Analyzing Volatility Forecasting Capabilities of Neural Network Enhanced ARCH Models
DOI:
https://doi.org/10.47611/jsrhs.v11i3.3561Keywords:
Financial Econometrics, Volatility Forecasting, Neural Networks, Forecasting, Time-Series Forecasting, EconometricsAbstract
Examines the capabilities of Autoregressive-Conditional-Heteroskedasticity (ARCH) family models (with Artificial Neural Networks) to predict volatility of thirty equities from a five-year fiscal-period. The models underwent the maximization of its parameters through Hessian matrices and were used to predict volatility by maximizing the log-likelihood function. Trained Long-Short-Term-Memory models using Neural-Net-Enhanced-ARCH algorithms and calculated the Root-Mean-Square-Error. Found the RMSE value of the traditional ARCH/GARCH models as 1.1695 as opposed to the algorithm’s 0.8763.
Downloads
References or Bibliography
Bollerslev, T. (2008). Glossary to arch (garch). CREATES Research paper, 49.
BookDown . (n.d.). https://bookdown.org/compfinezbook/introcompfinr/maximum -likelihood-estimation.html#the-likelihood-function. (Accessed: 2022-0130)
Brownlees, C. T., Engle, R. F., & Kelly, B. T. (2011). A practical guide to volatility forecasting through calm and storm. Available at SSRN 1502915.
Christensen, K., Siggaard, M., Veliyev, B., et al. (2021). A machine learning approach to volatility forecasting (Vol. 3). Department of Economics and Business Economics, Aarhus University.
GitHub. (n.d.). https://github.com/. (Accessed: 2022-02-01)
Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735–1780.
Jia, F., & Yang, B. (2021). Forecasting volatility of stock index: deep learning model with likelihood-based loss function. Complexity, 2021.
Malliaris, M., & Salchenberger, L. (1996). Using neural networks to forecast the s&p 100 implied volatility. Neurocomputing, 10(2), 183–195.
MarketWatch . (n.d.). https://www.marketwatch.com/. (Accessed: 2022-01-36)
Ormoneit, D., & Neuneier, R. (1996). Experiments in predicting the german stock index dax with density estimating neural networks. In Ieee/iafe 1996 conference on computational intelligence for financial engineering (cifer) (pp. 66–71).
Sharma, S., Sharma, S., & Athaiya, A. (2017). Activation functions in neural networks. towards data science, 6(12), 310–316.
Templeton, G. (2018). Artificial neural networks are changing the world. What are they.
Xie, Y. (2007). Maximum likelihood estimation and forecasting for garch, markov switching, and locally stationary wavelet processes (Vol. 2007) (No. 2007: 107).
Published
How to Cite
Issue
Section
Copyright (c) 2022 Priyansh Singh; Erin O'Rourke
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Copyright holder(s) granted JSR a perpetual, non-exclusive license to distriute & display this article.
