Multi-step-ahead stock price index forecasting using long short-term memory model with multivariate empirical mode decomposition

•MEMD- LSTM model for multi-step ahead stock price forecasting was built.•Multi-step ahead forecasting was based on the multiple-input multiple-output strategy.•MEMD was employed to decompose the original time series without information loss.•The proposed model demonstrated its superiority than othe...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Information sciences Ročník 607; s. 297 - 321
Hlavní autoři:	Deng, Changrui, Huang, Yanmei, Hasan, Najmul, Bao, Yukun
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Elsevier Inc 01.08.2022
Témata:	Long short-term memory Multi-step-ahead forecasting Multivariate empirical mode decomposition Orthogonal array tuning method Stock price index Long short-term memory Stock price index Multi-step-ahead forecasting Orthogonal array tuning method Multivariate empirical mode decomposition
ISSN:	0020-0255, 1872-6291
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	•MEMD- LSTM model for multi-step ahead stock price forecasting was built.•Multi-step ahead forecasting was based on the multiple-input multiple-output strategy.•MEMD was employed to decompose the original time series without information loss.•The proposed model demonstrated its superiority than other machine learning models.•The methodology goes well beyond straightforward application of the stock market. Accurate and reliable multi-step-ahead forecasting of stock price indexes over long-term future trends is challenging for capital investors and decision-makers. This study developed a hybrid stock price index forecasting modelling framework using Long Short-Term Memory (LSTM) with Multivariate Empirical Mode Decomposition (MEMD), which can capture the inherent features of the complex dynamics of stock price index time series. In conjunction with time–frequency analysis and deep learning algorithms, the proposed modelling framework implemented multi-step-ahead forecasting for stock price indexes using a multiple-input multiple-output (MIMO) strategy, where MEMD was first employed to simultaneously decompose the relevant features of the stock price index. Then LSTM was used to train the forecasting model by using the components extracted by MEMD and performing multi-step-ahead forecasting of the closing price of the stock price index. The hyperparameters of the LSTM model were optimized using an orthogonal array tuning method (OATM) based on the Taguchi design of experiments for enhancing the performance of prediction. Three real-world datasets were used for model validation from three exchange markets including Standard & Poor 500 index (SPX), Shanghai Stock Exchange (SSE), and Hang Seng Index (HSI). The results of the experiments suggested that the proposed hybrid model outperforms the benchmark models and improves the accuracy of multi-step-ahead forecasting.
ISSN:	0020-0255 1872-6291
DOI:	10.1016/j.ins.2022.05.088