A Hybrid Prediction Method for Stock Price Using LSTM and Ensemble EMD

Yang, Yujun; Yang, Y.B.; Xiao, Jianhua

doi:10.1155/2020/6431712

Cited by 25 publications

(10 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, despite this feature of machine learning techniques, statistical methods are not entirely discarded from the set of opportunities. Likewise, EMD and its variants are used in literature as a preprocessing of non-linear and noisy data (Yujun, Yimei & Jianhua, 2020).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

News sensitive stock market prediction: literature review and suggestions

Usmani¹,

Shamsi²

2021

PeerJ Computer Science

View full text Add to dashboard Cite

Stock market prediction is a challenging task as it requires deep insights for extraction of news events, analysis of historic data, and impact of news events on stock price trends. The challenge is further exacerbated due to the high volatility of stock price trends. However, a detailed overview that discusses the overall context of stock prediction is elusive in literature. To address this research gap, this paper presents a detailed survey. All key terms and phases of generic stock prediction methodology along with challenges, are described. A detailed literature review that covers data preprocessing techniques, feature extraction techniques, prediction techniques, and future directions is presented for news sensitive stock prediction. This work investigates the significance of using structured text features rather than unstructured and shallow text features. It also discusses the use of opinion extraction techniques. In addition, it emphasizes the use of domain knowledge with both approaches of textual feature extraction. Furthermore, it highlights the significance of deep neural network based prediction techniques to capture the hidden relationship between textual and numerical data. This survey is significant and novel as it elaborates a comprehensive framework for stock market prediction and highlights the strengths and weaknesses of existing approaches. It presents a wide range of open issues and research directions that are beneficial for the research community.

show abstract

Section: Discussionmentioning

confidence: 99%

“…For instance, removing stop words, lowercasing, stemming, and lemmatizing etc. In (Symeonidis, Effrosynidis & Arampatzis, (Wang et al, 2011;Dai, Wu & Lu, 2012;Cavalcante et al, 2016;Liang et al, 2019), Data decomposition (Jin, Yang & Liu, 2019;Yujun, Yimei & Jianhua, 2020)…”

Section: News Preprocessingmentioning

confidence: 99%

News sensitive stock market prediction: literature review and suggestions

Usmani¹,

Shamsi²

2021

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

Section: Hybrid Modelsmentioning

confidence: 99%

“…The hybrid models based on the nonlinear decomposition method and prediction model are gaining importance in recent years. Discrete wavelet transforms (DWT) (Gilles, 2013; Iwabuchi et al, 2022; Liang et al, 2019; Tang et al, 2021) and EMD (Bedi & Toshniwal, 2018; Yujun et al, 2020) are among the popular methods for signal decomposition. A hybrid model combining wavelet transform (WT) with the statistical model is presented in Syah et al (2021), Yang et al (2017), and Zhang and Tan (2013).…”

Section: Introductionmentioning

confidence: 99%

Electricity price forecasting using hybrid deep learned networks

Singh

2023

Journal of Forecasting

View full text Add to dashboard Cite

This paper presents a novel hybrid model integrating maximal overlap discrete wavelet transform (MODWT) denoising and empirical mode decomposition (EMD) with sequence‐to‐sequence (seq2seq) long short‐term memory (LSTM) neural networks for day‐ahead electricity price forecasting. The nonstationary and nonlinear time series electricity price data are first denoised using MODWT. The resulting signal is decomposed into several intrinsic mode functions (IMF) with different resolutions by EMD. The extracted IMF is then introduced into seq2seq LSTM to obtain an aggregated predicted value for electricity price. The proposed method is examined using the Nord pool Elspot energy market data. Empirical results show that the proposed model outperformed the other forecasting models like LSTM and stacked LSTM. The performance measures indicate that data denoising can significantly improve the prediction stability and the generalization ability of the LSTM model.

show abstract

“…Empirical mode decomposition (EMD) does not require human intervention to decompose, so the problem of wavelet decomposition can be avoided. Nowadays, some scholars have applied EMD model to predict the price of stock index futures (Yang et al, 2020). However, EMD also has some defects, such as pattern aliasing, which will affect the decomposition results.…”

Section: Brief Literature Reviewmentioning

confidence: 99%

An XGBoost-based multivariate deep learning framework for stock index futures price forecasting

Wang

Qian

Dong

2022

View full text Add to dashboard Cite

PurposeWith the rapid development of the financial market, stock index futures have been the one of important financial instruments. Predicting stock index futures accurately can bring considerable benefits for investors. However, traditional models do not perform well in stock index futures forecasting. This study put forward a novel hybrid model to improve the predictive accuracy of stock index futures.Design/methodology/approachThis study put forward a multivariate deep learning framework based on extreme gradient boosting (XGBoost) for stock index futures price forecasting. First, the original sequences were decomposed into several sub-sequences by variational mode decomposition (VMD), and these sub-sequences were reconstructed by sample entropy (SE). Second, the gradient boosting decision tree (GBDT) was used to rank the feature importance of influential factors, and the top influential factors were chosen for further prediction. Next, reconstructed sequence and the multiple factors screened were input into the bidirectional gate recurring unit (BiGRU) for modeling. Finally, XGBoost was used to integrate the modeling results.FindingsFor the sake of examining the robustness of the proposed model, CSI 500 stock index futures, NASDAQ 100 index futures, FTSE 100 index futures and CAC 40 index futures are selected as sample data. The empirical consequences demonstrate that the proposed model can serve as an effective tool for stock index futures prediction. In other words, the proposed model can improve the accuracy of stock index futures.Originality/valueIn this paper, an innovative hybrid model is proposed to enhance the predictive accuracy of stock index futures. Meanwhile, this method can be applied in other financial products prediction to achieve better forecasting results.

show abstract

A Hybrid Prediction Method for Stock Price Using LSTM and Ensemble EMD

Cited by 25 publications

References 41 publications

News sensitive stock market prediction: literature review and suggestions

News sensitive stock market prediction: literature review and suggestions

Electricity price forecasting using hybrid deep learned networks

An XGBoost-based multivariate deep learning framework for stock index futures price forecasting

Contact Info

Product

Resources

About