Dynamic functional time-series forecasts of foreign exchange implied volatility surfaces
Abstract
This paper presents static and dynamic versions of univariate, multivariate, and multilevel functional time-series methods to forecast implied volatility surfaces in foreign exchange markets. We find that dynamic functional principal component analysis generally improves out-of-sample forecast accuracy. More specifically, the dynamic univariate functional time-series method shows the greatest improvement. Our models lead to multiple instances of statistically significant improvements in forecast accuracy for daily EUR-USD, EUR-GBP, and EUR-JPY implied volatility surfaces across various maturities, when benchmarked against established methods. A stylised trading strategy is also employed to demonstrate the potential economic benefits of our proposed approach.
Keywords
Cite
@article{arxiv.2107.14026,
title = {Dynamic functional time-series forecasts of foreign exchange implied volatility surfaces},
author = {Han Lin Shang and Fearghal Kearney},
journal= {arXiv preprint arXiv:2107.14026},
year = {2021}
}
Comments
52 pages, 5 figures, to appear at the International Journal of Forecasting