Chaotic Recurrent Neural Networks for Financial Forecast

Jeff Wang; Raymond Lee

doi:doi:10.11648/j.ajnna.20210701.12

| Peer-Reviewed

Chaotic Recurrent Neural Networks for Financial Forecast

Jeff Wang, Raymond Lee

Published in American Journal of Neural Networks and Applications (Volume 7, Issue 1)

Received: 2 February 2021 Accepted: 10 February 2021 Published: 23 February 2021

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

In the past few decades, with the development of artificial intelligence and computer hardware, machine learning has been widely used in various applications including industrial, healthcare, education, finance, etc. Predicting financial time series sequences with effective AI tools for more accurate results has always been one of the hottest topics in finance and AI community. In this paper, the author introduces a new type of recurrent neural network algorithm, called Chaotic Recurrent Neural Network (CRNN), which is based on Dr. Raymond’s original research on Lee-Oscillator and Recurrent Neural Network (RNN) for worldwide financial prediction. We replaced the traditional activation function with a Lee Oscillator Neural Network, which not only can solve the vanishing gradient problem of traditional recurring neural networks during algorithm training, but can also provide an excellent memory correlation mechanism during long-term time series processing. The Experimental results reveal that CRNN outperforms than some popular neural network which widely applied to predict financial data, such as FFBPN, RNN, LSTM, in terms of forecast accuracy in certain cases. The experimental environment is based on Pytorch and Python 3.8, using 10 years (2010-2020) major financial index data, including DJI, HSI, IXIC, SPX, SSE, SZSE, APPL, to forecast 31th day closing price with previous 30 days closing price. Besides financial forecasting, our CRNN algorithm also has many potential applications, such as Natural Language Processing, weather forecasting, etc.

Published in	American Journal of Neural Networks and Applications (Volume 7, Issue 1)
DOI	10.11648/j.ajnna.20210701.12
Page(s)	7-14
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2024. Published by Science Publishing Group

Keywords

Deep Learning; Recurrent Neural Network, Chaotic Neural Network, Lee-Oscillator, FFBPN, RNN, LSTM, Financial Forecast

