Asian stock markets closing index forecast based on secondary decomposition, multi-factor analysis and attention-based LSTM model

Wang, Jujie; Cui, Quan; Sun, Xin; He, Maolin

doi:10.1016/j.engappai.2022.104908

Cited by 59 publications

(12 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This model had multifactor analysis, secondary decomposition, and an attention-based LSTM. The accuracy of the proposed module is 30%, and the MAPE is also lower than in other models [11]. Many researchers compared the LSTM algorithm with traditional machine learning algorithms like linear regression SVM, but the accuracy of the LSTM algorithm is better as compared to other algorithms, so in this analysis we are focusing on the features that are provided to the LSTM model because effective feature selection produced better output, so in this study we have provided technical indicators like RSI and different combinations of EMA like slow EMA, medium EMA, and fast EMA to improve the accuracy of the LSTM model.…”

Section: Introductionmentioning

confidence: 75%

Stock market prediction using the LSTM algorithm in association with the Relative Strength Index (RSI) and Exponential Moving Average (EMA) indicators.

Dhokane,

Agarwal

2023

Preprint

View full text Add to dashboard Cite

Because of the unpredictable nature of the financial market, stock prediction is very difficult. To invest investors' hard-earned money in the financial market, we require additional information. Traditional models like linear regression and Support Vector Regression (SVR) are used to predict stock prices, but they do not have much accuracy. Recurrent Neural Network (RNN) is having "vanishing gradient" issues. In this study, we explain the technique of combining the Long Short-Term Memory (LSTM) machine learning algorithm with leading indicators like the Relative Strength Index (RSI) and the Exponential Moving Average (EMA), i.e., the slow EMA, medium EMA, and fast EMA. For this study, we have selected seven different stocks from the National Stock Exchange (NSE), and the dataset period is from January 1, 2012, to December 31, 2022. When we add extra features like RSI, 50-day EMA, 100-day EMA, and 150-day EMA to traditional ones like open, high, low, close, and volume, we get better results than when we only use traditional ones like open, high, low, close, and volume. When the indicators are added along with the traditional features, the Mean Absolute Percentage Error (MAPE) goes down, the R2 score (coefficient of determination) goes up, and the model does better than the conventional model. This study and analysis helps to improve intraday trading by predicting the value and trend of certain stocks.

show abstract

Section: Introductionmentioning

confidence: 75%

Stock market prediction using the LSTM algorithm in association with the Relative Strength Index (RSI) and Exponential Moving Average (EMA) indicators.

Dhokane,

Agarwal

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…CEEMDAN is an improvement from EMD, while borrowing from the EEMD method by adding Gaussian noise and by multiple superposition and however, CEEMDAN can easily produce residual noise and false parts. Currently, ICEEM-DAN has been extensively applied to the prediction of the price of metals [38], stock price forecasting [39], and wind speed forecasting [40], etc. The ICEEMDAN decomposition algorithm is as blow:…”

Section: Improved Complementary Ensemble Empirical Mode Decomposition...mentioning

confidence: 99%

Hybrid Neural Network Wind Speed Prediction Based on Secondary Decomposition and Weighted Averaging

Bi,

Bai,

Hou

et al. 2024

Preprint

View full text Add to dashboard Cite

The randomicity and fluctuation of the wind speed will influence the precision of the forecast. To improve the precision of wind speed forecast, this paper presents a new method of combined wind speed forecast based on the second decomposition and weighted average. First, the ICEEMDAN decomposition method is used to get different sub-sequences, and then the fuzzy entropy is used to judge the degree of confusion of the sub-sequences. In this paper, the ARIMA model is used to predict the minimum fuzzy entropy. And the other subsequences are decomposed by BPNN, VMD and predicted by NAR and BP neural network with suitable weighting ratio for weighted average and PSO-LSTM neural network respectively, and ultimately all the predicted values are superimposed to get the final prediction. Experiments were conducted using three datasets and eight comparison models to verify the validity of this model. The prediction analysis was carried out using the actual measured data of a wind farm in Inner Mongolia, and the results indicated that (1) using fuzzy entropy can effectively improve the prediction precision; (2) the prediction accuracy of the combined prediction method of neural network based on secondary decomposition was greatly improved and the prediction results were more reliable; (3) Decompose one of the subsequences with VMD, predict it with NAR and BP neural network, and choose appropriate weight ratio for weighted average prediction will achieve better prediction results; (4) the root mean square error (RMSE) of the hybrid model on the three wind speed 1 datasets were 0.28777, 0.22786 and 0.17128, which are lower than the comparison values of other models. So, it is workable to use this hybrid model in wind speed prediction.

show abstract

“…[10] developed a prediction model based on VMD and LSTM for stock price prediction. A more recent paper by Wang et al [26] proposed a novel hybrid method based on secondary decomposition (SD), multi-factor analysis, and attention-based LSTM. In this method, SD uses improved VMD and improved CEEMDAN to filter the noise effectively and capture additional nonlinear features.…”

Section: Literature Reviewmentioning

confidence: 99%

Multi-step-ahead Stock Price Prediction Using Recurrent Fuzzy Neural Network and Variational Mode Decomposition

Nasiri¹,

Ebadzadeh²

2022

Preprint

View full text Add to dashboard Cite

<p>Financial time series prediction, a growing research topic, has attracted considerable interest from scholars, and several approaches have been developed. Among them, decomposition-based methods have achieved promising results. Most decomposition-based methods approximate a single function, which is insufficient for obtaining accurate results. Moreover, most existing researches have concentrated on one-step-ahead forecasting that prevents stock market investors from arriving at the best decisions for the future. This study proposes two novel methods for multi-step-ahead stock price prediction based on the issues outlined. DCT-MFRFNN, a method based on discrete cosine transform (DCT) and multi-functional recurrent fuzzy neural network (MFRFNN), uses DCT to reduce fluctuations in the time series and simplify its structure and MFRFNN to predict the stock price. VMD-MFRFNN, an approach based on variational mode decomposition (VMD) and MFRFNN, brings together their advantages. VMD-MFRFNN consists of two phases. The input signal is decomposed to several IMFs using VMD in the decomposition phase. In the prediction and reconstruction phase, each of the IMFs is given to a separate MFRFNN for prediction, and predicted signals are summed to reconstruct the output. Three financial time series, including Hang Seng Index (HSI), Shanghai Stock Exchange (SSE), and Standard & Poor's 500 Index (SPX), are used for the evaluation of the proposed methods. Experimental results indicate that VMD-MFRFNN surpasses other state-of-the-art methods. VMD-MFRFNN, on average, shows 35.93%, 24.88%, and 34.59% decreases in RMSE from the second-best model for HSI, SSE, and SPX, respectively. Also, DCT-MFRFNN outperforms MFRFNN in all experiments.</p>

show abstract

Asian stock markets closing index forecast based on secondary decomposition, multi-factor analysis and attention-based LSTM model

Cited by 59 publications

References 41 publications

Stock market prediction using the LSTM algorithm in association with the Relative Strength Index (RSI) and Exponential Moving Average (EMA) indicators.

Stock market prediction using the LSTM algorithm in association with the Relative Strength Index (RSI) and Exponential Moving Average (EMA) indicators.

Hybrid Neural Network Wind Speed Prediction Based on Secondary Decomposition and Weighted Averaging

Multi-step-ahead Stock Price Prediction Using Recurrent Fuzzy Neural Network and Variational Mode Decomposition

Contact Info

Product

Resources

About