Estimating the Value-at-Risk by Temporal VAE

TL;DR

This paper introduces a temporal variational autoencoder (TempVAE) for estimating the Value-at-Risk (VaR) of large financial portfolios, addressing challenges like posterior collapse with annealing, and demonstrating superior performance over classical methods.

Contribution

The paper proposes a novel TempVAE model with annealed regularization to improve VaR estimation in financial data, overcoming posterior collapse issues.

Findings

TempVAE outperforms classical GARCH and historical simulation methods.

Annealing regularization mitigates posterior collapse in TempVAE.

Effective VaR estimation on real financial data.

Abstract

Estimation of the value-at-risk (VaR) of a large portfolio of assets is an important task for financial institutions. As the joint log-returns of asset prices can often be projected to a latent space of a much smaller dimension, the use of a variational autoencoder (VAE) for estimating the VaR is a natural suggestion. To ensure the bottleneck structure of autoencoders when learning sequential data, we use a temporal VAE (TempVAE) that avoids an auto-regressive structure for the observation variables. However, the low signal- to-noise ratio of financial data in combination with the auto-pruning property of a VAE typically makes the use of a VAE prone to posterior collapse. Therefore, we propose to use annealing of the regularization to mitigate this effect. As a result, the auto-pruning of the TempVAE works properly which also results in excellent estimation results for the VaR that beats classical GARCH-type and historical simulation approaches when applied to real data.