Paper: arXiv 2310.01063
Authors: Jakub Michańków, Łukasz Kwiatkowski, Janusz Morajda
Abstract
In this paper, we develop a hybrid approach to forecasting the volatility and risk of financial instruments by combining common econometric GARCH time series models with deep learning neural networks. For the latter, we employ Gated Recurrent Unit (GRU) networks, whereas four different specifications are used as the GARCH component: standard GARCH, EGARCH, GJR-GARCH and APARCH. Models are tested using daily logarithmic returns on the S&P 500 index as well as gold price Bitcoin prices, with the three assets representing quite distinct volatility dynamics. As the main volatility estimator, also underlying the target function of our hybrid models, we use the price-range-based Garman-Klass estimator, modified to incorporate the opening and closing prices. Volatility forecasts resulting from the hybrid models are employed to evaluate the assets’ risk using the Value-at-Risk (VaR) and Expected Shortfall (ES) at two different tolerance levels of 5% and 1%. Gains from combining the GARCH and GRU approaches are discussed in the contexts of both the volatility and risk forecasts. In general, it can be concluded that the hybrid solutions produce more accurate point volatility forecasts, although it does not necessarily translate into superior VaR and ES forecasts.
Complexity vs Empirical Score
- Math Complexity: 7.5/10
- Empirical Rigor: 8.0/10
- Quadrant: Holy Grail — high math complexity, high empirical rigor
Why this score: The paper is mathematically dense, featuring multiple GARCH model specifications with derivatives and nonlinear functions, and employs complex deep learning architectures (GRU) with specific activation functions. It demonstrates high empirical rigor by applying models to real-world financial data (S&P 500, gold, Bitcoin), implementing rigorous backtesting for volatility and risk forecasts (VaR, ES), and using established libraries (R’s rugarch) for estimation.
Research Flowchart
flowchart TD
A["Research Goal<br>Hybrid GARCH-DL Volatility &<br>Risk Forecasting"] --> B["Data & Targets"]
B --> C["Methodology<br>GARCH Models x GRU Networks"]
C --> D["Computational Process<br>Hybrid Forecast Generation"]
D --> E{"Risk Metrics Evaluation<br>VaR & ES at 5% & 1%"}
E --> F["Key Findings"]
subgraph B ["Data & Inputs"]
B1["S&P 500, Gold, Bitcoin<br>Daily Log Returns"]
B2["Target Variable<br>Garman-Klass Volatility Estimator"]
end
subgraph C ["Models"]
C1["GARCH<br>EGARCH, GJR-GARCH, APARCH"]
C2["Deep Learning<br>GRU Networks"]
end
subgraph D ["Process"]
D1["Train Models"]
D2["Generate Hybrid Forecasts"]
end
subgraph F ["Outcomes"]
F1["Superior Volatility<br>Point Forecasts"]
F2["No Significant Improvement<br>in VaR/ES Forecasts"]
end
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes a hybrid approach that combines GARCH econometric models with GRU deep learning networks for forecasting financial volatility and risk.
Source sentence
In this paper, we develop a hybrid approach to forecasting the volatility and risk of financial instruments by combining common econometric GARCH time series models with deep learning neural networks.
Assumes 6
- The GKYZ price‑range estimator (based on opening, high, low, close) is used as the target volatility measure. model
Source sentence
As the main volatility estimator, also underlying the target function of our hybrid models, we use the price-range-based Garman‑Klass estimator, modified to incorporate the opening and closing prices.
- The estimator is scaled to match the magnitude of GARCH volatility estimates using the formula of Fiszeder (2005, 2009). model
Source sentence
To that end, the following formula proposed by Fiszeder (2005, 2009) is employed
- Daily logarithmic returns are the input data for both GARCH and GRU components. data
Source sentence
Models are tested using daily logarithmic returns on the S&P 500 index as well as gold price Bitcoin prices
- GRU network training uses Adam optimizer with learning rate 0.0009 and MSE loss against GKYZ forecasts. model
Source sentence
For the network optimisation, we use Adam optimiser (Kingma & Ba, 2017), with the learning rate set to 0.0009. The loss function is defined as the mean square error between the GKYZ volatility estimates at time t+1 and the network output
Show 2 more
- Return forecasts are generated only by the underlying GARCH model, not by the hybrid GRU component. model
Source sentence
GARCH model, and thereby are not further processed through the hybrid GARCH‑GRU structure.
- Statistical significance of MSE differences is assessed with Diebold‑Mariano test (Harvey et al. modification). statistical
Source sentence
Differences between the MSEs for two competing models are tested for their statistical significance via the Diebold & Mariano (1995) test, with a modification proposed by Harvey, Leybourne & Newbold (1997).
Data
- S&P 500 index daily returns market-prices public
Source sentence
the S&P 500 index (5‑day week, quotations over 6 April 2009 to 31 December 2020)
- Bitcoin (BTC/USD) daily returns crypto-onchain public
Source sentence
Bitcoin (BTC/USD; 7‑day week, quotations over 5 August 2013 to 31 December 2020)
- Gold (XAU/USD) daily returns market-prices public
Source sentence
gold (XAU/USD; 5‑day week, quotations over 8 July 2010 to 31 December 2020)
Costs
Not applicable
Finds 5
- Hybrid GARCH‑GRU models achieve substantially lower MSE in point volatility forecasts compared with pure GARCH models. predictive-accuracy
Source sentence
combining GARCH and GRU models largely improves volatility forecasts. Enhancing a GARCH model with a GRU network results in a one‑ or two‑order‑of‑magnitude drop in MSE
- The improvement in volatility forecasting does not consistently translate into superior VaR and ES forecasts; the best risk‑forecasting specification varies by asset and confidence level. performance
Source sentence
the gains from the volatility prediction by means of the hybrid GARCH‑GRU structures do not appear to translate unanimously into superior Value at Risk and Expected Shortfall forecasts
- For S&P 500 and gold, EGARCH‑GRU (skewed t for S&P 500, symmetric t for gold) yields the lowest volatility MSE; for Bitcoin, APARCH‑GRU with normal distribution is best. predictive-accuracy
Source sentence
for each of the three assets under consideration, it was a hybrid model that emerged superior for the point volatility forecasting (in terms of MSE): EGARCH‑GRU models for S&500 and gold (under a skewed and a symmetric t‑distribution, respectively), while APARCH‑GRU (with a normal distribution) – for Bitcoin
- Risk‑assessment at 5% and 1% tolerances is best served by different hybrid specifications per asset (e.g., GJR‑GRU for S&P 500 at 5%, AP‑GRU for Bitcoin at 5%). performance
Source sentence
S&P 500: GJR(SSTD)-GRU at the 5% tolerance, and AP(SSTD) at 1%; Bitcoin: AP(N) at 5%, and AP(STD) at 1%; gold: G(STD)-GRU and E(N)-GRU at 5%, and G(SSTD) at 1%
- Statistical tests (Diebold‑Mariano) show that many MSE reductions are significant, though some hybrid‑vs‑pure comparisons are not statistically significant. statistical
Source sentence
the difference appears either statistically insignificant (conditionally normal EGARCH vs. EGARCH‑GRU) or at least not as statistically significant as one could expect (conditionally t‑distributed EGARCH vs. EGARCH‑GRU, and APARCH vs. APARCH‑GRU with a skewed t‑distribution)
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 45 related papers). Coverage is partial, so this is neither replication nor refutation.
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.