Details
| Originalsprache | Englisch |
|---|---|
| Seiten (von - bis) | 1539-1555 |
| Seitenumfang | 17 |
| Fachzeitschrift | International Journal of Forecasting |
| Jahrgang | 40 |
| Ausgabenummer | 4 |
| Frühes Online-Datum | 25 Jan. 2024 |
| Publikationsstatus | Veröffentlicht - Okt. 2024 |
Abstract
This paper presents a dynamic network autoregressive conditional heteroscedasticity (ARCH) model suitable for high-dimensional cases where multivariate ARCH models are typically no longer applicable. We adopt the theoretical foundations from spatiotemporal statistics and transfer the dynamic ARCH model processes to networks. The model integrates temporally lagged volatility and information from adjacent nodes, which may instantaneously spill across the entire network. The model is used to forecast volatility in the US stock market, and the edges are determined based on various distance and correlation measures between the time series. The performance of alternative network definitions is compared with independent univariate log-ARCH models in terms of out-of-sample prediction accuracy. The results indicate that more accurate forecasts are obtained with network-based models and that accuracy can be improved by combining the forecasts of different network definitions. We emphasise the significance for practitioners to integrate network structure information when developing volatility forecasts.
ASJC Scopus Sachgebiete
- Betriebswirtschaft, Management und Rechnungswesen (insg.)
- Betriebswirtschaft und Internationales Management
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
in: International Journal of Forecasting, Jahrgang 40, Nr. 4, 10.2024, S. 1539-1555.
Publikation: Beitrag in Fachzeitschrift › Artikel › Forschung › Peer-Review
}
TY - JOUR
T1 - Network log-ARCH models for forecasting stock market volatility
AU - Mattera, Raffaele
AU - Otto, Philipp
N1 - Publisher Copyright: © 2024 The Author(s)
PY - 2024/10
Y1 - 2024/10
N2 - This paper presents a dynamic network autoregressive conditional heteroscedasticity (ARCH) model suitable for high-dimensional cases where multivariate ARCH models are typically no longer applicable. We adopt the theoretical foundations from spatiotemporal statistics and transfer the dynamic ARCH model processes to networks. The model integrates temporally lagged volatility and information from adjacent nodes, which may instantaneously spill across the entire network. The model is used to forecast volatility in the US stock market, and the edges are determined based on various distance and correlation measures between the time series. The performance of alternative network definitions is compared with independent univariate log-ARCH models in terms of out-of-sample prediction accuracy. The results indicate that more accurate forecasts are obtained with network-based models and that accuracy can be improved by combining the forecasts of different network definitions. We emphasise the significance for practitioners to integrate network structure information when developing volatility forecasts.
AB - This paper presents a dynamic network autoregressive conditional heteroscedasticity (ARCH) model suitable for high-dimensional cases where multivariate ARCH models are typically no longer applicable. We adopt the theoretical foundations from spatiotemporal statistics and transfer the dynamic ARCH model processes to networks. The model integrates temporally lagged volatility and information from adjacent nodes, which may instantaneously spill across the entire network. The model is used to forecast volatility in the US stock market, and the edges are determined based on various distance and correlation measures between the time series. The performance of alternative network definitions is compared with independent univariate log-ARCH models in terms of out-of-sample prediction accuracy. The results indicate that more accurate forecasts are obtained with network-based models and that accuracy can be improved by combining the forecasts of different network definitions. We emphasise the significance for practitioners to integrate network structure information when developing volatility forecasts.
KW - ARCH models
KW - Financial networks
KW - Network processes
KW - Risk prediction
KW - Spatial econometrics
KW - Stock market volatility
UR - http://www.scopus.com/inward/record.url?scp=85185186204&partnerID=8YFLogxK
U2 - 10.48550/arXiv.2303.11064
DO - 10.48550/arXiv.2303.11064
M3 - Article
AN - SCOPUS:85185186204
VL - 40
SP - 1539
EP - 1555
JO - International Journal of Forecasting
JF - International Journal of Forecasting
SN - 0169-2070
IS - 4
ER -