References

[1]	Zhou Z. Machine Learning. Tsinghua University Press, China, Beijing, 2016.
[2]	Cucu GS, Ciotec AD and Neagoe Ve. Deep Convolutional Neural Networks versus Multilayer Perceptron for financial Prediction. International Conference on communications (COMM), 2018, pp. 201-206.
[3]	J. Roman and A. Jameel. Backpropagation and Recurrent Neural Network in financial analysis of multiple stock market returns. In System Sciences, Proceeding of the Twenty-Ninth Hawaii International Conference, IEEE, 1996, pp. 2327-2333.
[4]	Sreelekshmy Selvin, Vinayakumar R, Gopalakrishnan E. A, etc. Stock Price Prediction Using LSTM, RNN and CNN-Sliding Window Model. IEEE, India, 2017.
[5]	Chaitanya Lahari M, Dhakate Hardik Ravi, R Bharathi. Fuel Price Prediction Using RNN. IEEE, India, 2018, pp. 1510-1514.
[6]	Shun Chen and Lei Ge. Exploring the attention mechanism in LSTM-based Hong Kong stock price movement prediction. Quantitative Finance, China, 2019, pp. 1507-1515.
[7]	Ferdiansyah, Siti Hajar Othman, Raja Zahilah Raja Md Radzi, etc. A LSTM-Method for Bitcoin Price Prediction: A Case Study Yahoo Finance Stock Market. International Conference on Electrical Engineering and Computer Science (ICECOS), 2019, pp. 206-210.
[8]	Krishana Kumar, Md. Tanwir Uddin Haider. Enhanced Prediction of Intra-day Stock Market Using Metaheuristic Optimization on RNN-LSTM Network. New Generation Computing, Springer, Japan, 2020.
[9]	Qihang Ma. Comparison of ARIMA, ANN and LSTM for Stock Price Prediction. ISEESE, EDP Science, Guangzhou, China, 2020.
[10]	Ian Goodfellow, Yoshua Bengio, Aaron Couville. Deep Learning. 2016, chapter 10, 10.7 The Challenge of Long-Term Dependencies, pp. 390-392.
[11]	S. Hochreiter and J. Schamidhuber. Long short-term memory. Neural Computation, vol 9, no. 8, 1997, pp. 1735-1780.
[12]	Y. Chen, B. Yang, J. Dong, and A. Abraham. Time-series forecasting using flexible neural tree model. Information Science, vol. 174, no. 3-4, pp. 219-235.
[13]	F. Giordano, M. La Rocca and C. Perna. Forecasting nonlinear time series with neural network sieve bootstrap. Computational Statistics and Data Analysis, vol. 51, no. 8, pp. 3871-3884.
[14]	M. Khashei and M. Bijari. An artificial neural network (p, d, q) model for timeseries forecasting. Expert Systems with Application, vol. 37, no. 1, 2010, pp. 478-489.
[15]	Aihara K, Takable T & Toyoda. M. Chaotic Neural Networks. Physics Letter A, 1990, 144 (6, 7).
[16]	K. M. KWONG, Max. H. Y. Wong, Raymond S. T. LEE and James N. K. LIU. Financial Trend Forecasting with Fuzzy Chaotic Oscillator-based Neural Networks (CONN). IEEE, August 20-24, 2009, Korea, pp. 1947-1952.
[17]	Freeman W. J. A proposed name for aperiodic brain activity: Stochastic chaos. Neural Networks, 13, 2000, 11-13.
[18]	Aihara K, Matsumoto G. Forced Oscillations and Route to Chaos in the Hodgkin-Huxley Axons and Squid Giant Axons. Chaos in biological systems, H. Degn, A. V. Holden & L. F. Olsen (Eds.), New York: Plenum, 1987, pp. 121-131.
[19]	Levitan I. B, Kaczmarek L. K. The Neuron. Oxford University Press, 2001.
[20]	Lee R. S. T. LEE-Associator-A Transient Chaotic Auto-association Network for Progressive Memory Recalling. Neural Networks, 19 (5), 2006, pp. 644-666.
[21]	Lee R. S. T. Chaotic Type-2 Transient-Fuzzy Deep Neuro-Oscillatory Network (CT2TFDNN) for Worldwide Financial Prediction. IEEE, TRANSACTIONS ON FUZZY SYSTEM, vol. 28, no. 4, 2019.
[22]	https://waditu.com/.
[23]	Turing Y. F. Qiu, Alex Y. C. Yuan, Peter Z. Chen, Raymond S. T. Lee. Hybrid Chaotic Radial Basis Function Neural Oscillatory Network (HCRBFNON) for Financial Forecast and Trading System. IEEE, Symposium Series on Computational Intelligence (SSCI), Xiamen, China, 2019, pp. 2811-2818.
[24]	Yifu Qiu, Raymond S. T. Lee. A Hybrid Chaotic Oscillatory Neural Network (HCONN) Based Financial Time Series Prediction System. Beijing Normal University-Hong Kong Baptist University United International College, China, 2019.
[25]	Muhammad Haseeb Arshad, Mahmoud Kassas, Alaa E. Hussein, and Mohammad A. Abido. A simple Technique for Studying Chaos Using Jerk Equation with Discrete Time Sine Map. MDPI, 2021.

Cite This Article

Plain Text BibTeX RIS

APA Style

Jeff Wang, Raymond Lee. (2021). Chaotic Recurrent Neural Networks for Financial Forecast. American Journal of Neural Networks and Applications, 7(1), 7-14. https://doi.org/10.11648/j.ajnna.20210701.12

Copy | Download

ACS Style

Jeff Wang; Raymond Lee. Chaotic Recurrent Neural Networks for Financial Forecast. Am. J. Neural Netw. Appl. 2021, 7(1), 7-14. doi: 10.11648/j.ajnna.20210701.12

Copy | Download

AMA Style

Jeff Wang, Raymond Lee. Chaotic Recurrent Neural Networks for Financial Forecast. Am J Neural Netw Appl. 2021;7(1):7-14. doi: 10.11648/j.ajnna.20210701.12

