Neural-Network Volatility Forecasting
Journal of Financial Econometrics · 07.07.2026 · 24 (4)
DOI: 10.1093/jjfinec/nbag019 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Financial Econometrics, online erschienen am 18.08.2026. Verfasst von Chen Liu und 4 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben.
Abstract (Originalsprache)
We investigate how training regimes and sample size affect the performance of neural networks in financial forecasting. Using volatility forecasts for more than 10,000 stocks, we find that, within the specifications studied, performance gains from sample size scaling outweigh those from model size scaling or architectural choice. We further show that, when NNs are applied to financial data, global estimation is better aligned with their data-intensive nature and materially enhances their practical viability.
Zitieren
APA
Liu, C., Tran, M., Wang, C., Gerlach, R., & Kohn, R. (2026). Neural-Network Volatility Forecasting. Journal of Financial Econometrics, 24(4). https://doi.org/10.1093/jjfinec/nbag019
Vancouver
Liu C, Tran M, Wang C, Gerlach R, Kohn R. Neural-Network Volatility Forecasting. Journal of Financial Econometrics. 2026;24(4). doi:10.1093/jjfinec/nbag019
BibTeX
@article{Liu2026,
author = {Liu, Chen and Tran, Minh-Ngoc and Wang, Chao and Gerlach, Richard and Kohn, Robert},
title = {Neural-Network Volatility Forecasting},
journal = {Journal of Financial Econometrics},
year = {2026},
volume = {24},
number = {4},
doi = {10.1093/jjfinec/nbag019}
}
EUVIMED