESG) to a whole internal market risk model - with enough risk factors to model the full band-width of investments for an insurance company and for a one year time horizon as required in Solvency 2. We demonstrate that the results of a GAN-based internal model are similar to regulatory approved internal models in Europe. Therefore, GAN-based models can be seen as a data-driven alternative way of market risk modeling.