Copy | Download

@article{10.11648/j.ajnna.20210701.12,
  author = {Jeff Wang and Raymond Lee},
  title = {Chaotic Recurrent Neural Networks for Financial Forecast},
  journal = {American Journal of Neural Networks and Applications},
  volume = {7},
  number = {1},
  pages = {7-14},
  doi = {10.11648/j.ajnna.20210701.12},
  url = {https://doi.org/10.11648/j.ajnna.20210701.12},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajnna.20210701.12},
  abstract = {In the past few decades, with the development of artificial intelligence and computer hardware, machine learning has been widely used in various applications including industrial, healthcare, education, finance, etc. Predicting financial time series sequences with effective AI tools for more accurate results has always been one of the hottest topics in finance and AI community. In this paper, the author introduces a new type of recurrent neural network algorithm, called Chaotic Recurrent Neural Network (CRNN), which is based on Dr. Raymond’s original research on Lee-Oscillator and Recurrent Neural Network (RNN) for worldwide financial prediction. We replaced the traditional activation function with a Lee Oscillator Neural Network, which not only can solve the vanishing gradient problem of traditional recurring neural networks during algorithm training, but can also provide an excellent memory correlation mechanism during long-term time series processing. The Experimental results reveal that CRNN outperforms than some popular neural network which widely applied to predict financial data, such as FFBPN, RNN, LSTM, in terms of forecast accuracy in certain cases. The experimental environment is based on Pytorch and Python 3.8, using 10 years (2010-2020) major financial index data, including DJI, HSI, IXIC, SPX, SSE, SZSE, APPL, to forecast 31th day closing price with previous 30 days closing price. Besides financial forecasting, our CRNN algorithm also has many potential applications, such as Natural Language Processing, weather forecasting, etc.},
 year = {2021}
}

Copy | Download

TY  - JOUR
T1  - Chaotic Recurrent Neural Networks for Financial Forecast
AU  - Jeff Wang
AU  - Raymond Lee
Y1  - 2021/02/23
PY  - 2021
N1  - https://doi.org/10.11648/j.ajnna.20210701.12
DO  - 10.11648/j.ajnna.20210701.12
T2  - American Journal of Neural Networks and Applications
JF  - American Journal of Neural Networks and Applications
JO  - American Journal of Neural Networks and Applications
SP  - 7
EP  - 14
PB  - Science Publishing Group
SN  - 2469-7419
UR  - https://doi.org/10.11648/j.ajnna.20210701.12
AB  - In the past few decades, with the development of artificial intelligence and computer hardware, machine learning has been widely used in various applications including industrial, healthcare, education, finance, etc. Predicting financial time series sequences with effective AI tools for more accurate results has always been one of the hottest topics in finance and AI community. In this paper, the author introduces a new type of recurrent neural network algorithm, called Chaotic Recurrent Neural Network (CRNN), which is based on Dr. Raymond’s original research on Lee-Oscillator and Recurrent Neural Network (RNN) for worldwide financial prediction. We replaced the traditional activation function with a Lee Oscillator Neural Network, which not only can solve the vanishing gradient problem of traditional recurring neural networks during algorithm training, but can also provide an excellent memory correlation mechanism during long-term time series processing. The Experimental results reveal that CRNN outperforms than some popular neural network which widely applied to predict financial data, such as FFBPN, RNN, LSTM, in terms of forecast accuracy in certain cases. The experimental environment is based on Pytorch and Python 3.8, using 10 years (2010-2020) major financial index data, including DJI, HSI, IXIC, SPX, SSE, SZSE, APPL, to forecast 31th day closing price with previous 30 days closing price. Besides financial forecasting, our CRNN algorithm also has many potential applications, such as Natural Language Processing, weather forecasting, etc.
VL  - 7
IS  - 1
ER  -

Copy | Download

Author Information

Jeff Wang

Division of Computer Science and Technology, Beijing Normal University-Hong Kong Baptist University United International College, Zhuhai, China
Raymond Lee

Division of Computer Science and Technology, Beijing Normal University-Hong Kong Baptist University United International College, Zhuhai, China

Download PDF

Sections

Plain Text BibTeX RIS

APA Style

Jeff Wang, Raymond Lee. (2021). Chaotic Recurrent Neural Networks for Financial Forecast. American Journal of Neural Networks and Applications, 7(1), 7-14. https://doi.org/10.11648/j.ajnna.20210701.12

