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

Svetlana Borovkova; Ioannis Tsiamas

doi:10.1002/for.2585

journal article Open Access May 10, 2019

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

Svetlana Borovkova

Ioannis Tsiamas

Journal of Forecasting Vol. 38 No. 6 pp. 600-619 · Wiley

View at Publisher Save 10.1002/for.2585

Abstract

AbstractWe propose an ensemble of long–short‐term memory (LSTM) neural networks for intraday stock predictions, using a large variety of technical analysis indicators as network inputs. The proposed ensemble operates in an online way, weighting the individual models proportionally to their recent performance, which allows us to deal with possible nonstationarities in an innovative way. The performance of the models is measured by area under the curve of the receiver operating characteristic. We evaluate the predictive power of our model on several US large‐cap stocks and benchmark it against lasso and ridge logistic classifiers. The proposed model is found to perform better than the benchmark models or equally weighted ensembles.

Topics

No keywords indexed for this article. Browse by subject →

References

21

[1]

10.1080/13518479500000023

[2]

A deep learning framework for financial time series using stacked autoencoders and long-short term memory

Wei Bao, Jun Yue, Yulei Rao

PLoS ONE 10.1371/journal.pone.0180944

[3]

Learning Deep Architectures for AI

Y. Bengio

Foundations and Trends® in Machine Learning 10.1561/2200000006

[4]

10.1007/978-3-642-35289-8_26

[5]

10.2307/2325486

[6]

Fischer T. &Krauss C.(2017).Deep learning with long short‐term memory networks for financial market predictions. (AU Discussion Papers in Economics).Erlangen Germany: Friedrich‐Alexander University Erlangen‐Nuremberg Institute for Economics.

[7]

Glorot X. "Understanding the difficulty of training deep feedforward neural networks" Journal of Machine Learning Research (2010)

[8]

Hegazy O. "A machine learning model for stock market prediction" International Journal of Computer Science and Telecommunications (2013)

[9]

Hinton G. Srivastava N. &Swersky K.(2012).Neural networks for machine learning. (Lecture 6).Toronto Canada: University of Toronto.

[10]

Long Short-Term Memory

Sepp Hochreiter, Jürgen Schmidhuber

Neural Computation 10.1162/neco.1997.9.8.1735

[11]

10.1016/j.cor.2004.03.016

[12]

Kennedy J. &Eberhart R.(1995).Particle swarm optimization In.Proceedings IEEE International Conference on Neural Networks.Piscataway NJ:IEEE Vol. 4 pp.1942–1948.

[13]

Kent A. (1989)

[14]

Lei Ba J. Kiros J. R. &Hinton G. E.(2016).Layer normalization. Retrieved from arXiv:1607.06450.

[15]

10.1109/ijcnn.2017.7966019

[16]

10.1016/j.omega.2004.07.024

[17]

Qu H. "A new kernel of support vector regression for forecasting high‐frequency stock returns" Mathematical Problems in Engineering (2016)

[18]

Rechenthin M. D.(2014).Machine‐learning classification techniques for the analysis and prediction of high‐frequency stock direction. (PhD thesis) University of Iowa.

[19]

10.1016/0893-6080(94)90030-2

[20]

Semeniuta S. Severyn A. &Barth E.(2016).Recurrent dropout without memory loss. Retrieved from arXiv:1603.05118.

[21]

Srivastava N. "Dropout: A simple way to prevent neural networks from overfitting" Journal of Machine Learning Research (2014)

Cited By

176

Performance Evaluation of Long Short-Term Memory and Autoregressive Integrated Moving Average Time Series Models for Stock Price Prediction

Adeniran, Rachel Ihunanya., Olabiyisi, Stephen Olatunde. · 2025

International Journal of Latest Tec...

An efficient hybrid approach for forecasting real-time stock market indices

Riya Kalra, Tinku Singh · 2024

Journal of King Saud University - C...

Crude Oil Price Time Series Forecasting: A Novel Approach Based on Variational Mode Decomposition, Time-Series Imaging, and Deep Learning

Zi-Jian Peng, Chuan Zhang · 2023

IEEE Access

Machine learning techniques and data for stock market forecasting: A literature review

Mahinda Mailagaha Kumbure, Christoph Lohrmann · 2022

Expert Systems with Applications

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

Audeliano Wolian Li, Guilherme Sousa Bastos · 2020

IEEE Access

Forecasting significant stock price changes using neural networks

Firuz Kamalov · 2020

Neural Computing and Applications

A CNN-BiLSTM-AM method for stock price prediction

Wenjie Lu, Jiazheng Li · 2020

Neural Computing and Applications

Metrics

176

Citations

21

References

Details

Published: May 10, 2019
Vol/Issue: 38(6)
Pages: 600-619
License: View

Authors

S

Svetlana Borovkova

School of Business and Economics Vrije Universiteit Amsterdam Amsterdam The Netherlands

I

Ioannis Tsiamas

School of Business and Economics Vrije Universiteit Amsterdam Amsterdam The Netherlands

Cite This Article

Svetlana Borovkova, Ioannis Tsiamas (2019). An ensemble of LSTM neural networks for high‐frequency stock market classification. Journal of Forecasting, 38(6), 600-619. https://doi.org/10.1002/for.2585

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

You May Also Like