Advertisement
Published in:
2021 | OriginalPaper | Chapter
A Deep Hybrid Neural Network Forecasting for Multivariate Non-stationary Time Series
Authors : Xiaojian Yang, Xiyu Liu
Published in: Human Centered Computing
Publisher: Springer International Publishing
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Abstract
In the field of financial time series prediction, multivariate time series is increasingly considered as the input of the prediction model and non-stationary time series have always been the most common data sets. However, the processing efficiency is low but the cost is high whenthe traditional methods is used for modeling non-stationary time series. This paper is aimed at providing the methodological guidance for building low-cost models for modeling multivariate non-stationary time series. By building a univariate CNN, a multivariate CNN, a nonpooling CNN (NPCNN), a CNN-LSTM and a NPCNN-LSTM, we conducted a series of comparative experiments. We found that multivariate non-stationary time series is not complex enough, the pooling operation will lose the useful information and the LSTM layer can weaken this negative effect. Meanwhile, convolutional layers and LSTM layers can improve the prediction accuracy. Adding the LSTM to prediction models can make models have better performance in short-term prediction.