Copy | Download

ACS Style

Jeff Wang; Raymond Lee. Chaotic Recurrent Neural Networks for Financial Forecast. Am. J. Neural Netw. Appl. 2021, 7(1), 7-14. doi: 10.11648/j.ajnna.20210701.12

Copy | Download

AMA Style

Jeff Wang, Raymond Lee. Chaotic Recurrent Neural Networks for Financial Forecast. Am J Neural Netw Appl. 2021;7(1):7-14. doi: 10.11648/j.ajnna.20210701.12

Copy | Download

@article{10.11648/j.ajnna.20210701.12,
  author = {Jeff Wang and Raymond Lee},
  title = {Chaotic Recurrent Neural Networks for Financial Forecast},
  journal = {American Journal of Neural Networks and Applications},
  volume = {7},
  number = {1},
  pages = {7-14},
  doi = {10.11648/j.ajnna.20210701.12},
  url = {https://doi.org/10.11648/j.ajnna.20210701.12},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajnna.20210701.12},
  abstract = {In the past few decades, with the development of artificial intelligence and computer hardware, machine learning has been widely used in various applications including industrial, healthcare, education, finance, etc. Predicting financial time series sequences with effective AI tools for more accurate results has always been one of the hottest topics in finance and AI community. In this paper, the author introduces a new type of recurrent neural network algorithm, called Chaotic Recurrent Neural Network (CRNN), which is based on Dr. Raymond’s original research on Lee-Oscillator and Recurrent Neural Network (RNN) for worldwide financial prediction. We replaced the traditional activation function with a Lee Oscillator Neural Network, which not only can solve the vanishing gradient problem of traditional recurring neural networks during algorithm training, but can also provide an excellent memory correlation mechanism during long-term time series processing. The Experimental results reveal that CRNN outperforms than some popular neural network which widely applied to predict financial data, such as FFBPN, RNN, LSTM, in terms of forecast accuracy in certain cases. The experimental environment is based on Pytorch and Python 3.8, using 10 years (2010-2020) major financial index data, including DJI, HSI, IXIC, SPX, SSE, SZSE, APPL, to forecast 31th day closing price with previous 30 days closing price. Besides financial forecasting, our CRNN algorithm also has many potential applications, such as Natural Language Processing, weather forecasting, etc.},
 year = {2021}
}

Copy | Download

TY  - JOUR
T1  - Chaotic Recurrent Neural Networks for Financial Forecast
AU  - Jeff Wang
AU  - Raymond Lee
Y1  - 2021/02/23
PY  - 2021
N1  - https://doi.org/10.11648/j.ajnna.20210701.12
DO  - 10.11648/j.ajnna.20210701.12
T2  - American Journal of Neural Networks and Applications
JF  - American Journal of Neural Networks and Applications
JO  - American Journal of Neural Networks and Applications
SP  - 7
EP  - 14
PB  - Science Publishing Group
SN  - 2469-7419
UR  - https://doi.org/10.11648/j.ajnna.20210701.12
AB  - In the past few decades, with the development of artificial intelligence and computer hardware, machine learning has been widely used in various applications including industrial, healthcare, education, finance, etc. Predicting financial time series sequences with effective AI tools for more accurate results has always been one of the hottest topics in finance and AI community. In this paper, the author introduces a new type of recurrent neural network algorithm, called Chaotic Recurrent Neural Network (CRNN), which is based on Dr. Raymond’s original research on Lee-Oscillator and Recurrent Neural Network (RNN) for worldwide financial prediction. We replaced the traditional activation function with a Lee Oscillator Neural Network, which not only can solve the vanishing gradient problem of traditional recurring neural networks during algorithm training, but can also provide an excellent memory correlation mechanism during long-term time series processing. The Experimental results reveal that CRNN outperforms than some popular neural network which widely applied to predict financial data, such as FFBPN, RNN, LSTM, in terms of forecast accuracy in certain cases. The experimental environment is based on Pytorch and Python 3.8, using 10 years (2010-2020) major financial index data, including DJI, HSI, IXIC, SPX, SSE, SZSE, APPL, to forecast 31th day closing price with previous 30 days closing price. Besides financial forecasting, our CRNN algorithm also has many potential applications, such as Natural Language Processing, weather forecasting, etc.
VL  - 7
IS  - 1
ER  -

Copy | Download