A Machine Learning Approach to Volatility Forecasting
Journal of Financial Econometrics · 15.11.2023 · 21 (5) · 1680-1727
DOI: 10.1093/jjfinec/nbac020 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Financial Econometrics, online erschienen am 30.06.2022. Verfasst von Kim Christensen und 2 weiteren Autor:innen. Die Arbeit wurde bisher 125-mal zitiert (Crossref) und nennt 70 Literaturangaben.
Abstract (Originalsprache)
We inspect how accurate machine learning (ML) is at forecasting realized variance of the Dow Jones Industrial Average index constituents. We compare several ML algorithms, including regularization, regression trees, and neural networks, to multiple heterogeneous autoregressive (HAR) models. ML is implemented with minimal hyperparameter tuning. In spite of this, ML is competitive and beats the HAR lineage, even when the only predictors are the daily, weekly, and monthly lags of realized variance. The forecast gains are more pronounced at longer horizons. We attribute this to higher persistence in the ML models, which helps to approximate the long memory of realized variance. ML also excels at locating incremental information about future volatility from additional predictors. Lastly, we propose an ML measure of variable importance based on accumulated local effects. This shows that while there is agreement about the most important predictors, there is disagreement on their ranking, helping to reconcile our results.
Zitieren
APA
Christensen, K., Siggaard, M., & Veliyev, B. (2023). A Machine Learning Approach to Volatility Forecasting. Journal of Financial Econometrics, 21(5), 1680-1727. https://doi.org/10.1093/jjfinec/nbac020
Vancouver
Christensen K, Siggaard M, Veliyev B. A Machine Learning Approach to Volatility Forecasting. Journal of Financial Econometrics. 2023;21(5):1680-1727. doi:10.1093/jjfinec/nbac020
BibTeX
@article{Christensen2023,
author = {Christensen, Kim and Siggaard, Mathias and Veliyev, Bezirgen},
title = {A Machine Learning Approach to Volatility Forecasting},
journal = {Journal of Financial Econometrics},
year = {2023},
volume = {21},
number = {5},
pages = {1680--1727},
doi = {10.1093/jjfinec/nbac020}
}
EUVIMED