Cryptocurrency volatility forecasting using commonality in intraday volatility
Open Access
- 25 November 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 436-444
Abstract
We investigate the benefits of using intraday realized volatility (RV) commonality, and propose a novel non-parametric framework for forecasting one-day ahead intraday RV (1D-ahead intraday RV). Specifically, we train multiple models using machine learning (ML) techniques under various training settings (single-asset, cluster-driven, and cross-asset), where commonality gradually enters model dynamics as training schemes become more complex. We conclude that models that leverage the cryptocurrency commonality outperform models that do not explicitly account for it, regardless of the market regime considered. The source code of this project is available at: github.com/edjanga/crypto_volatility_commonality.Keywords
This publication has 27 references indexed in Scilit:
- Forecasting intraday volatility in the US equity market. Multiplicative component GARCHJournal of Financial Econometrics, 2011
- Volatility forecast comparison using imperfect volatility proxiesJournal of Econometrics, 2011
- Asymmetric volatility in the foreign exchange marketsJournal of International Financial Markets, Institutions and Money, 2009
- A Simple Approximate Long-Memory Model of Realized VolatilityJournal of Financial Econometrics, 2008
- Dynamic Conditional CorrelationJournal of Business & Economic Statistics, 2002
- Measuring and Testing the Impact of News on VolatilityThe Journal of Finance, 1993
- Wavelet transforms and atmopsheric turbulencePhysical Review Letters, 1993
- The autocorrelation structure for the GARCH-M processEconomics Letters, 1991
- Silhouettes: A graphical aid to the interpretation and validation of cluster analysisJournal of Computational and Applied Mathematics, 1987
- Generalized autoregressive conditional heteroskedasticityJournal of Econometrics, 1986