# Estimating value at risk: LSTM vs. GARCH

arXiv: https://arxiv.org/abs/2207.10539 · HTML: https://mlsanity.com/paper/2207.10539/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 59 references that are in the map.
- First posted on arXiv 21 Jul 2022.

## Builds on (most cited first, 4 of 4)

- [LSTM: A Search Space Odyssey](https://mlsanity.com/paper/1503.04069/) (2015)
- [Universal features of price formation in financial markets: perspectives from Deep Learning](https://mlsanity.com/paper/1803.06917/) (2018)
- [A Statistical Recurrent Stochastic Volatility Model for Stock Markets](https://mlsanity.com/paper/1906.02884/) (2019)
- [A Bayesian Long Short-Term Memory Model for Value at Risk and Expected Shortfall Joint Forecasting](https://mlsanity.com/paper/2001.08374/) (2020)

## Built on by (most cited first, 1 of 1)

- [Interval Forecasts for Gas Prices in the Face of Structural Breaks -- Statistical Models vs. Neural Networks](https://mlsanity.com/paper/2407.16723/) (2024)

## Abstract (arXiv)

Estimating value-at-risk on time series data with possibly heteroscedastic dynamics is a highly challenging task. Typically, we face a small data problem in combination with a high degree of non-linearity, causing difficulties for both classical and machine-learning estimation algorithms. In this paper, we propose a novel value-at-risk estimator using a long short-term memory (LSTM) neural network and compare its performance to benchmark GARCH estimators. Our results indicate that even for a relatively short time series, the LSTM could be used to refine or monitor risk estimation processes and correctly identify the underlying risk dynamics in a non-parametric fashion. We evaluate the estimator on both simulated and market data with a focus on heteroscedasticity, finding that LSTM exhibits a similar performance to GARCH estimators on simulated data, whereas on real market data it is more sensitive towards increasing or decreasing volatility and outperforms all existing estimators of value-at-risk in terms of exception rate and mean quantile score.