EconBase
← All papers

A machine learning search for optimal GARCH parameters

Luke De Clerk, Sergey Savl'ev

arXiv 10 Jan 2022 · Econometrics

arXiv:2201.03286 · PDF · DOI · OpenAlex · Extracted main text

Abstract

Here, we use Machine Learning (ML) algorithms to update and improve the efficiencies of fitting GARCH model parameters to empirical data. We employ an Artificial Neural Network (ANN) to predict the parameters of these models. We present a fitting algorithm for GARCH-normal(1,1) models to predict one of the model's parameters, $\alpha_1$ and then use the analytical expressions for the fourth order standardised moment, $\Gamma_4$ and the unconditional second order moment, $\sigma^2$ to fit the other two parameters; $\beta_1$ and $\alpha_0$, respectively. The speed of fitting of the parameters and quick implementation of this approach allows for real time tracking of GARCH parameters. We further show that different inputs to the ANN namely, higher order standardised moments and the autocovariance of time series can be used for fitting model parameters using the ANN, but not always with the same level of accuracy.

Citation extraction

36
references
45
in-text mentions
36
distinct cited
1
self-citations
5,242
main-text words

appendix boundary found by appendix_command · 89% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1T. Bollerslev, “Generalised autoregressive conditional heteroscedast… (1986) Generalised autoregressive conditional heteroscedasticity1.00063100%
2R. Engle, “Autoregressive conditional heteroscedasticity with estima… (1982) Autoregressive conditional heteroscedasticity with estimates of the variance of uk inflation0.64422100%
3L. D. Clerk and S. Savel'ev, “Non-stationary modelling of garch to f… (2021) Non-stationary modelling of garch to fit higher order moments of financial series within fixed time windows self0.64422100%
4J. Hutchinson, A. Lo, and T. Poggio, “A nonparametric approach to pr… (1994) A nonparametric approach to pricing and hedging derivative securities via learning networks0.51121100%
5D. Nelson, “Conditional heteroskedastcicity in asset returns: A new… (1991) Conditional heteroskedastcicity in asset returns: A new approach0.51121100%
6A. Choudhary, S. Ahlawat, R. Rishi, and V. Dhaka, “Performance analy… (2010) Performance analysis of feed-foreward mlp with various activation functions for handwritten numerals recognition0.40511100%
7P. Sibi, S. A. Jones, and P. Siddarth, “Analysis of different activa… (2013) Analysis of different activation functions using back propagation neural networks0.40511100%
8V. Bushaev, “Adam- latest trends in deep learning optimization.” [On… Adam- latest trends in deep learning optimization0.40511100%
9J. Staccioli and M. Napolentano, “An agent-based model of intra-day… (2021) An agent-based model of intra-day financial market dynamics0.40511100%
10A. Fadlalla and C. Lin, “An analysis of the application of neural ne… (2001) An analysis of the application of neural networks in finance0.40511100%

Showing the top 10 of 36 scored citations.