An ensemble of LSTM neural networks for high‐frequency stock market classification

Borovkova, Svetlana; Tsiamas, Ioannis

doi:10.1002/for.2585

Cited by 160 publications

(94 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A model with two layers of LSTM stacked and generated 400 characteristics based on market information was proposed by [37]. However, for training, only 250 were randomly selected.…”

Section: ) Analysis Based On Predictor Techniquesmentioning

confidence: 99%

Stock Market Forecasting Using Deep Learning and Technical Analysis: A Systematic Review

Bastos

2020

IEEE Access

View full text Add to dashboard Cite

Stock market forecasting is one of the biggest challenges in the financial market since its time series has a complex, noisy, chaotic, dynamic, volatile, and non-parametric nature. However, due to computing development, an intelligent model can help investors and professional analysts reduce the risk of their investments. As Deep Learning models have been extensively studied in recent years, several studies have explored these techniques to predict stock prices using historical data and technical indicators. However, as the objective is to generate forecasts for the financial market, it is essential to validate the model through profitability metrics and model performance. Therefore, this systematic review focuses on Deep Learning models implemented for stock market forecasting using technical analysis. Discussions were made based on four main points of view: predictor techniques, trading strategies, profitability metrics, and risk management. This study showed that the LSTM technique is widely applied in this scenario (73.5%). This work significant contribution is to highlight some limitations found in the literature, such as only 35.3% of the studies analysed profitability, and only two articles implemented risk management. Therefore, despite the widely explored theme, there are still interesting open areas for research and development. INDEX TERMS Deep learning, profitability metrics, risk management, stock market forecasting, systematic review, technical analysis, technical indicators.

show abstract

“…A model with two layers of LSTM stacked and generated 400 characteristics based on market information was proposed by [37]. However, for training, only 250 were randomly selected.…”

Section: ) Analysis Based On Predictor Techniquesmentioning

confidence: 99%

Stock Market Forecasting Using Deep Learning and Technical Analysis: A Systematic Review

Bastos

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In the stock market prediction, many studies have been proposed based on ensemble methods. Borovkova and Tsiamas proposed an ensemble using LSTM for intraday stock predictions [73]. Qi, et al, used eight LSTM neural network with Bagging method to establish ensemble model for the prediction of Chinese Stock Market [74].…”

Section: Ensemble Learning Applicationsmentioning

confidence: 99%

On the Ensemble of Recurrent Neural Network for Air Pollution Forecasting: Issues and Challenges

Surakhi¹,

Serhan²,

Salah³

2020

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

Time-series is a sequence of observations that are taken sequentially over time. Modelling a system that generates a future value from past observations is considered as time-series forecasting system. Recurrent neural network is a machine learning method that is widely used in the prediction of future values. Due to variant improvements on recurrent neural networks, choosing of the best model for better prediction generation is dependent on problem domain and model design characteristics. Ensemble forecasting is more accurate than single model due to the combination of more than one model for forecasting. Designing an ensemble model of recurrent neural network for time-series forecasting applications would enhance prediction accuracy and improve performance. This paper highlights some of the challenges that are faced by the design of the ensemble model of different recurrent neural network versions, and surveys some of the most relevant works in order to give a direction of how to conduct ensemble learning research in the future. Based on the reviewed literature, we propose a framework for time-series forecasting based on the using of ensemble technique.

show abstract

“…A model that use LSTM was also used by Alessandretti et al [5] for predicting the cryptocurrency market where LSTM performed better for predictions with longer data days than models that use Gradient Boosting Decision Tree. LSTM for predicting stock price movements used in [17]- [19]. Nelson et al [20] used LSTM to predict stock market price movements.…”

Section: Bayesian Optimized Recurrent Neural Network Was Used Bymentioning

confidence: 99%

Artificial Bee Colony-Optimized LSTM for Bitcoin Price Prediction

Yuliyono¹,

Girsang²

2019

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

In recent years, deep learning has been widely used for time series prediction. Deep learning model that is most often used for time series prediction is LSTM. LSTM is widely used because of its excellence in remembering very long sequences. However, doing training on models that use LSTM requires a long time. Trying from one model to another model that use LSTM will take a very long time, thus a method is needed for optimizing hyperparameter to get a model with a small RMSE. This research proposed Artificial Bee Colony (ABC) as a method in optimizing hyperparameter for models that use LSTM. ABC is a metaheuristic method that mimics the behavior of bee colonies in foraging. Optimized hyperparameter in this research consisted of sliding window size, number of LSTM units, dropout rate, regularizer, regularizer rate, optimizer and learning rate. In this research the proposed method called as ABC-LSTM. Bitcoin prices historical data was used as the dataset for evaluating the prediction of the models. The best ABC-LSTM model resulted best RMSE of 189.61 compared to model that use LSTM without optimization resulted best RMSE of 236.17. This result showed that ABC-LSTM model outperformed models that use LSTM without optimization.

show abstract

An ensemble of LSTM neural networks for high‐frequency stock market classification

Cited by 160 publications

References 15 publications

Stock Market Forecasting Using Deep Learning and Technical Analysis: A Systematic Review

Stock Market Forecasting Using Deep Learning and Technical Analysis: A Systematic Review

On the Ensemble of Recurrent Neural Network for Air Pollution Forecasting: Issues and Challenges

Artificial Bee Colony-Optimized LSTM for Bitcoin Price Prediction

Contact Info

Product

Resources

About