hugogobato / introducing-nbeatsx-to-realized-volatility-forecasting

Data and Calculations used for the research Introducing NBEATSx to Realized Volatility Forecasting

Introducing NBEATSx to Realized Volatility Forecasting

Results and Code used for the research Introducing NBEATSx to Realized Volatility Forecasting

Authors: Hugo Gobato Souto and Amir Moradi*

*Corresponding author,

International School of Business at HAN University of Applied Sciences, Ruitenberglaan 31, 6826 CC Arnhem, the Netherlands; [email protected]; ORCID code: 0000-0003-1169-7192

Abstract This paper investigates the application of neural basis expansion analysis with exogenous variables (NBEATSx) in the prediction of daily stock realized volatility for various time steps. It compares NBEATSx’s forecasting accuracy and robustness with several commonly used models, namely Long-Short Term Memory (LSTM) network, Temporal Neural Network (TCN), HAR, GARCH, and GJR-GARCH models. In this research, a total of six distinct stock indexes, three error measures, and four statistical tests are used, while three robustness tests are conducted to verify the outcomes of this paper. The findings of this research show that NBEATSx consistently yields statistically more accurate and robust forecasts than the other considered models. On average, NBEATSx generates forecasts that are respectively 13% and 8% more accurate for medium-term and long-term forecasting. Additionally, it produces forecasts that are respectively 43%, 60%, and 59% more robust for short-term, medium-term, and long-term forecasting. Yet, it should be noted that the superiority of NBEATSx in terms of forecast accuracy is not evident when applied to stock indexes from developing countries.

Suggested Citation: Souto, H.G. & Moradi, A. (2023) Introducing NBEATSx to Realized Volatility Forecasting. Expert Systems with Applications, 242. https://doi.org/10.1016/j.eswa.2023.122802