Risk Management with Feature-Enriched Generative Adversarial Networks (FE-GAN)

TL;DR

This paper introduces FE-GAN, an enhanced GAN framework for financial risk management that improves estimation of VaR and ES, outperforming traditional models especially with Tail-GAN in Expected Shortfall estimation.

Contribution

The paper proposes FE-GAN, incorporating feature enrichment into GANs, and evaluates specialized models WGAN and Tail-GAN for improved financial risk estimation.

Findings

FE-GAN outperforms traditional GAN architectures in VaR and ES estimation.

Tail-GAN surpasses WGAN in ES estimation due to its task-specific loss.

Both models perform similarly in VaR estimation.

Abstract

This paper investigates the application of Feature-Enriched Generative Adversarial Networks (FE-GAN) in financial risk management, with a focus on improving the estimation of Value at Risk (VaR) and Expected Shortfall (ES). FE-GAN enhances existing GANs architectures by incorporating an additional input sequence derived from preceding data to improve model performance. Two specialized GANs models, the Wasserstein Generative Adversarial Network (WGAN) and the Tail Generative Adversarial Network (Tail-GAN), were evaluated under the FE-GAN framework. The results demonstrate that FE-GAN significantly outperforms traditional architectures in both VaR and ES estimation. Tail-GAN, leveraging its task-specific loss function, consistently outperforms WGAN in ES estimation, while both models exhibit similar performance in VaR estimation. Despite these promising results, the study acknowledges limitations, including reliance on highly correlated temporal data and restricted applicability to other domains. Future research directions include exploring alternative input generation methods, dynamic forecasting models, and advanced neural network architectures to further enhance GANs-based financial risk estimation.