Research on SZSE Component Index Volatility Prediction Based on CEEMDAN-BiLSTM
Modern Economics & Management Forum · 03.06.2026 · 7 (2) · 156
DOI: 10.32629/memf.v7i2.5179 ↗Kurz gefasst
Fachartikel in der Zeitschrift Modern Economics & Management Forum, online erschienen am 03.06.2026. Verfasst von Xin Yang. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
This study proposes a hybrid framework combining CEEMDAN and BiLSTM to predict high-frequency volatility of the SZSE Component Index. CEEMDAN first decomposes the volatility series into multi-scale components, which are then modeled individually by BiLSTM networks. Using 1-minute intraday data from 2014 to 2024, the proposed model significantly improves forecasting accuracy, achieving an R² of 0.9325 and reducing MAPE to 19.045%, substantially outperforming standard BiLSTM (R² = 0.5365, MAPE = 33.246%). Results demonstrate that signal decomposition effectively enhances the modeling of multi-scale volatility dynamics.
Zitieren
APA
Yang, X. (2026). Research on SZSE Component Index Volatility Prediction Based on CEEMDAN-BiLSTM. Modern Economics & Management Forum, 7(2), 156. https://doi.org/10.32629/memf.v7i2.5179
Vancouver
Yang X. Research on SZSE Component Index Volatility Prediction Based on CEEMDAN-BiLSTM. Modern Economics & Management Forum. 2026;7(2):156. doi:10.32629/memf.v7i2.5179
BibTeX
@article{Yang2026,
author = {Yang, Xin},
title = {Research on SZSE Component Index Volatility Prediction Based on CEEMDAN-BiLSTM},
journal = {Modern Economics & Management Forum},
year = {2026},
volume = {7},
number = {2},
pages = {156},
doi = {10.32629/memf.v7i2.5179}
}
EUVIMED