Modeling and Predicting Time Series with Non-stationarity and Volatility

The difficulty of time series prediction lies in how to handle non-stationarity and volatility. When dealing with non-stationarity, existing deep learning models adopt a method of stabilizing the input sequences before training, which has problems of weak ability to eliminate non-stationarity or los...

Cijeli opis

Spremljeno u:
Bibliografski detalji
Glavni autor: FENG Qiang, ZHAO Jianguang, YANG Rong, NIU Baoning
Format: Artigo
Jezik:Chinês
Izdano: Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press 2025-05-01
Serija:Jisuanji kexue yu tansuo
Teme:
time series prediction; non-stationarity; high volatility; long short-term memory neural network; multi-head self-attention
Online pristup:http://fcst.ceaj.org/fileup/1673-9418/PDF/2407096.pdf
Oznake: Dodaj oznaku
Bez oznaka, Budi prvi tko označuje ovaj zapis!

Similar Items