Neural Networks and Value at Risk

Arimond, Alexander; Borth, Damian; Hoepner, Andreas G. F.; Klawunn, Michael; Weisheit, Stefan

doi:10.2139/ssrn.3591996

Cited by 7 publications

(4 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, his model can be interpreted as an ensemble model. Chen et al (2009) and Arimond et al (2020) estimate the VaR by modeling parameters of their respective distribution assumption. Chen et al (2009) use a standard ANN whereas Arimond et al (2020) compare ANNs with temporal convolutional neural nets and RNNs.…”

Section: Comparison To Related Workmentioning

confidence: 99%

“…Chen et al (2009) and Arimond et al (2020) estimate the VaR by modeling parameters of their respective distribution assumption. Chen et al (2009) use a standard ANN whereas Arimond et al (2020) compare ANNs with temporal convolutional neural nets and RNNs. Arian et al (2020) use standard VAE for the task of estimating the VaR.…”

Section: Comparison To Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Estimating the Value-at-Risk by Temporal VAE

Buch

Grimm

Korn

et al. 2023

Risks

View full text Add to dashboard Cite

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 the use of an autoregressive 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 use of a VAE prone to posterior collapse. Therefore, we use annealing of the regularization to mitigate this effect. As a result, the auto-pruning of the TempVAE works properly, which also leads to excellent estimation results for the VaR that beat classical GARCH-type, multivariate versions of GARCH and historical simulation approaches when applied to real data.

show abstract

Section: Comparison To Related Workmentioning

confidence: 99%

Section: Comparison To Related Workmentioning

confidence: 99%

Estimating the Value-at-Risk by Temporal VAE

Buch

Grimm

Korn

et al. 2023

Risks

View full text Add to dashboard Cite

show abstract

“…That study, (Arimond et al 2020), compares FFNN, temporal CNN, and LSTM algorithms with the Hidden Markov Model (Hidden Markov Model (HMM)) to estimate the VaR threshold. A VaR breach is reached when portfolio returns fall below the threshold.…”

Section: Findings: Risk Managementmentioning

confidence: 99%

Deep learning in the stock market—a systematic survey of practice, backtesting, and applications

Olorunnimbe

Viktor

2022

Artif Intell Rev

View full text Add to dashboard Cite

The widespread usage of machine learning in different mainstream contexts has made deep learning the technique of choice in various domains, including finance. This systematic survey explores various scenarios employing deep learning in financial markets, especially the stock market. A key requirement for our methodology is its focus on research papers involving backtesting. That is, we consider whether the experimentation mode is sufficient for market practitioners to consider the work in a real-world use case. Works meeting this requirement are distributed across seven distinct specializations. Most studies focus on trade strategy, price prediction, and portfolio management, with a limited number considering market simulation, stock selection, hedging strategy, and risk management. We also recognize that domain-specific metrics such as “returns” and “volatility” appear most important for accurately representing model performance across specializations. Our study demonstrates that, although there have been some improvements in reproducibility, substantial work remains to be done regarding model explainability. Accordingly, we suggest several future directions, such as improving trust by creating reproducible, explainable, and accountable models and emphasizing prediction of longer-term horizons—potentially via the utilization of supplementary data—which continues to represent a significant unresolved challenge.

show abstract

“…explored the effectiveness of three different architectures, including long short-term memory (LSTM) neural networks, deep neural networks, and hybrid models combining convolutional and LSTM neural networks. Their study aimed at forecasting crude oil prices using data from leading US information technology companies showed that LSTM architecture outperforms other architectures in terms of oil price prediction accuracy Arimond et al (2020). contrasted recurrent neural networks, especially LSTM models, with existing value-at-risk (VaR) estimation methods.…”

mentioning

confidence: 99%

Hybrid deep learning combined with traditional financial models: Application of RNN models and GARCH-Family Model for Natural Gas Price Volatility Forecasting

Chen,

Fan

2024

Preprint

View full text Add to dashboard Cite

The natural gas market has significant commonalities with the general financial market, especially its time series data are often non-stationary and show different fluctuation characteristics due to different market conditions. Therefore, accurate forecasting of natural gas price volatility requires a correct handling of the unique characteristics of its time series. In this paper, GARCH model and TGARCH model are specially selected to capture the volatility heteroscedasticity generated in different market scenarios, and IGARCH model is used to ensure that the model can still maintain high prediction accuracy when the time series is non-stationary. In order to deal with the long-term dependence of natural gas prices on time series, this paper introduces the LSTM model and the GRU model, both of which are variants of recurrent neural network (RNN). Thus we obtain the GARCH-IGARCH-TGARCH-LSTM/GRU model. It is worth noting that this model is applied to the field of natural gas price volatility prediction for the first time, which provides a new research perspective for in-depth understanding and accurate prediction of natural gas market volatility. We use the natural gas futures price index from June 2013 to June 2023 for the simulation test. Using 100 repeated experiments, we verify the robustness of the GARCH-IGARCH-TGARCH-GRU model in volatility forecasting and demonstrate its superior forecasting accuracy with a mean square error (MSE) of 0.22 and a mean absolute error (MAE) of 0.13. In the face of market breaks and extreme events, the integrated model shows higher adaptability and robustness. This study not only provides a powerful volatility forecasting tool for natural gas market participants, but also provides a strong demonstration of the universality of this type of model.

show abstract

Neural Networks and Value at Risk

Cited by 7 publications

References 48 publications

Estimating the Value-at-Risk by Temporal VAE

Estimating the Value-at-Risk by Temporal VAE

Deep learning in the stock market—a systematic survey of practice, backtesting, and applications

Hybrid deep learning combined with traditional financial models: Application of RNN models and GARCH-Family Model for Natural Gas Price Volatility Forecasting

Contact Info

Product

Resources

About