Scenario generation for market risk models using generative neural networks
This provides a data-driven alternative for market risk modeling in the insurance industry, though it is incremental as it builds on existing GAN approaches.
The research tackled the problem of generating economic scenarios for market risk models by expanding generative adversarial networks (GANs) to handle a full set of risk factors for insurance investments over a one-year horizon, as required by Solvency 2, and demonstrated that GAN-based models produce results similar to regulatory-approved models in Europe.
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.